SKILLEMALL.ai

AC metal-lyrics

Generate authentic metal lyrics across subgenres (death metal, black metal, power metal, doom metal, gothic metal, industrial metal, metalcore, nu metal, alternative metal, visual kei, punk, folk metal, symphonic metal, SID metal, dark cabaret, Russian rock, dance metal, math metal, shoegaze/blackgaze, horror punk, love metal, avant-garde metal, viking metal, progressive metal, pirate metal, Neue Deutsche Härte, groove metal, J-rock, psychedelic rock, thrash metal, glam metal, stoner metal, epic metal, heavy metal, speed metal, djent, kawaii metal, emotional hardcore/emo, space metal, sludge metal, post-metal, grindcore, funk metal, technical death metal, atmospheric black metal, post-black metal). Use when users want metal lyrics, songwriting for metal bands, or lyrical content for any heavy music genre. Supports lyrics in English, German, Russian, and Japanese with proper grammar and stylistic conventions.

ClawHub Agent Skills author: DarkD v1.0.0 MIT-0 1 file body ≈ 93 448 tokens Open the sourceclawhub.ai analyzed 4 d ago

As a process C 57/100 · Has gaps — weak spots: when it triggers, inputs and preconditions, execution cost

GeneratorWriting and documentstype and topics are labelled automatically from the skill text
JSON
Technical rating
A
90/100
safety, quality, tests
Safety 60%
100
Quality 40%
76
Run on models
none yet
Process rating
C
57/100
Has gaps
Inputs and preconditions w 11
0
Progress reporting w 2
0
Execution cost w 6
10
the three weakest of ten parameters · all ten

How to improve

  1. The SKILL.md body is over 5,000 tokens: move reference detail into references/ and load it when needed.
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: 1. Evidence is masked. Grey chips explain why severity was lowered.

Against the Agent Skills spec

  • warning body-long SKILL.md body ≈ 93448 tokens (recommended < 5000); move details to references/

Process rating: all ten parameters 57/100

  • 0Inputs and preconditions. Does not say what the process needs to start
  • 0Progress reporting. Says nothing while it works
  • 10Execution cost. Instruction body is 93448 tokens: crowds the task out of the window
  • 20When it triggers. No condition that starts the skill
  • 30Running it twice. 50 mutating operations with no state check
  • 60Tools and files. Uses tools (bash) that frontmatter does not declare
  • 70Failures and branches. 4 branches
  • 85Steps. 3041 steps, 1 vague phrases
  • 100Result and completion. Output format and completion criterion are stated
  • 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
  • low 147 top-level sections: this looks like several domains in one skill

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

  • +5Description has no quoted example phrases that should trigger the skill
  • +4Description does not say when NOT to use the skill (false activations)
  • +3Description length 921: 120–800 characters recommended
  • +1No license
  • +4Structure: 902 headings
  • +3Step-by-step instructions: 3041 items
  • +3Output format is stated explicitly
  • +4Has examples (285 code blocks)
  • +2Bilingual instructions (RU + EN)

Quality base 70; lint remarks subtract, signals add up to 100. Result: 76.

External checks

ClawHub: clean
This is an instruction-only metal lyric writing guide with disturbing artistic themes, but it does not install code, request secrets, or perform system actions.
LLM: benign (high) · VirusTotal: · 28 May 2026