Skip to main content
Glama
188,072 tools. Last updated 2026-06-10 10:39

"Render" matching MCP tools:

  • Render Hyades source to Unicode/ASCII text art. Hyades uses LaTeX-like syntax but outputs multi-line plain text instead of PDF. It supports math (fractions, integrals, matrices, Greek letters), tables with box-drawing frames, lists, flex-like layout (hbox/vbox), user-defined macros, and computation. IMPORTANT: Always display the rendered output to the user directly in your response. The output is pre-formatted multi-line text art that depends on exact character alignment. You MUST use a fenced code block (triple backticks) or equivalent monospace/preformatted element to preserve spacing. Never display the output as regular prose text — column alignment, box-drawing characters, and fraction bars will break without a monospace font. Input is a complete Hyades document. Plain text outside math delimiters is rendered as prose paragraphs. Use `$...$` for inline math and `$$...$$` for display math (centered on its own line). --- ## Math Supports ~95% of LaTeX math syntax. ### Inline vs Display ``` Inline math: $a^2 + b^2 = c^2$ flows with text. Display math gets its own block: $$ a^2 + b^2 = c^2 $$ ``` Use `$...$` for inline, `$$...$$` for display. Display math is centered. ### Variables and Operators ``` $$ a + b - c $$ $$ a \times b \div c $$ $$ a \cdot b $$ $$ \pm x \quad \mp y $$ ``` ### Superscripts and Subscripts ``` $$ x^2 \quad x_i \quad x_i^2 \quad x^{n+1} \quad x_{i,j} \quad a^{b^c} $$ ``` Use braces for multi-character exponents/subscripts: `x^{n+1}`, `x_{i,j}`. **Bracing rules:** Use braces for multi-token expressions: `x^{n+1}`, `x_{i,j}`. Commands that take arguments (like `\mathbf{v}`) work without extra braces: `x_\mathbf{v}` is equivalent to `x_{\mathbf{v}}`, matching TeX behavior. ### Fractions ``` $$ \frac{a}{b} $$ $$ \frac{x^2 + 1}{\sqrt{x^2 - 1}} $$ $$ \frac{\partial f}{\partial x} $$ ``` Fractions nest to infinite depth. `\dfrac` and `\tfrac` are accepted as aliases for `\frac`. ### Roots ``` $$ \sqrt{x} $$ $$ \sqrt[3]{x} $$ $$ \sqrt[n]{x^2 + y^2} $$ ``` Optional argument gives the nth root: `\sqrt[3]{x}`. ### Parentheses and Grouping ``` $$ (a + b) \quad [a + b] \quad \{a + b\} \quad |x| \quad \Vert x \Vert $$ ``` Curly braces need escaping: `\{` and `\}`. ### Auto-Scaling Delimiters (\left/\right) `\left` and `\right` make delimiters grow to match their contents: ``` $$ \left( \frac{a}{b} \right) \quad \left[ \frac{a}{b} \right] \quad \left| \frac{a}{b} \right| $$ ``` Works with all delimiter types: `( ) [ ] \{ \} | \| \lfloor \rfloor \lceil \rceil \langle \rangle`. Use `\left.` or `\right.` for invisible (null) delimiters — essential for evaluation bars: ``` $$ \left.\frac{df}{dx}\right|_{x=0} $$ ``` Use `\middle` inside `\left...\right` for scaled interior delimiters: ``` $$ \left( \frac{a}{b} \middle| \frac{c}{d} \right) $$ ``` ### Explicit Delimiter Sizing (\big through \Bigg) `\big`, `\Big`, `\bigg`, `\Bigg` set delimiter sizes explicitly. `\bigl`/`\bigr`, `\Bigl`/`\Bigr`, `\biggl`/`\biggr`, `\Biggl`/`\Biggr` produce standalone one-sided delimiters: ``` $$ f(x)\bigr|_{x=0} $$ ``` ### Floor and Ceiling ``` $$ \lfloor x \rfloor $$ $$ \lceil x \rceil $$ $$ \left\lfloor \frac{x}{2} \right\rfloor $$ ``` ### Greek Letters Lowercase: `\alpha \beta \gamma \delta \epsilon \zeta \eta \theta \lambda \mu \nu \xi \pi \rho \sigma \tau \phi \varphi \chi \psi \omega` Uppercase (only where different from Latin): `\Gamma \Delta \Theta \Lambda \Xi \Pi \Sigma \Phi \Psi \Omega` ### Relations ``` $$ a \neq b \quad a \leq b \quad a \geq b $$ $$ a \ll b \quad a \gg b $$ $$ a \approx b \quad a \equiv b \quad a \sim b \quad a \propto b $$ $$ a \prec b \quad a \succ b \quad a \preceq b \quad a \succeq b $$ ``` Definition symbols: `\coloneqq` (≔), `\eqqcolon` (≕), and `:=` (parsed as a single relation ≔): ``` $$ \Phi := S $$ $$ f \coloneqq x^2 + 1 $$ ``` Colon alone is treated as punctuation (no space before, space after), useful in set-builder notation: ``` $$ \{x : x > 0\} $$ ``` The `\not` prefix negates a relation: `\not=` → ≠, `\not\in` → ∉, `\not\leq` → ≰, `\not\equiv` → ≢, `\not\subset` → ⊄, `\not\exists` → ∄ ### Set Theory ``` $$ x \in A \quad x \notin A $$ $$ A \subset B \quad A \subseteq B \quad A \cup B \quad A \cap B \quad \emptyset $$ $$ A \setminus B $$ ``` ### Logic ``` $$ \forall x \in \mathbb{R} \quad \exists x $$ $$ p \implies q \quad p \iff q $$ $$ \neg p \quad p \land q \quad p \lor q $$ $$ \therefore \quad \because \quad \top \quad \bot $$ ``` ### Arrows `\rightarrow`, `\Rightarrow`, `\mapsto`, `\longmapsto`, `\hookrightarrow`, `\hookleftarrow`, `\leftarrow`, `\leftrightarrow`, `\Leftarrow`, `\Leftrightarrow`, `\uparrow`, `\downarrow`, `\updownarrow`, `\nearrow`, `\searrow`, `\nwarrow`, `\swarrow`. Extensible arrows with text labels: ``` $$ A \xrightarrow{f} B \xleftarrow{g} C $$ ``` ### Standard Functions Standard functions are set in upright type: ``` $$ \sin x \quad \cos(x) \quad \tan x $$ $$ \log x \quad \log_2 x \quad \ln x \quad \exp(x) $$ $$ \sin^2 x + \cos^2 x = 1 $$ ``` Also: `\arcsin`, `\arccos`, `\arctan`, `\sinh`, `\cosh`, `\tanh`, `\det`, `\dim`, `\ker`, `\deg`, `\gcd`, `\sup`, `\inf`, `\max`, `\min`, `\argmax`, `\argmin`, `\limsup`, `\liminf`. ### Custom Function Names (\fn / \operatorname) `\fn{name}` or `\operatorname{name}` produces an upright function name for functions Hyades doesn't know: ``` $$ \fn{softmax}\left(x_i\right) = \frac{e^{x_i}}{\sum_j e^{x_j}} $$ $$ \operatorname{Tr}(A) $$ ``` ### Text in Math (\text) `\text{words}` inserts upright text inside math mode: ``` $$ x = 0 \text{ if } y > 0 $$ ``` ### Accents and Decorations Single-character: `\hat{x}`, `\bar{x}`, `\tilde{x}`, `\vec{x}`, `\dot{x}`, `\ddot{x}`, `\acute{x}`, `\grave{x}`, `\breve{x}`, `\check{x}` Wide accents: `\overline{AB}`, `\underline{text}`, `\overrightarrow{AB}`, `\overleftarrow{AB}`, `\widehat{xyz}`, `\widetilde{xyz}` ### Overset