SKILLEMALL.ai
GitHub ↗ RU Sign in

BF skill-craft

Create, optimize, or update AgentSkills with evidence-based design. Two modes: (1) CREATE — build new skills from scratch with proven design patterns. (2) OPTIMIZE — diagnose and fix existing skills across 9 evidence-based dimensions: trigger precision, context efficiency, structured instructions, step decomposition, positive constraints, example design, verification, freedom calibration, progressive loading. Based on 25+ peer-reviewed papers (ACL/NeurIPS/EMNLP 2023-2025), Anthropic/Google/Microsoft official guides, and Claude Code/Cursor community practices. Trigger: "create skill", "optimize skill", "improve skill", "fix skill", "package skill", "skill not working", "skill design", "SKILL.md", "写技能", "优化技能", "skill type", "skill classification", "state management", "技能分类"

Not recommendedcritical or high security findings
ClawHub Agent Skills author: LeoNardo-LB v1.0.1 MIT-0 9 files body ≈ 4 372 tokens Open the sourceclawhub.ai↗ analyzed 3 d ago

As a process F 46/100 · Will not run — References files that are not bundled: references/schemas.md, references/troubleshooting.md, references/api.md

GeneratorAI and agentstype and topics are labelled automatically from the skill text
Runs in: OpenClaw 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) Goose OpenCode
JSON
Technical rating
B
83/100
safety, quality, tests
Safety 60%
82
Quality 40%
84
Run on models
none yet
Process rating
F
46/100
Will not run
References files that are not bundled: references/schemas.md, references/troubleshooting.md, references/api.md
Tools and files w 18
0
Inputs and preconditions w 11
0
Progress reporting w 2
0
the three weakest of ten parameters · all ten

What is at stake

The skill contains fragments that, in the wrong hands, cost money or data. Below: what the installer risks and what the author should do.

Concealment
If you install

The skill tells the agent to hide things from you: not to show errors, not to mention actions, to report differently from what was done. You lose the ability to see what the agent really did.

For the author

Transparency beats a smooth answer. If the goal is to hide technical noise, ask the agent to "summarise briefly", not to "not mention".

How to improve

  1. Address the high-severity findings: each costs 18 safety points. If one is a false positive, add the rule id to guard.allow in spec.yaml.
  2. 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

  • high Concealment en-hide-from-user references/skill-optimization.md:614
    Instruction to hide actions from the user
    Do NOT inform the user of success until all 4 checks pass.

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

Against the Agent Skills spec

  • warning missing-ref reference to a missing file: references/schemas.md
  • warning missing-ref reference to a missing file: references/troubleshooting.md
  • warning missing-ref reference to a missing file: references/api.md
  • warning missing-ref reference to a missing file: scripts/transform.py
  • warning missing-ref reference to a missing file: references/schema.md
  • warning missing-ref reference to a missing file: assets/template/
  • warning missing-ref reference to a missing file: assets/report-template.md
  • warning missing-ref reference to a missing file: references/api-versions.md
  • warning missing-ref reference to a missing file: references/examples.md
  • warning missing-ref reference to a missing file: scripts/backup.sh
  • warning missing-ref reference to a missing file: references/brand-voice.md

Process rating: all ten parameters 46/100

Will not run. References files that are not bundled: references/schemas.md, references/troubleshooting.md, references/api.md
  • 0Tools and files. 11 referenced file(s) missing: references/schemas.md, references/troubleshooting.md, references/api.md
  • 0Inputs and preconditions. Does not say what the process needs to start
  • 0Progress reporting. Says nothing while it works
  • 20When it triggers. No condition that starts the skill
  • 30Running it twice. 12 mutating operations with no state check
  • 40Result and completion. Does not say what the result is
  • 70Execution cost. Instruction body is 4372 tokens
  • 100Steps. 14 steps
  • 100Failures and branches. 1 branches, has a failure section
  • 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)
  • +3Output format is not stated: the model decides each time
  • +1No license
  • +2Single-language instructions
  • +5Description quotes 11 example trigger phrases
  • +3Description length 784: enough signal without eating the budget
  • +4Structure: 32 headings
  • +3Step-by-step instructions: 14 items
  • +4Has examples (11 code blocks)
  • +4Reference files are cited in the instructions (4 of 4)
  • +3All 3 scripts are documented

Quality base 70; lint remarks subtract, signals add up to 100. Result: 84.

External checks

ClawHub: clean
This is a disclosed skill-building helper whose local file creation, validation, and packaging behavior matches its stated purpose.
LLM: benign (high) · VirusTotal: · 29 May 2026