SKILLEMALL.ai
GitHub ↗ RU Sign in

AC clawhub-skill-guide

Create, structure, and publish OpenClaw skills to ClawHub that pass the security scanner with clean ratings. Covers frontmatter schema, env var declarations, script safety, config change patterns, and the full publish workflow. Use when: creating a new skill, publishing to ClawHub, fixing security scan warnings, structuring skill files, writing SKILL.md frontmatter, declaring environment variables, understanding scanner categories, preparing scripts for publication.

modbender/skill-library-mcp Agent Skills author: modbender MIT 8 files body ≈ 2 881 tokens Open the sourcegithub.com↗ analyzed 2 d ago

Create, structure, and publish OpenClaw skills to ClawHub that pass the security scanner with clean ratings.

As a process C 54/100 · Has gaps — weak spots: result and completion, when it triggers, running it twice

GeneratorAI and agentsSecuritytype 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
A
93/100
safety, quality, tests
Safety 60%
96
Quality 40%
88
Run on models
none yet
Process rating
C
54/100
Has gaps
Result and completion w 14
0
Progress reporting w 2
0
When it triggers w 12
20
the three weakest of ten parameters · all ten

How to improve

    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 · 4

    ✓ No critical or high findings

    Medium and low: 4
    • low Dangerous commands cmd-shell-rc references/script-safety.md:93
      Writes to a shell startup file (documentation of a security skill)
      echo "alias myskill='...'" >> ~/.bashrc
      security skill
    • low Dangerous commands cmd-privilege references/script-safety.md:94
      Privilege escalation / world-writable permissions (documentation of a security skill)
      sudo mv binary /usr/local/bin/
      security skill
    • low Secrets in code secret-password-literal references/script-safety.md:108
      Hard-coded password / key literal (may be an example)
      API_KEY = "sk-a…456"

    A further 1 matches are quotations in this security skill's documentation and are not counted as findings.

    Files scanned: 8. Evidence is masked. Grey chips explain why severity was lowered.

    Against the Agent Skills spec

    ✓ No remarks against the Agent Skills spec

    Process rating: all ten parameters 54/100

    • 0Result and completion. Does not say what the result is
    • 0Progress reporting. Says nothing while it works
    • 20When it triggers. No condition that starts the skill
    • 30Running it twice. 14 mutating operations with no state check
    • 55Failures and branches. 1 branches
    • 60Tools and files. Uses tools (web) that frontmatter does not declare
    • 70Inputs and preconditions. Inputs and preconditions are listed
    • 85Steps. 35 steps, 2 vague phrases
    • 100Consistency. Name and required fields are in place
    • 100Execution cost. Instruction body is 2881 tokens

    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
    • +1No license
    • +2Single-language instructions
    • +3Description length 470: enough signal without eating the budget
    • +4Structure: 27 headings
    • +3Step-by-step instructions: 35 items
    • +4Has examples (11 code blocks)
    • +4Reference files are cited in the instructions (4 of 4)

    Quality base 70; lint remarks subtract, signals add up to 100. Result: 88.