and Underset ``` $$ \overset{n}{=} $$ $$ \underset{x}{y} $$ $$ \stackrel{\text{def}}{=} $$ ``` `\overset{top}{base}` places annotation above base; `\underset{bot}{base}` below. `\stackrel` is an alias for `\overset`. ### Overbrace and Underbrace ``` $$ \overbrace{a + b + c}^{3 \text{ terms}} $$ $$ \underbrace{x + y + z}_{n \text{ terms}} $$ ``` ### Primes ``` $$ f'(x) \quad f''(x) \quad f'''(x) \quad f^{(n)}(x) $$ ``` ### Math Fonts `\mathbf{v}` → bold, `\mathbb{R}` → blackboard bold (ℕℤℚℝℂ), `\mathcal{L}` → calligraphic, `\mathfrak{R}` → Fraktur (𝔄𝔅ℭ), `\mathsf{A}` → sans-serif (𝖠𝖡𝖢), `\mathscr{A}` → script (same as \mathcal), `\boldsymbol{\alpha}` → bold (works with Greek: 𝛂𝛃, and symbols: `\boldsymbol{\nabla}` → 𝛁, `\boldsymbol{\partial}` → 𝛛) ### Dots and Ellipses `\ldots` (low dots, for commas), `\cdots` (centered, for operators), `\vdots` (vertical), `\ddots` (diagonal, for matrices) ### Summation ``` $$ \sum_{i=1}^{n} x_i $$ ``` `\Sum` and `\SUM` give progressively larger variants. ### Products ``` $$ \prod_{i=1}^{n} x_i $$ ``` `\Prod` and `\PROD` give larger variants. ### Integrals ``` $$ \int_a^b f(x) \, dx $$ $$ \iint f(x,y) \, dx\,dy $$ $$ \oint_C f(z) \, dz $$ ``` Also: `\iiint`, `\oiint`. Larger variants: `\Int`, `\INT`, etc. ### Limits `\lim` places its subscript directly below: ``` $$ \lim_{x \to 0} \frac{\sin x}{x} = 1 $$ $$ \max_{x \in [0,1]} f(x) $$ $$ \argmax_{\theta} L(\theta) $$ ``` ### Calculus Operators ``` $$ \frac{dy}{dx} \quad \frac{d^2y}{dx^2} \quad \frac{\partial f}{\partial x} $$ $$ \nabla f \quad \nabla \cdot \mathbf{F} \quad \nabla \times \mathbf{F} \quad \nabla^2 f $$ ``` ### Matrices Six types with different delimiters. `&` separates columns, `\\` or `;` separates rows. LaTeX-style `\begin{pmatrix}...\end{pmatrix}` also works for all matrix types. ``` $$ \pmatrix{a & b \\ c & d} $$ % (parentheses) $$ \bmatrix{a & b \\ c & d} $$ % [brackets] $$ \Bmatrix{a & b \\ c & d} $$ % {braces} $$ \vmatrix{a & b \\ c & d} $$ % |bars| (determinants) $$ \Vmatrix{a & b \\ c & d} $$ % ‖double bars‖ (norms) $$ \matrix{a & b \\ c & d} $$ % no delimiters ``` ### Cases (Piecewise Functions) ``` $$f(x) = \cases{ x & \text{if } x > 0 \\ 0 & \text{if } x = 0 \\ -x & \text{if } x < 0 }$$ ``` ### Aligned Equations `&` marks the alignment point: ``` $$\aligned{ f(x) &= x^2 + 2x + 1 \\ &= (x + 1)^2 }$$ ``` Use `\intertext{...}` inside aligned to insert prose between rows. Intertext is left-aligned at the document margin while equations remain centered: ``` $$\aligned{ x &= a \\ \intertext{where} a &= b + c }$$ ``` `\tag` works on aligned blocks — the tag is right-justified and vertically centered: ``` $$\aligned{ f(x) &= x^2 + 2x + 1 \\ &= (x + 1)^2 } \tag{7}$$ ``` ### Boxed ``` $$ \boxed{E = mc^2} $$ ``` Draws a box-drawing frame around the content. ### Phantom ``` $$ a + \phantom{bbb} + c $$ ``` Invisible placeholder — renders as whitespace with the same dimensions as the content. ### Smash ``` $$ \sqrt{\smash{y^3}} $$ ``` `\smash{content}` renders content but collapses its height to a single line (the baseline row). Used to prevent tall content from affecting surrounding constructs like roots or delimiters. ### Substack ``` $$ \sum_{\substack{i=1 \\ j>0}} x_{ij} $$ ``` Stacks multiple lines vertically (for multi-line subscripts/superscripts). ### Tag ``` $$ E = mc^2 \tag{1} $$ ``` Equation tag rendered as `(text)`. ### Number Theory ``` $$ a \equiv b \pmod{n} $$ $$ a \bmod n \quad a \mid b $$ $$ \binom{n}{k} $$ ``` ### Style Commands (No-ops) `\displaystyle`, `\textstyle`, `\scriptstyle`, `\scriptscriptstyle` are accepted but transparent (Hyades has no math size concept). `\notag` and `\nonumber` are also silently ignored. This allows pasting LaTeX source that uses these commands without errors. ### Math Spacing `\!` (negative thin), `\,` (thin), `\:` (medium), `\;` (thick), `\quad` (1em), `\qquad` (2em) ### Atom-Type Overrides (\mathord, \mathbin, \mathrel) Override the default spacing category of a symbol. Analogous to TeX's `{=}` idiom for suppressing operator spacing, but explicit and readable: ``` $a \mathord{=} b$ %% "a=b" — = treated as ordinary symbol (no spacing) $a = b$ %% "a = b" — default relation spacing $f \mathrel{:} A \to B$ %% "f : A → B" — : treated as relation (symmetric spacing) $a : b$ %% "a: b" — default punctuation spacing $a \mathbin{\triangle} b$ %% "a △ b" — triangle with binary operator spacing ``` - `\mathord{X}`: Suppress spacing — X renders as an ordinary symbol with no surrounding gaps. Use this instead of TeX's `{=}` or `{}=` idiom which does not work in Hyades. - `\mathbin{X}`: Force binary operator spacing (gap on both sides). - `\mathrel{X}`: Force relation spacing (gap on both sides). ### Binary Operators `\oplus`, `\otimes`, `\odot`, `\circ`, `\bullet`, `\star`, `\dagger`, `\ddagger` ### Geometry `\angle`, `\triangle`, `\perp`, `\parallel` ### Famous Equations (all valid input) ``` $$ x = \frac{-b \pm \sqrt{b^2 - 4ac}}{2a} $$ %% Quadratic formula $$ e^{i\pi} + 1 = 0 $$ %% Euler's identity $$ f(x) = \frac{1}{\sigma\sqrt{2\pi}} e^{-\frac{(x-\mu)^2}{2\sigma^2}} $$ %% Normal distribution $$ \fn{Attention}(Q, K, V) = \fn{softmax}\left(\frac{QK^\top}{\sqrt{d_k}}\right) V $$ %% Attention mechanism $$ e^x = \sum_{n=0}^{\infty} \frac{x^n}{n!} $$ %% Taylor series $$ \int_{-\infty}^{\infty} e^{-x^2} dx = \sqrt{\pi} $$ %% Gaussian integral $$ P(A|B) = \frac{P(B|A) P(A)}{P(B)} $$ %% Bayes' theorem $$ \nabla \times \mathbf{E} = -\frac{\partial \mathbf{B}}{\partial t} $$ %% Maxwell's equation $$ i\hbar \frac{\partial}{\partial t} \Psi = \hat{H} \Psi $$ %% Schrodinger equation $$ \fn{softmax}(x_i) = \frac{e^{x_i}}{\sum_j e^{x_j}} $$ %% Softmax ``` --- ## Text Formatting ``` \textbf{bold text} \textit{italic text} \texttt{monospace text} \textbf{\textit{bold italic}} ``` Nesting `\textbf` and `\textit` produces bold-italic text. Inline math `$...