SKILLEMALL.ai

DF fire-smoke-skill-vfx

Build the effects of a fire skill as one visual language in Three.js. Flames that read as fire, not as orange fog or cones: ray-marched flame volumes whose turbulence rises with buoyancy (slow at the root, accelerating and stretching as it climbs) instead of scrolling, a temperature ramp from a white-hot core a little above the fuel through yellow and orange to deep red tips, broad brighter licks inside, walls of fire broken into clumps of separate tongues of very different heights with notches between them and licks that detach and go out, a fire whirl wound in helical sheets with a waist and a blue root; charcoal smoke drawn premultiplied over the frame and lit only by the fire (cauliflower billows for a burst, a thin streaked curtain off a grass-fire front, fibrous wisps off small fires, ragged hot cracks inside a burst's smoke); embers and sparks that drift on a curl field, cool from white through orange to red and fall as ash; heat haze as refraction; firelight shared with the world; a world-space heat map that makes the ground's needles smoulder as hairlines and its pockets breathe; and gentle ink impact frames limited to three flashes a second. Use for fire or flame skills, fireballs, fire waves or breath, rings of fire, fire tornadoes or whirls, burning ground, wildfire fronts, smoke columns, embers, smouldering aftermath, "fire and smoke", "realistic fire", "flame thrower", "inferno", "burning field" or "skill effects only". Includes a reusable module and a five-beat demo on a scanned CC0 burned-ground floor with failure-mode switches.

MengTo/Skills Agent Skills author: MengTo MIT 9 files · 4 scripts body ≈ 7 139 tokens Open the sourcegithub.com↗ analyzed 4 d ago

Build the effects of a fire skill as one visual language in Three.js. Flames that read as fire, not as orange fog or cones: ray-marched flame volumes whose…

As a process F 33/100 · No process to follow — References files that are not bundled: demo/index.html

GeneratorSoftware developmentMarketingtype and topics are labelled automatically from the skill text
JSON
Technical rating
D
74/100
safety, quality, tests
Safety 60%
100
Quality 40%
36
Run on models
none yet
Process rating
F
33/100
No process to follow
References files that are not bundled: demo/index.html
Tools and files w 18
0
Result and completion w 14
0
Inputs and preconditions w 11
0
the three weakest of ten parameters · all ten

How to improve

  1. Shorten the description to 1024 characters.
  2. The SKILL.md body is over 5,000 tokens: move reference detail into references/ and load it when needed.
  3. The text references files that are not there: add them or drop the references.
For the model run — optional
  • Your own cases (evals/evals.json, 4–6 real requests with expected answers): the full check would then run those instead of a model-drafted suite.
  • A spec.yaml with trigger phrases and assertions — a behaviour contract for CI; `skilltest init` writes a template.

Guard findings · 0

✓ No critical or high findings

Files scanned: 9. Evidence is masked. Grey chips explain why severity was lowered.

Against the Agent Skills spec

  • error description-long description is 1570 chars, limit 1024
  • warning frontmatter-yaml SKILL.md: the frontmatter is not valid YAML (YAML parse error: Nested mappings are not allowed in compact mappings at line 2, column 14: description: Build the effects of a fire skill as one visual language in Three.… ^ ); fields were read line by line. The usual cause is a colon inside an unquoted value
  • warning body-long SKILL.md body ≈ 7139 tokens (recommended < 5000); move details to references/
  • warning missing-ref reference to a missing file: demo/index.html
  • note description-budget description takes 1570 of the ~15000-char shared budget for all skills

Process rating: all ten parameters 33/100

Will not run. References files that are not bundled: demo/index.html
  • 0Tools and files. 1 referenced file(s) missing: demo/index.html
  • 0Result and completion. Does not say what the result is
  • 0Inputs and preconditions. Does not say what the process needs to start
  • 0Failures and branches. Linear process with no failure handling
  • 20When it triggers. No condition that starts the skill
  • 30Running it twice. 2 mutating operations with no state check
  • 70Execution cost. Instruction body is 7139 tokens
  • 100Steps. 57 steps
  • 100Consistency. Name and required fields are in place
  • 100Progress reporting. Reports progress
  • medium Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing

Everything here is measured from the skill text rather than judged by a model, so the numbers are checkable. A parameter weighs more when it is a more common reason for the process to stall.

Quality signals

  • +4Description does not say when NOT to use the skill (false activations)
  • +3Description length 1570: 120–800 characters recommended
  • +3Output format is not stated: the model decides each time
  • +1No license
  • +2Single-language instructions
  • +5Description quotes 6 example trigger phrases
  • +4Structure: 9 headings
  • +3Step-by-step instructions: 57 items
  • +4Has examples (1 code blocks)
  • +4Reference files are cited in the instructions (1 of 1)

Quality base 70; lint remarks subtract, signals add up to 100. Result: 36.