SKILLEMALL.ai
GitHub ↗ RU Sign in

CD skill-creator

Use when the user asks to create, scaffold, update or package a skill, or asks how skill frontmatter, progressive disclosure or bundled resources should be structured. Walks through init_skill.py, writing SKILL.md and package_skill.py.

coco-research/coco Agent Skills author: coco-research 7 files · 3 scripts body ≈ 4 409 tokens Open the sourcegithub.com↗ analyzed 2 d ago

Walks through initskill.py, writing SKILL.md and packageskill.py.

As a process D 43/100 · Unfinished process — References files that are not bundled: FORMS.md, REFERENCE.md, EXAMPLES.md

GeneratorWordAWSGoogle CloudAI and agentsWriting and documentstype and topics are labelled automatically from the skill text
Runs in: Claude / Claude Code ChatGPT / Codex Gemini CLI Cursor GitHub Copilot / VS Code Qwen Code Kimi Code CLI Z.ai (GLM) DeepSeek (Deep Code) Mistral Vibe LangChain (deepagents) OpenClaw Goose OpenCode
JSON
Technical rating
C
84/100
safety, quality, tests
Safety 60%
95
Quality 40%
68
Run on models
none yet
Process rating
D
43/100
Unfinished process
References files that are not bundled: FORMS.md, REFERENCE.md, EXAMPLES.md
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

What is at stake

Medium-severity findings: the skill is probably honest, but read what alarmed the scanner.

Dangerous commands medium severity

Below is the worst case for this category. The finding here is medium: the guard saw a sign, not a proof.

If you install

The skill contains commands that delete files, rewrite disks or execute code fetched from the network. The agent may run them without asking if it believes the instructions require it.

For the author

Replace destructive commands with safe equivalents that ask for confirmation, scope them to one folder, and stop piping curl into a shell: pin a version and a checksum.

How to improve

  1. 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 · 1

✓ No critical or high findings

Medium and low: 1
  • medium Dangerous commands cmd-autorun-instruction SKILL.md:264
    Instructs the agent to auto-run a script on every session
    When creating a new skill from scratch, always run the `init_skill.py` script. The script conveniently generates a new template skill directory that automatically includes everything a skill requires,

Files scanned: 7. Evidence is masked. Grey chips explain why severity was lowered.

Against the Agent Skills spec

  • warning missing-ref reference to a missing file: FORMS.md
  • warning missing-ref reference to a missing file: REFERENCE.md
  • warning missing-ref reference to a missing file: EXAMPLES.md
  • warning missing-ref reference to a missing file: DOCX-JS.md
  • warning missing-ref reference to a missing file: REDLINING.md
  • warning missing-ref reference to a missing file: OOXML.md
  • warning missing-ref reference to a missing file: scripts/rotate_pdf.py
  • warning missing-ref reference to a missing file: references/finance.md
  • warning missing-ref reference to a missing file: references/mnda.md
  • warning missing-ref reference to a missing file: references/policies.md
  • warning missing-ref reference to a missing file: references/api_docs.md
  • warning missing-ref reference to a missing file: assets/logo.png
  • warning missing-ref reference to a missing file: assets/slides.pptx
  • warning missing-ref reference to a missing file: assets/frontend-template/
  • warning missing-ref reference to a missing file: assets/font.ttf
  • warning missing-ref reference to a missing file: assets/hello-world/
  • warning missing-ref reference to a missing file: references/schema.md
  • note frontmatter-key unknown frontmatter key "domain"

Process rating: all ten parameters 43/100

Will not run. References files that are not bundled: FORMS.md, REFERENCE.md, EXAMPLES.md
  • 0Tools and files. 17 referenced file(s) missing: FORMS.md, REFERENCE.md, EXAMPLES.md
  • 0Result and completion. Does not say what the result is
  • 0Inputs and preconditions. Does not say what the process needs to start
  • 0Progress reporting. Says nothing while it works
  • 55Failures and branches. 1 branches
  • 60Steps. 69 steps, 8 vague phrases
  • 70Execution cost. Instruction body is 4409 tokens
  • 100When it triggers. States when to use and when not to
  • 100Consistency. Name and required fields are in place
  • 100Running it twice. Mutating operations check current state

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)
  • +3Output format is not stated: the model decides each time
  • -5TODO / placeholder text left in the skill
  • -31 of 3 scripts are never mentioned in SKILL.md
  • +2Single-language instructions
  • +3Description length 235: enough signal without eating the budget
  • +4Structure: 22 headings
  • +3Step-by-step instructions: 69 items
  • +4Has examples (8 code blocks)
  • +4Reference files are cited in the instructions (2 of 2)
  • +1License stated

Quality base 70; lint remarks subtract, signals add up to 100. Result: 68.