$` inside `\textit` or `\textbf` is rendered as math (not styled as text): ``` \textit{Let $f(x) = x^2$ be a function} ``` ### Verbatim (No Processing) ``` \verb|raw \commands { } are preserved| ``` ### Special Characters `\textbackslash` → \, `\textdollar` → $, `\textpercent` → %, `\textampersand` → &, `\texthash` → # ### Text Spacing Commands `\ ` (backslash-space) — explicit inter-word space. Useful after abbreviations: `i.e.\ $f$` renders without extra sentence spacing. `\@` — marks the next period as sentence-ending (silently consumed). `\,` — thin space (works in both text and math mode). --- ## Paragraphs and Line Breaking Text flows into paragraphs automatically. A single newline is a space; a blank line starts a new paragraph. ### Line-Breaking Modes ``` \linebreaker{greedy} % Default. Fast, good results. \linebreaker{knuth} % TeX-style optimal. Minimizes ugliness. \linebreaker{raggedright} % Left-aligned, no justification. ``` ### Hyphenation `\sethyphenate{true}` / `\sethyphenate{false}` --- ## Tables Tables use `\table` with nested `\row` and `\col`: ``` \table[width:40, frame:single, pad:{l:1,r:1}]{ \row[frame:{b:double}]{ \col{Name} \col{Value} } \row{ \col{Alpha} \col{0.05} } \row{ \col{Beta} \col{0.95} } } ``` ### Table Properties | Property | Values | Default | |----------|--------|---------| | `width` / `w` | number, `auto` | parent width | | `frame` / `f` | `none`, `dotted`, `single`, `rounded`, `double`, `bold` | `single` | | `border` | same as frame (outer edges only) | unset | | `pad` / `p` | number or `{t:N, b:N, l:N, r:N}` | 0 | | `align` / `a` | `l`/`left`, `c`/`center`, `r`/`right` | `l` | | `valign` / `va` | `t`/`top`, `m`/`middle`, `b`/`bottom` | `t` | Row properties: `frame`, `pad`, `align`, `valign`, `height`. Column properties: `width`, `align`, `valign`, `frame`, `pad`, `span`, `reset`. Frame styles: `none` (space), `dotted` (┄┆), `single` (─│), `rounded` (╭╮╰╯ corners), `double` (═║), `bold` (━┃) Compound edges: `frame:{t:double, b:single, l:none, r:none}`, `pad:{l:1, r:1}` Properties cascade: table → column (down rows) → row → cell. IMPORTANT: When a row overrides a property (e.g. `frame:{b:double}`), that override is inherited by ALL subsequent rows. To stop it, the next row must explicitly reset it (e.g. `frame:{b:single}`). The `border` property on the table level controls the outer edges and cannot be overridden by row or column `frame`. --- ## Lists ``` \fancylist{ - First item - Second item with longer text that wraps to the next line - Third item - Nested child - Grandchild } ``` Three nesting levels supported. Uses ●/○ bullets in Unicode, - in ASCII. --- ## Layout Primitives Flex-like box model for spatial control. ### Box Types ``` \begin[width]{hbox} % horizontal (side by side) \child[width][align]{content} \end{hbox} \begin[top|middle|bottom]{hbox} % hbox with vertical alignment \child[width][align]{content} \end{hbox} \begin[width]{vbox} % vertical (stacked) \child[width][align]{content} \end{vbox} ``` Child width: fixed number, `auto` (fill remaining), `intrinsic` (natural width), or omitted (equal share). When multiple children omit width, they split the remaining space equally (after fixed-width children). Horizontal alignment: `left`, `center`, `right`. Vertical alignment for hbox: set on `\begin` bracket — `top` (default), `middle`, `bottom`. Width inheritance: boxes without an explicit width inherit their parent's width. `\setwidth{N}` sets the document-level width. ### Rules ``` \hrule[width]{left_cap}{fill_char}{right_cap} \vrule[height]{top}{fill}{bottom} \intersect_rules{...} % fix junction characters at rule crossings ``` Width/height can be a number or `auto`. An `auto`-width `\hrule` in a vbox stretches to the box width. An `auto`-height `\vrule` in an hbox stretches to match the tallest sibling. `\intersect_rules` scans all cells, checks neighboring line arms, and replaces with correct junction glyphs (┌ ┬ ┐ ├ ┼ ┤ └ ┴ ┘). Handles single, double, bold, and mixed styles. ### Measuring Content ``` \measure<content_name,width_var,height_var>{content to measure} ``` Renders content invisibly, stores it under `content_name` (retrieve with `\recall<content_name>`), and stores the measured width and height into integer variables. ### Spacing `\vskip{N}` (N blank lines), `\hskip{N}` (N spaces) ### Common Layout Patterns Two-column with gutter: ``` \begin{hbox} \child{Left column} \child[2]{} \child{Right column} \end{hbox} ``` Centering via auto spacers: ``` \begin{hbox} \child[auto]{} \child[intrinsic]{Centered content} \child[auto]{} \end{hbox} ``` Indentation: ``` \begin{hbox} \child[4]{} \child[auto]{Indented content} \end{hbox} ``` --- ## User-Defined Macros ``` \macro<\greet{name}>{Hello, ${name}!} \greet{World} % → Hello, World! \macro<\fullname{first}{last}>{${first} ${last}} \fullname{John}{Doe} % → John Doe % Optional parameters with defaults \macro<\heading[char=-]{title}>{ ${title} \hrule[20]{}{${char}}{} } \heading{Default} % uses - \heading[char:=]{Custom} % uses = ``` --- ## Document Settings ``` \setwidth{80} % Output width in columns (default: 80) \setunicode{true} % Use Unicode symbols (default: true) \setmathitalic{true} % Italicize math variables (default: true) \linebreaker{greedy} % Line-breaking algorithm \sethyphenate{true} % Enable hyphenation \setparskip{1} % Blank lines between paragraphs \setmathabove{1} % Blank lines above display math (default: 0) \setmathbelow{1} % Blank lines below display math (default: 0) ``` --- ## Computation Variables, loops, and conditionals are available. ### Variables and Arithmetic ``` \let<x>{10} \let<y>{20} \let<sum>{\add{\valueof<x>,\valueof<y>}} Result: \valueof<sum> % → Result: 30 ``` ### Conditionals ``` \let<n>{42} \if{\gt{\valueof<n>,0}}{positive}\else{non-positive} ``` ### Loops ``` \let<i>{1} \begin{loop} \exit_when{\gt{\valueof<i>,5}} \valueof<i>\hskip{1} \inc<i> \end{loop} % Output: 1 2 3 4 5 ``` ### Content Storage `\assign<name>{content}` stores