SKILLEMALL.ai

DF lightning-energy-skill-vfx

Build the effects of a close-combat energy skill as one visual language in Three.js. Lightning that reads as lightning, dynamic but never in your face: trees of strips (trunk, forks of forks, hair-fine branchlets) with a fine white core in a violet-blue glow, each channel reaching out as a stepped leader, flaring as it connects, holding its shape and fading through an afterglow, one discharge at a time; a storm-cloud orb (a lit billow surface that churns in place, 10-15 plasma-globe arcs from a small white core to its inner wall, crawlers on the rim, a hairline fresnel); ground strikes that flash when the leader arrives, crawl along the stone's own cracks and reflect in wet stone (the demo's floor is a scanned CC0 texture); a torn black shadow with dry-brush edges that hangs off the orb and streams behind it, air bursts felt as refraction, orange sparks, fractured rocks that land or float in a storm domain, and impact frames that hold, invert in two-tone ink with tapered speed lines, shake and bend the lens, limited to three flashes a second. Use for anime or dark-fantasy skill effects, lightning or thunder fists, plasma or energy balls, charge-ups, dashes with shadow trails, ground strikes, storm or domain rings, ultimates, hit-stop, impact frames, negative flashes, screen shake, "black lightning", "thunderstorm fist", "realistic lightning", "afterimage" or "skill effects only". Includes a reusable module and a five-beat demo with failure-mode switches.

MengTo/Skills Agent Skills author: MengTo MIT 9 files · 4 scripts body ≈ 9 346 tokens Open the sourcegithub.com↗ analyzed 4 d ago

Build the effects of a close-combat energy skill as one visual language in Three.js. Lightning that reads as lightning, dynamic but never in your face: trees…

As a process F 29/100 · 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
72/100
safety, quality, tests
Safety 60%
100
Quality 40%
31
Run on models
none yet
Process rating
F
29/100
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 1478 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 close-combat energy skill as one visual lan… ^ ); fields were read line by line. The usual cause is a colon inside an unquoted value
  • warning body-long SKILL.md body ≈ 9346 tokens (recommended < 5000); move details to references/
  • warning missing-ref reference to a missing file: demo/index.html

Process rating: all ten parameters 29/100

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
  • 0Progress reporting. Says nothing while it works
  • 20When it triggers. No condition that starts the skill
  • 30Running it twice. 16 mutating operations with no state check
  • 40Execution cost. Instruction body is 9346 tokens: crowds the task out of the window
  • 100Steps. 79 steps
  • 100Consistency. Name and required fields are in place
  • 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 1478: 120–800 characters recommended
  • +3Output format is not stated: the model decides each time
  • -41 reference files, but SKILL.md never points to them: the model will not open them
  • +1No license
  • +2Single-language instructions
  • +5Description quotes 5 example trigger phrases
  • +4Structure: 9 headings
  • +3Step-by-step instructions: 79 items
  • +4Has examples (1 code blocks)

Quality base 70; lint remarks subtract, signals add up to 100. Result: 31.