Skip to main content
Glama

fx_recipe

Adds authored, reusable visual FX recipes—spell bursts, explosions, reel wins, UI glows—to Spine animations and merges them as one group bone for easy recoloring, resizing, and retiming.

Instructions

Authored FX layers lifted from real reference clips: lotus set (rune_ring, burst_flare, rim_wisps, bloom_aura, floor_glow, fireflies, twinkles, plus magic_reveal = all seven timed like the clip, 13.2 s), light_beam (style gold | ribbon | blue), crosshair / hit_burst / lock_on (reticle locks on, fires, impact), cell_glow (resizable 9-slice glowing cells that pop), puff (cartoon smoke puff, or flash + ring for an AE smoke_puff), smoke_glow (rising haze with a base glow), meteor_trace (comet racing around a frame), projectile (shot on an arc + impact), ice and water (frost, icicles, ice_shatter, bubbles, water_splash; AE template caustics), explosion and shine, the reel moments reel_stop (spring thud, squash, dust, screen shake on your reel/screen bones through inserted carrier bones) and anticipation_reel (accelerating heartbeat glow, edge flames or sparks, dimmed neighbours), the slot families (spin: near_miss, spin_blur, turbo_spin, screen_shake; wins: payline, win_highlight, multiplier_stack, win_rollup; payouts: coin_fountain, cascade_pop; features: wild_land, expanding_wild, scatter_trigger, free_spins_transition; bonus: pick_reveal, hold_respin, jackpot_wheel, meter_fill; ambient: weather, god_rays, water_surface, heat_shimmer, fog_roll, lightning_storm; UI: button_press, idle_shimmer, focus_glow, padlock, popup; saber = a port of Video Copilot's Saber beams with 12 presets and an ae_hint for the saber AE template; pinata family = wild_glow, wild_transform, mult_cell_glow, cell_pop, confetti_burst, mult_streak, wild_merge, coins_to_bar, bar_sweep, pinata_hit, jar_burst, banner_backdrop from one picture kit (swap a texture pack in by name with art=, retune it with options gain / thick); recipes that move your reel / symbol / screen / button bones do it through inserted carrier bones, never your own keys), and the hybrids portal and electric_frame, whose plasma / lightning part is After Effects: they return a ring_hint to pass to ae_fx_to_spine (guide explains). Procedural textures, additive only (one draw call), one group bone per recipe so it recolours, resizes and retimes as one piece, and it merges into any animation with into=.

recipe="" lists every recipe with its options and defaults; recipe="guide" returns the guide (how to use, fork and mix them, how they were made, and the traps). x, y = the subject centre in the parent bone's space; scale 1 = a ~720-unit canvas with a ~420-wide subject; start = seconds into the animation; duration = life window (window recipes) or a time scale (one-shots); color = main tint; intensity = alpha gain; count = tufts / motes / stars / sparks; options = recipe-specific values (see the listing). magic_reveal takes options={skip: [recipe, ...], overrides: {recipe: {param: value}}}. Each recipe fires an fx_ event.

art = your own pictures instead of the generated ones, keeping all the motion: {role: "file.png" | "file.psd#Layer" | {path, blend, scale, slice, px, anchor}}; the roles of each recipe are in the listing (e.g. crosshair: reticle). For lock_on / magic_reveal key it by member: {"crosshair": {"reticle": ...}}.

tier = small | medium | big | mega | epic: one recipe covers every win size (scale, counts, one-shot time and the recipe's own tier overrides; see the listing's tiers). Bundles: sequence = any list of recipes with offsets into one animation (options={steps: [{recipe, start, dx, dy, ...any fx_recipe argument}]}); win_banner = Big/Mega/Epic banner from one recipe (tier= picks the layers; options={banner: bone} slams your banner art in on an exact spring).

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
xNo
yNo
artNo
intoNo
nameNo
seedNo
tierNo
colorNo
countNo
scaleNo
startNo
behindNo
parentNoroot
recipeNo
optionsNo
projectNo
durationNo
front_ofNo
intensityNo

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.2.0

TDQS

A3.7/5.0
Behavior4/5

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

With no annotations, the description carries the full burden and discloses important behavioral traits: procedural, additive only (one draw call), one group bone per recipe, and that it merges into animations via into=. It also notes that recipes moving bones use inserted carrier bones, never the user's keys. It does not cover side effects like project modification or reversibility, but the core behavior is well‑explained.

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

Conciseness2/5

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

The description is extremely long, sprawling, and list-heavy, reading like a reference manual rather than a focused tool description. It is not front-loaded beyond the first clause and lacks clear structural breaks (e.g., sections), making it hard to scan. Many sentences could be trimmed or moved to external docs.

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

Completeness3/5

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

Given 19 parameters, no schema descriptions, and no output schema, the description provides substantial coverage but is incomplete. It omits semantics for multiple parameters and does not explain return values or side effects in full. It is adequate for basic use but leaves an agent exposed on edge cases.

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 0%, so the description must compensate. It defines most key parameters (x, y, scale, start, duration, color, intensity, count, recipe, options, tier, art, into, parent) with useful semantics like coordinate space, time units, and option syntax. Several parameters (name, seed, project, behind, front_of) remain undocumented, keeping it from a 5.

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

Purpose4/5

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

The description clearly identifies the tool as a generator of authored FX layers from recipes, listing the available families and key behaviors. It distinguishes itself from siblings like ae_fx_to_spine by explaining that hybrids return a ring_hint for that tool, but it does not explicitly contrast with fx_generate, leaving some ambiguity about when to choose this over others.

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?

It gives explicit operational guidance: recipe='' lists all recipes, recipe='guide' returns the guide, and it details parameter usage and bundle options. However, it lacks a direct comparison to alternatives (e.g., fx_generate) and does not state when not to use this tool, which prevents a perfect score.

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