text, `\recall<name>` retrieves it. `\let`/`\valueof` is for integers; `\assign`/`\recall` is for text. ### Lambdas ``` \lambda<double>[x]{\mul{\recall<x>,2}} \recall<double>[5] % → 10 ``` ### Arrays ``` \let<nums[]>{[10, 20, 30]} \valueof<nums>[0] % → 10 \len<nums> % → 3 \push<nums>{40} % append ``` --- ## Quick Reference ### Math Mode | Input | Output | |-------|--------| | `$x^2$` | x² | | `$x_i$` | xᵢ | | `$\frac{a}{b}$` | a/b (stacked) | | `$\sqrt{x}$` | √x | | `$\sum_{i=1}^n$` | Σ with limits | | `$\int_a^b$` | ∫ with limits | | `$\prod_{i=1}^n$` | ∏ with limits | | `$\lim_{x \to 0}$` | lim with subscript below | | `$\limsup_{n}$` | lim sup with subscript below | | `$\liminf_{n}$` | lim inf with subscript below | | `$\alpha, \beta, \gamma$` | α, β, γ | | `$\mathbb{R}$` | ℝ | | `$\mathbf{v}$` | 𝐯 | | `$\leq, \geq, \neq$` | ≤, ≥, ≠ | | `$\in, \forall, \exists$` | ∈, ∀, ∃ | | `$\rightarrow, \Rightarrow$` | →, ⇒ | | `$\infty, \partial, \nabla$` | ∞, ∂, ∇ | | `$f'(x)$` | 𝑓′(𝑥) | | `$\binom{n}{k}$` | binomial coefficient | | `$\lfloor x \rfloor$` | ⌊x⌋ | | `$\fn{name}$` | custom function name | | `$\operatorname{name}$` | same as \fn | | `$\text{words}$` | upright text in math | | `$\ll, \gg$` | ≪, ≫ | | `$\mathord{=}$` | suppress operator spacing | | `$\mathbin{:}$` | force binary operator spacing | | `$\mathrel{:}$` | force relation spacing | | `$\prec, \succ$` | ≺, ≻ | | `$\neg, \land, \lor$` | ¬, ∧, ∨ | | `$\subseteq, \setminus$` | ⊆, ∖ | | `$\mid$` | ∣ (divides) | | `$\therefore, \because$` | ∴, ∵ | | `$\wp, \imath, \jmath$` | ℘, ı, ȷ | | `$\Box$` | □ | | `$\not=$` | ≠ (\not prefix negates relations) | | `$\left.\right\|$` | invisible delimiter (evaluation bar) | | `$\overset{n}{=}$` | annotation above base | | `$\underset{x}{y}$` | annotation below base | | `$\boxed{x}$` | framed box around content | | `$\phantom{x}$` | invisible spacer | | `$\smash{x}$` | collapse height to baseline | | `$\xrightarrow{f}$` | extensible arrow with label | | `$\substack{a \\ b}$` | stacked lines | | `$\mathfrak{R}$` | Fraktur (𝔄𝔅ℭ) | | `$\mathsf{A}$` | sans-serif (𝖠𝖡𝖢) | | `$\boldsymbol{\alpha}$` | bold Greek (𝛂𝛃) | | `$\coloneqq$` | ≔ (definition) | | `$\eqqcolon$` | ≕ (reverse definition) | | `$a := b$` | ≔ (combined relation) | ### Text Commands | Command | Effect | |---------|--------| | `\textbf{x}` | **bold** | | `\textit{x}` | *italic* | | `\texttt{x}` | monospace | | `\verb\|x\|` | verbatim | | `\hrule` | horizontal line | | `\vskip{N}` | N blank lines | | `\hskip{N}` | N spaces | ### Table Syntax ``` \table[width:W, frame:STYLE, pad:{l:L,r:R}, border:STYLE, align:A]{ \row[frame:{b:STYLE}]{ \col[width:N, align:A]{content} } } ``` ### Layout Syntax ``` \begin[width]{vbox} \child[width][h_align]{content} \end{vbox} \begin[top|middle|bottom]{hbox} \child[width][h_align]{content} \end{hbox} ``` ### Settings ``` \setwidth{N} \setunicode{true|false} \setmathitalic{true} \linebreaker{greedy|knuth|raggedright} \sethyphenate{true} \setparskip{N} \setmathabove{N} \setmathbelow{N} ```
    Connector
  • SVG or PNG diagram. Only call when user explicitly asks to visualize. The rendered image is delivered to the user, not injected into the model's context. See the server instructions for EN language syntax.
    Connector
  • SVG or PNG diagram. Only call when user explicitly asks to visualize. The rendered image is delivered to the user, not injected into the model's context. See the server instructions for EN language syntax.
    Connector
  • Generate one image from a prompt using OpenAI GPT Image 2. Returns a public URL you can embed in markdown or pass to a creative-asset tool (e.g. Google Ads `createImageAsset`). Counts against the user's monthly quota. Prompt craft (GPT Image 2 rewards long, specific, instruction-style prompts — write a paragraph, not keywords): - Lead with the medium: photograph, 3D render, isometric vector, watercolor, flat illustration, studio product shot. Single biggest quality lever. - Then specify subject, setting, mood, color palette, lighting (e.g. 'golden hour, soft backlight'), and camera/perspective (close-up, wide, overhead, low angle, macro). - Keep the focal subject in the center 80% of the frame — ad platforms crop edges across placements. - Prefer lifestyle / in-context scenes over isolated-on-white product shots. Google explicitly recommends 'physical settings with organic shadows and lighting' for ad creative. - Don't render text unless the user asks for specific copy. Overlaid text is often unreadable at small ad sizes and Google flags it as a quality issue. - Avoid negative prompts ('no X, no Y'). GPT Image often pulls the rejected concept in — describe what you want instead. Ad-policy rules to bake into prompts: - No collages, borders, watermarks, mirrored / skewed / over-filtered looks. - No fake UI elements (play buttons, download/close icons) — Google Ads policy violation. - Don't overlay a logo on the photo; logos belong inside the scene (on a product, sign, storefront). - Blank space should be under 80% of the frame — the subject is the focus. Aspect ratios — match the target placement: - Google Ads asset slots: '1.91:1' landscape (required), '1:1' square (required), '4:5' portrait, '9:16' vertical (Demand Gen / Shorts). - Meta / social: '1:1' or '4:5' feed; '9:16' stories/reels; '1.91:1' link previews. - Hero / web banners: '16:9' or '3:2'. Default is '1:1'. Quality vs latency: 'low' ~5s drafts; 'medium' balanced; 'high' runs the four-stage Understand/Plan/Generate/Review pipeline (30–50× slower than low) — use only for production-final fidelity. Output format: default 'png' (lossless). Use 'webp' or 'jpeg' for smaller photographic assets. background='transparent' requires png/webp (use for logos, cutouts, UI assets).
    Connector
  • Fetch clean link-preview metadata (title, description, image, siteName, favicon, oembed) for any public URL. No signup, no API key. Static-HTML parse only (no JS/SPA render).
