mnema

Official

Overview Schema Source Related Servers Discussions Admin

Propose a skill

create_skill

Propose a reusable skill into the mnema chain, scoped public, private, or global, and pinned to the current session so team or future sessions can reuse it. Returns the minted id.

Instructions

Propose a reusable pattern (a skill) into the mnema chain, attributed to this agent and pinned to the current session. A skill needs both a name (a short title) and a body (the reusable pattern itself). Optionally pick the scope it lands in: public (team-visible), private (this machine, this project), or global (personal, cross-project); omitted, a pattern states how the work is done here and lands PUBLIC: committed, so the team gets it on clone (global outside a project); it is born proposed, so creating one proposes it rather than adopting it. Optionally pick the project it lands in, when the workspace holds more than one. Returns the minted id (the key to move it), the name, and which tree it landed in. RECORDING IS PERMANENT: mnema is append-only and nothing deletes a fact. A record in the public scope is committed to the repository and reaches every machine that clones it (published, if that repository is public). So do NOT record credentials here. Values in a recognized format (cloud keys, API tokens, private keys, a password inside a URL) are replaced with a typed placeholder before anything is written and the reply says what was replaced, but a format mnema does not recognize is written verbatim and cannot be taken back. Do not record personal data either: an email address is replaced with and reported, and the mnid already says who wrote. Each text field holds at most 65536 bytes; a longer one is refused, not truncated.

Tool call template

Replace each placeholder with a value matching the input schema. Only required parameters are included; add optional parameters as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {
      "name": "<name>",
      "body": "<body>"
    },
    "name": "create_skill"
  }
}

Input Schema

Name	Required	Description
`body`	Yes	The reusable pattern itself.
`name`	Yes	A short title for the pattern.
`scope`	No	Where the skill lands; overrides the routing rule (public).
`project`	No	Which project of this workspace the fact belongs to: its absolute path, as this server gave it; a bare name is refused. Omitted, it lands in the project this session resolved to (the one `bootstrap` names). Pass it whenever the work being recorded happened in a different project of this workspace.

Schema Changelog

Changes observed during successful MCP inspections.

First observedNov 9, 2026

TDQS

A4.6/5.0

Behavior5/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Goes well beyond the annotations: it discloses that records are append-only and irreversible, that public scope is committed and propagates to every clone, that credentials and emails are redacted with a typed placeholder and reported back, and that unrecognized secret formats are written verbatim. It also states the 65536-byte cap is a refusal, not a truncation, and describes the return payload (minted id, name, tree).

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness4/5

Is the description appropriately sized, front-loaded, and free of redundancy?

Front-loaded with purpose and defaults, then warnings, then limits — a sensible ordering. It is long, and the scope-sentence is a dense chain of colons and parentheticals that slows parsing, but nearly every clause carries operational information an agent needs before writing.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness5/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a 4-parameter mutation with no output schema, it covers the routing defaults, project resolution, irreversibility, secret-handling behavior, size limits, and the shape of the reply. Nothing material an agent needs to call it safely is missing.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters4/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is already 100%, so the baseline is 3, but the description adds real semantics: the default routing rule (public, or global outside a project), what "private" means (this machine, this project), and that project must be an absolute path as the server gave it, with a bare name refused. Only minor detail (e.g. the scope enum's full mapping) is already in the schema.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

Opens with a specific verb and resource: "Propose a reusable pattern (a skill) into the mnema chain, attributed to this agent and pinned to the current session." It also pre-empts confusion with the lifecycle sibling by stating the record "is born `proposed`, so creating one proposes it rather than adopting it," which separates creation from transition.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines4/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

Gives concrete selection guidance for the optional parameters: which scope to pick and what each means, and "Pass it whenever the work being recorded happened in a different project of this workspace." It never names an alternative tool or states an explicit when-not-to-use case (e.g. versus skill_transition), so it stops short of a 5.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.