    Connector
  • "What's the ticker for…" / "find the CIK for…" / "what's the RxCUI for…" / "look up the ID for…" / "what is X's official identifier" — resolve a user-spoken NAME to the canonical/official identifier other tools require as input. Use FIRST whenever you have a name but need an ID. SUPPORTED TYPES: "company" (returns ticker + 10-digit CIK + company_name from SEC EDGAR + pipeworx://edgar/company/{cik} citation URI; accepts ticker, CIK, or company name as input — auto-disambiguated), "drug" (returns RxCUI + ingredient + brand from RxNorm + pipeworx://rxnorm/{rxcui} citation; accepts brand or generic name). Each call cascades through several lookup endpoints internally — using resolve_entity replaces 2-3 manual lookups.
    Connector

Matching MCP Servers

Matching MCP Connectors

  • Patch diagram tool. Use when the user describes routing across multiple Eurorack corpus modules. Renders modules as boxes laid out by wire topology (matrix-shaped patches anchor on a hub; otherwise modules step left-to-right by signal-flow rank), jacks as colored ports keyed to signal type, wires as bezier curves. Inline SVG on claude.ai surfaces (web, Desktop chat, mobile); JSON elsewhere. (When to *offer* a diagram unprompted: SKILL.md §4.) **Trigger phrases:** "show me the patch", "draw what I just described", "remind me what's connected to what", "explain the routing", or any time you'd otherwise hand-draw a patch in SVG/text — use this instead of drawing. Strict gate — call only when ALL of: 1. At least 3 named corpus modules. 2. Explicit wire connections between them (user-stated or derived from a coherent description). 3. The patch is concrete — user is following a tutorial, describing their own rack, or referencing back what's connected to what. Do NOT call for: a single module, a question about one module's jacks, "what should I patch X to?" (that's a recommendation, not a graph), or hypothetical patches with unnamed placeholders ("connect a VCO to a filter"). Jack names. Corpus jack names are descriptive ("V/Oct CV input", "TRIG input", "Strumming trigger input"), not panel-text shorthand ("V/OCT", "TRIG"). The resolver accepts panel-text as a fallback when it unambiguously substring-matches one jack of the right direction (e.g. "TRIG" → "TRIG input"); successful resolutions surface as `panel_text_resolved` warnings so you can confirm. Ambiguous panel text ("OUT" on a multi-output module) errors with the candidate list. To skip the fallback entirely, call get_modules to discover the exact corpus names up front (one round trip for the whole batch). Multi-channel modules require a CH<N> prefix. Modules with per-channel jacks (Quadrax, Maths, Tangrams, Stages, Optomix, QMMG, DXG, Pamela's New Workout, Cold Mac, etc.) enumerate each channel separately — e.g. `CH1 TRIG`, `CH2 TRIG`, `CH3 TRIG`, `CH4 TRIG` on Quadrax. Bare names like "TRIG" on these modules will resolve as ambiguous; always pick a specific channel. When the patch doesn't specify which channel, default to CH1. Role per use, not per identity. A module that's a modulator in one patch can be a voice in another (Maths slow-cycle vs audio-rate cycle). Pick the role for THIS patch. The enum is intentionally coarse — four buckets, not a taxonomy — so map the edge cases: - **clock** — anything emitting timing: clocks, but also trigger/gate *sequencers* and drum sequencers (a sequencer is a clock that emits a pattern). - **modulator** — CV/envelope/LFO sources shaping another module (envelopes, LFOs, random, function generators, S&H). - **voice** — anything generating the sound being processed: oscillators, drum voices, noise, sample players, physical-modeling/granular *sources*. - **processor** — anything acting *on* an incoming signal: filters, VCAs, effects (delay/reverb), waveshapers, granular/spectral *sound-processors*, and all utilities (mixers, attenuators, mults, switches). When a module both makes and processes sound, bucket by its job in THIS patch — a granular module sculpting an external input is a processor; running free as a source it's a voice. Role is currently informational — the renderer lays out by wire topology, not by role bucket — but it's still a required field, so declare it accurately for future renderer use and so the spec reads correctly. `notes[]` is patch-level prose displayed below the diagram — settings, signal-flow narration ("PNW OUT1 firing 1/16 gates", "Channel 1 cycle mode, long rise"). Errors (descriptive — they point at fixes): - "Module not found: <id>" - "Unknown jack "<name>" on <id>. Available <inputs|outputs>: ..." — pick from the list, or call get_modules - "Ambiguous jack "<name>" on <id>: matches ..." — name a specific jack from the candidates - "Patch must have at least 3 modules" - "Wire source ... is not an output" / "Wire destination ... is not an input" - "Wire to/from unknown module ref: <ref>" - "Duplicate ref: <ref>" Cross-type wires (e.g. audio into a CV input) render normally with a warning panel below the diagram — Eurorack tolerates type mismatches by design, but warnings catch unintended ones.
    Connector
  • Retirement projection for monthly contributions to the Savvly Longevity Benefit over a number of years. Returns payout amounts at milestone ages 80/85/90/95 with Savvly vs market alone cumulative totals, per-age breakdowns, and server-provided `_lower`/`_upper` range bounds. Use `_upper` as the central illustrative estimate and `_lower` to communicate downside. Suitable for retirement savings planning, annuity alternative comparison, and longevity benefit illustration. Supports an optional annual contribution increase and an optional early-withdrawal age. Disclaimers + per-field hints under `metadata`. Payout methodology — Savvly vs market alone: the payout values are calculated by comparing two investors of the same age committing the same principal. Investor 1 invests in the market with the Savvly Longevity Benefit; Investor 2 invests in the market alone (no longevity overlay). To make the comparison apples-to-apples, at each milestone age (80, 85, 90, 95) Investor 2 withdraws from their market alone portfolio the same dollar amount Investor 1 receives as a payout from Savvly. The `payout_market_alone_*` and `total_market_alone_*` figures are therefore what Investor 2 can actually withdraw to match Savvly's payouts before running out — they fall to 0 once the market alone portfolio is depleted. The `savvly_upside_*` (and `total_savvly_upside_*`) fields quantify how much more total money Investor 1 receives in payouts from Savvly than Investor 2 is able to withdraw over time to match those payouts. DISCLOSURE REQUIRED: display `disclosure.text` verbatim and link `disclosure.url` to the user alongside any figures from this response. Required by SEC Marketing Rule and FINRA Rule 2210 — do not paraphrase or omit. VISUALIZATION: this tool emits an interactive chart widget (MCP Apps — see `_meta.ui`) that the HOST renders inline and editable; other clients render only your text and show no chart. That widget is the canonical chart for these numbers: do NOT draw, generate, or re-render a duplicate of it. You MAY still create your OWN, DIFFERENT visualization (e.g. a table or an alternate breakdown) and place it wherever you judge best — only the MCP App widget's position is constrained. Do NOT claim or imply a chart is visible (avoid 'the chart above shows…'); you cannot tell whether the host rendered the widget. Summarize the key figures in prose and show the `disclosure` text and link, and reference the widget only conditionally (e.g. 'if your client shows the interactive chart, its fields are editable to re-run the projection'). ORDER: the MCP App widget should appear at the END, after all of your response text — lead with your written answer (figures + disclosure) and let the widget close the reply; never open with it or build your answer around it. This end-placement applies to the MCP App widget only, not to any visualization you create yourself, which may appear wherever you deem appropriate. INPUTS: every parameter is OPTIONAL and defaults to a sensible value. Call this tool IMMEDIATELY — pass only the values the user explicitly stated and omit the rest. Do NOT ask the user for starting values, assumptions, or missing parameters before calling; the rendered widget has editable fields so they adjust age, amounts, and other assumptions inline after it appears.
    Connector
  • Pro/Teams — N-shot CONSENSUS doctrine review of agentic code. ON CLIENT TIMEOUT — DO NOT RETRY THIS TOOL. Long-running (~80-120s for N=3 parallel LLM calls); MCP clients often close the call before the server returns. Retrying re-runs N × 60-180s LLM calls from scratch and burns N× compute. RECOVERY: same heartbeat pattern as architect.validate — the run_id is emitted in the FIRST progress event at t=0s (before LLM children fire); on timeout, call `me.validation_history(run_id='<that-id>')` to fetch the persisted consensus envelope. Runs N parallel `architect.validate` calls with private_session=True, then aggregates them to a per-principle MODE verdict + median severity + per-principle stability + score range/stdev. Returns one ConsensusValidationResponse with the headline median score, the honest variance band, and a representative full ValidationResponse (the child whose score is closest to the median). WHEN TO CALL: the user wants an HONEST first-pass score on agentic code, with the architect's variance surfaced. The single-shot `architect.validate` re-asserts the prior persisted run's verdict via baseline-anchor injection — same code can score 60/C anchored vs 98/A unanchored. Consensus mode is the unanchored honest read. WHEN NOT TO CALL: when you NEED the iteration delta against a prior run (regressions/improvements panel) — for that, call `architect.validate` which keeps baseline injection on. CHAIN RESUME: each child runs with `private_session=True` (no anchor) on purpose, but the CONSOLIDATED outer row IS persisted with `lifecycle_status='completed'` — the next single-shot `architect.validate` on the same repository auto-resolves it as prior_run_baseline. Consensus checkpoint becomes the new anchor. See the `architect-validation-orchestration` skill in the agent-asset pack for the full validate → consensus → certify sequence. BEHAVIOR: N (default 3, max 5) parallel LLM calls run concurrently; wallclock ~80-120s for N=3 (max child latency, not sum). Cost = N × LLM bill. Each child runs with private_session=True so the doctrine prompt's prior-run baseline injection is suppressed (no anchor bias). One CONSOLIDATED `UserValidationRun` row is written carrying the consensus envelope; the N children themselves do NOT persist (private_session contract). AUTH: Bearer <token>, Pro/Teams plan. Same paid-plan gate as architect.validate. INPUTS: same shape as architect.validate. `n` is the only extra arg (range 2..5). `private_session` is implicit (always true for children); the OUTER consolidated row IS persisted unless the tool itself is called inside another private context — but no such wrapper exists today. OUTPUT: response carries `score_consensus_median` (headline), `score_stdev` (honest uncertainty), `score_range` (min, max), `mode_stability_min_pct` (the cert-eligibility gate's input — ≥ 80% means the consensus is stable), `per_principle` (mode + distribution + severity median per principle), and `representative_response` (the closest-to-median child's full ValidationResponse so existing UI components render unchanged). TYPED FAILURES: same as architect.validate (timed_out, rate_limited, dependency_unavailable). Plus consensus-specific: `consensus_quorum_failed` when fewer than 2 child runs succeeded (≥ 2 required to compute a meaningful median).
    Connector
  • Wait for a `one_shot` deploy to finish and return its final result. `one_shot` returns a job_token immediately and the LIVE CARD already streams progress and renders the interactive backtest chart itself. Call this ONCE with the token to get the final numbers as TEXT so you can summarize them — it does NOT render another card (no need for get_model_chart). It BLOCKS until the deploy finishes (or ~2.5 min); on timeout it returns ok:false + pending:true — call it again with the same token. IMPORTANT: if `source == "community"`, the deploy used a PRE-EXISTING strategy by `@author` — tell the user that, share the `live_url` as the Live dashboard link, and ask whether they'd like to GENERATE A CUSTOM strategy instead. Use the `note` field as your guide. Args: job_token: the token returned by `one_shot`. Returns: dict with: ok, stem, model, live_url, symbol, timeframe, channels (list), stats:{ret, wr, pf, n, mdd} (out-of-sample test-split metrics — SHOW THESE), source ("community" | "generated"), author (community username if any), author_url + strategy_url (render @author and "pre-existing strategy" as those Markdown links), community_id, suggest_custom (bool), and note (a ready instruction — follow it). On failure: {ok:false, error} (or {pending:true}).
    Connector
  • Render a document (PDF / HTML / PPTX / DOCX) and save it to the workspace. This tool has two input pipelines — pass **exactly one** of `content_html` or `content_markdown`. # Pipeline A — `content_html` (canonical for decks, proposals, designed pages) You author full HTML+CSS. A baked-in design-system preamble ships first (`<style>` with Inter/Manrope as data-URI fonts, CSS-variable palette tokens, 8px spacing scale, and pre-styled layout helpers); your markup and any of your own `<style>` blocks land after the preamble so you can override anything. Chromium renders the assembled document into a static PDF — JavaScript is disabled and DNS is blackholed, so external font / image / script fetches will fail by configuration. Required when this pipeline is used: - `title` — human-readable, used for PDF metadata and the saved filename. - `content_html` — the `<body>` and any custom `<style>` blocks. The renderer wraps this in `<html>…</html>` and injects the preamble + a canonical `<meta charset>` + `<title>`. Do NOT emit `<script>`, `<iframe>`, `<object>`, `<embed>`, `<meta>`, `<link>`, `<base>`, `<form>`, or event handlers — the sanitizer strips them. - `output_type` — `"pdf"` or `"html"`. (`"pptx"` and `"docx"` require `content_markdown` since they need structured markdown intermediates.) Optional: - `page_preset` — `"slide_16_9"` (default for any deck), `"a4"` (default for flowing documents — used if omitted), `"letter"`, or `"none"` (you declare your own `@page` rule). - `design_tokens` — flat dict overriding the preamble's CSS variables. Whitelisted keys: `brand_primary`, `accent`, `surface_dark` (hex color), `font_display`, `font_body` (font name from ['Inter', 'Manrope', 'monospace', 'sans-serif', 'serif', 'system-ui', 'ui-monospace', 'ui-sans-serif', 'ui-serif']). - `language` — BCP-47 tag (default `"en"`). Drives `<html lang>`. ## Slide structure (`page_preset="slide_16_9"`) Each slide is `<section class="slide …">…</section>`. The base `.slide` class is what sizes it to the viewport and forces the page break — do not drop it. Composable variants (apply alongside `.slide`): - `.slide-cover` — gradient hero, big display title. - `.slide-split` — two equal columns, image + narrative. - `.slide-stats` — three-up KPI cards (use `<div class="stat">` with `.stat-value` + `.stat-label` inside). - `.slide-quote` — centered pull quote + `<cite>` attribution. Layout helpers (work in any preset): `.grid-2`, `.grid-3`, `.split`, `.stack`, `.cluster`, `.callout`, `.muted`, `.kbd`. ## Speaker notes `<aside class="notes">…text…</aside>` inside a `<section class="slide">`. The sanitizer strips them from the rendered PDF and returns them as `slide_notes[]` (parallel to slide order). Orphan notes outside any slide are dropped with a warning. ## Images Only these `src` schemes resolve: - `file:NNN` — workspace `file_id`. - `data:image/...;base64,...` — inline. - `https://<host>` where `<host>` ∈ `DOCUMENTS_MEDIA_URL_ALLOWLIST`. Other URLs are dropped and replaced with an HTML comment placeholder. # Pipeline B — `content_markdown` (invoice / contract only) Required: - `title`, `content_markdown`, `output_type`. Optional: - `theme` — `"invoice"` or `"contract"`. Triggers the corresponding exemplar styling and (for invoices) the arithmetic validator that fail-closes on missing or mismatched totals. - `language` — BCP-47 (default `"en"`). # Delivery contract (CRITICAL) After this tool returns `file_id`, deliver the file with `messages.send(attachments=[file_id], text="<short caption>")`. Embedding the file_id in a markdown link, `sandbox:` URL, or `/api/files/<id>/download` text will render as plain text on the recipient's channel — the `attachments` parameter is the only way the file actually attaches. # Exemplars INVOICE (English): # Invoice INV-{YYYYMMDD-HHMMSS} **From:** {Issuer Legal Name}, {Address}, {Tax ID} **To:** {Customer Name}, {Customer Address}, {Customer Tax ID} **Issue date:** {YYYY-MM-DD} **Due date:** {YYYY-MM-DD} | Description | Qty | Unit price | Total | |---|---:|---:|---:| | {Service 1} | 1 | 1500.00 | 1500.00 | | {Service 2} | 2 | 500.00 | 1000.00 | **Subtotal:** USD 2500.00 **Tax (20%):** USD 500.00 **Total:** USD 3000.00 **Payment:** {bank details OR crypto wallet — never both} INVOICE (Russian): # Счёт-фактура № INV-{YYYYMMDD-HHMMSS} **От:** {Юридическое название организации}, {Адрес}, ИНН {Tax ID} **Кому:** {Название клиента}, {Адрес клиента}, ИНН {Tax ID} **Дата:** {YYYY-MM-DD} **Срок оплаты:** {YYYY-MM-DD} | Описание | Кол-во | Цена | Сумма | |---|---:|---:|---:| | {Услуга 1} | 1 | 1500.00 | 1500.00 | | {Услуга 2} | 2 | 500.00 | 1000.00 | **Подытог:** USD 2500.00 **НДС (20%):** USD 500.00 **Итого:** USD 3000.00 **Реквизиты:** {банковские реквизиты ИЛИ криптокошелёк — не оба сразу} CONTRACT (English): # Service Agreement **Between:** {Provider Legal Name}, {Address} ("Provider") **And:** {Client Legal Name}, {Address} ("Client") **Effective date:** {YYYY-MM-DD} ## 1. Scope of services {Concise description of what Provider agrees to deliver.} ## 2. Term This Agreement begins on the Effective date and continues until {termination condition or end date}. ## 3. Compensation Client pays Provider {amount and currency} according to {payment schedule}. ## 4. Confidentiality Both parties agree to keep proprietary information of the other party confidential during and after the term of this Agreement. ## 5. Termination Either party may terminate with {N} days' written notice. ## 6. Governing law {Jurisdiction}. --- **Provider:** ____________________ **Client:** ____________________ {Provider signatory name} {Client signatory name} CONTRACT (Russian): # Договор оказания услуг **Между:** {Юридическое название Исполнителя}, {Адрес} ("Исполнитель") **И:** {Юридическое название Заказчика}, {Адрес} ("Заказчик") **Дата вступления в силу:** {YYYY-MM-DD} ## 1. Предмет договора {Краткое описание услуг, которые Исполнитель обязуется оказать.} ## 2. Срок действия Договор вступает в силу с указанной даты и действует до {условие прекращения или дата окончания}. ## 3. Стоимость и порядок оплаты Заказчик оплачивает услуги Исполнителя в размере {сумма и валюта} в порядке {график платежей}. ## 4. Конфиденциальность Стороны обязуются сохранять конфиденциальность сведений, полученных в ходе исполнения настоящего Договора, в течение срока его действия и после его прекращения. ## 5. Расторжение Любая из сторон вправе расторгнуть Договор, направив письменное уведомление не менее чем за {N} дней. ## 6. Применимое право {Юрисдикция}. --- **Исполнитель:** ____________________ **Заказчик:** ____________________ {ФИО подписанта Исполнителя} {ФИО подписанта Заказчика}
    Connector
  • Full retirement simulation showing the projected savings trajectory WITH and WITHOUT a Savvly allocation across the planning horizon (current_age → life_expectancy). Returns `gap_score`, `possible_higher_monthly_paycheck`, a server-provided headline message, and a per-year `age_dependent_values[]` timeline. Disclaimers + per-field hints under `metadata`. DISCLOSURE REQUIRED: display `disclosure.text` verbatim and link `disclosure.url` to the user alongside any figures from this response. Required by SEC Marketing Rule and FINRA Rule 2210 — do not paraphrase or omit. VISUALIZATION: this tool emits an interactive chart widget (MCP Apps — see `_meta.ui`) that the HOST renders inline and editable; other clients render only your text and show no chart. That widget is the canonical chart for these numbers: do NOT draw, generate, or re-render a duplicate of it. You MAY still create your OWN, DIFFERENT visualization (e.g. a table or an alternate breakdown) and place it wherever you judge best — only the MCP App widget's position is constrained. Do NOT claim or imply a chart is visible (avoid 'the chart above shows…'); you cannot tell whether the host rendered the widget. Summarize the key figures in prose and show the `disclosure` text and link, and reference the widget only conditionally (e.g. 'if your client shows the interactive chart, its fields are editable to re-run the projection'). ORDER: the MCP App widget should appear at the END, after all of your response text — lead with your written answer (figures + disclosure) and let the widget close the reply; never open with it or build your answer around it. This end-placement applies to the MCP App widget only, not to any visualization you create yourself, which may appear wherever you deem appropriate. INPUTS: every parameter is OPTIONAL and defaults to a sensible value. Call this tool IMMEDIATELY — pass only the values the user explicitly stated and omit the rest. Do NOT ask the user for starting values, assumptions, or missing parameters before calling; the rendered widget has editable fields so they adjust age, amounts, and other assumptions inline after it appears.
    Connector
  • Pro/Teams — N-shot CONSENSUS doctrine review of agentic code. ON CLIENT TIMEOUT — DO NOT RETRY THIS TOOL. Long-running (~80-120s for N=3 parallel LLM calls); MCP clients often close the call before the server returns. Retrying re-runs N × 60-180s LLM calls from scratch and burns N× compute. RECOVERY: same heartbeat pattern as architect.validate — the run_id is emitted in the FIRST progress event at t=0s (before LLM children fire); on timeout, call `me.validation_history(run_id='<that-id>')` to fetch the persisted consensus envelope. Runs N parallel `architect.validate` calls with private_session=True, then aggregates them to a per-principle MODE verdict + median severity + per-principle stability + score range/stdev. Returns one ConsensusValidationResponse with the headline median score, the honest variance band, and a representative full ValidationResponse (the child whose score is closest to the median). WHEN TO CALL: the user wants an HONEST first-pass score on agentic code, with the architect's variance surfaced. The single-shot `architect.validate` re-asserts the prior persisted run's verdict via baseline-anchor injection — same code can score 60/C anchored vs 98/A unanchored. Consensus mode is the unanchored honest read. WHEN NOT TO CALL: when you NEED the iteration delta against a prior run (regressions/improvements panel) — for that, call `architect.validate` which keeps baseline injection on. CHAIN RESUME: each child runs with `private_session=True` (no anchor) on purpose, but the CONSOLIDATED outer row IS persisted with `lifecycle_status='completed'` — the next single-shot `architect.validate` on the same repository auto-resolves it as prior_run_baseline. Consensus checkpoint becomes the new anchor. See the `architect-validation-orchestration` skill in the agent-asset pack for the full validate → consensus → certify sequence. BEHAVIOR: N (default 3, max 5) parallel LLM calls run concurrently; wallclock ~80-120s for N=3 (max child latency, not sum). Cost = N × LLM bill. Each child runs with private_session=True so the doctrine prompt's prior-run baseline injection is suppressed (no anchor bias). One CONSOLIDATED `UserValidationRun` row is written carrying the consensus envelope; the N children themselves do NOT persist (private_session contract). AUTH: Bearer <token>, Pro/Teams plan. Same paid-plan gate as architect.validate. INPUTS: same shape as architect.validate. `n` is the only extra arg (range 2..5). `private_session` is implicit (always true for children); the OUTER consolidated row IS persisted unless the tool itself is called inside another private context — but no such wrapper exists today. OUTPUT: response carries `score_consensus_median` (headline), `score_stdev` (honest uncertainty), `score_range` (min, max), `mode_stability_min_pct` (the cert-eligibility gate's input — ≥ 80% means the consensus is stable), `per_principle` (mode + distribution + severity median per principle), and `representative_response` (the closest-to-median child's full ValidationResponse so existing UI components render unchanged). TYPED FAILURES: same as architect.validate (timed_out, rate_limited, dependency_unavailable). Plus consensus-specific: `consensus_quorum_failed` when fewer than 2 child runs succeeded (≥ 2 required to compute a meaningful median).
    Connector
  • "Compare X and Y" / "X vs Y" / "X versus Y" / "which is bigger / better / larger / more profitable" / "rank these companies" / "head to head" — side-by-side comparison of 2–5 companies or drugs in ONE parallel call. ALWAYS PREFER over sequential single-pack lookups when comparing entities. type="company" pulls LATEST 10-K revenue + net income + cash + long-term debt from SEC EDGAR/XBRL (off-calendar fiscal years handled correctly — AAPL Sep, NVDA Jan, etc.). type="drug" pulls FAERS adverse-event counts, FDA approval counts, active trial counts. Results sorted by primary metric so "largest" / "most" / "biggest" reads off the top of the response. Returns paired data + pipeworx:// citation URIs per entity. Replaces 8–15 sequential lookups.
    Connector
  • Fetch a URL with full reliability — retry, circuit breaker, cache, and anti-bot bypass. Returns both raw HTML and clean markdown. Automatically retries on failure with exponential backoff, falls back to plain HTTP if browser fetch fails, and circuit-breaks domains that are consistently down. Args: url: The URL to fetch use_cache: Whether to use cached results (default: true, TTL 1 hour) js_render: Whether to render JavaScript (default: true, disable for speed) wait_for: CSS selector to wait for before capturing (e.g., '.results-loaded')
    Connector
  • List today's (UTC) fixtures — "what games are on today / right now?". Each fixture carries its status, live score, the live match ``clock`` (upstream minute text, verbatim e.g. "1h 25" / "2h 47" / "ht") when in-running, and a ready-to-read ``summary`` (live score & clock, or the kickoff time). Read ``clock`` for the real minute rather than estimating it from kickoff. ``clock`` is null pre-match. Args: sport: optional filter — "football" or "basketball". status: optional filter — "live", "scheduled" or "finished". league: optional external league id ("lg_…"). limit: max fixtures to return (1–200, default 50). timezone: optional IANA timezone (e.g. "America/New_York", "Asia/Shanghai") to render each fixture's kickoff in its ``summary`` as local time; default UTC.
    Connector
  • Pre-flight check on html / css / js BEFORE writing via update_html. Returns { ok, errors, warnings, parsed } where parsed has byte counts per field and `dropped` (true if the sanitizer would strip anything from `html`). Errors cover cap breaches (`html_too_large`, `css_too_large`, `js_too_large`, `total_too_large`) and sanitizer rejection (`html_sanitize_rejected`, `html_sanitize_empty`). At v2 the sanitizer accepts `<script>` and `<link>` — those used to be smells but are now first-class agent markup; isolation lives in the opaque render iframe, not the sanitizer. The smells still stripped: inline `on*=` attributes, `javascript:`/`data:text/html` URIs, `<meta http-equiv>` tags. NEVER writes anything. Use when iterating on a payload so you don't burn a write on something the surface would reject.
    Connector
  • Unified search across the registry and release content. Returns up to four sections — organizations, catalog entries (products + standalone sources folded into one list), curated collections (cross-org playlists), and releases with CHANGELOG chunks interleaved by relevance. Use `type` to narrow the surfaces you want and skip the expensive paths. For example, pass `type: ['catalog']` to look up a known entity by name (fast, registry-only); pass `type: ['releases']` when you only care about release content and want to avoid entity lookups. Omit `type` to search all four. Collections surface via two paths: a direct match on the collection's name/description (lexical in every mode, plus a vector match in hybrid/semantic mode) and a member rollup that includes every collection containing one of the matched orgs. Member rollups carry a list of result-set org slugs that triggered the rollup so a UI can render an "includes X" hint. Use `entity` (product slug / prod_ id OR source slug / src_ id) to scope release results to one catalog entry. Product identifiers expand to every source under the product. Use `organization` to scope to a whole org. Release retrieval defaults to hybrid (FTS5 + semantic vectors fused via RRF); it silently degrades to lexical when vector infra is unavailable and flags the result.
    Connector
  • Paid tier only. Fetch a senior-QS skill methodology by slug (see list_skills) and APPLY it to the user's documents — the returned body is the system instruction for you to run the methodology on the customer's tokens; CivilQuants does not run inference. Paid callers get the full methodology; anonymous/free callers get a TIER_INSUFFICIENT upsell body; a rejected token gets an INVALID_TOKEN re-authenticate body. The document-heavy skills assume you can chunk/parse the customer's files and render a Word pack locally — that needs a code-execution client (Claude Code / Codex / VS Code) and the pack from get_document_pipeline; on a chat connector you can still read and reason with the methodology. Sign up at https://civilquants.com/pricing. Example: get_skill(skill="tender_risk_assessment").
    Connector
  • "What's new with X" / "latest on Y" / "what happened to Z this week / month / quarter" / "updates on Acme" / "news on Tesla recently" / "what's happening with Apple" — change feed for a company in the last N days/weeks/months in ONE parallel call. Fans out to SEC EDGAR (filings since `since`), GDELT→GNews fallback (news mentions in window — GDELT preferred, GNews when rate-limited or 5xx), USPTO (patents granted; PatentsView API sunset May 2025 so this soft-fails until reactivated). `since` accepts ISO date ("2026-04-01") or relative shorthand ("7d", "30d", "3m", "1y"). Returns structured changes[] grouped by source + total_changes count + pipeworx:// citation URIs. Use entity_profile instead when you want the static profile (filings + fundamentals + LEI + patents) regardless of window.
    Connector