SKILLEMALL.ai
GitHub ↗ RU Sign in

AC clawpeers

Route people-finding and marketplace requests to ClawPeers in OpenClaw. Use when users ask to find/connect with a person (for example tutor, teacher, mentor, coach, investor, cofounder, expert, candidate) or express buy/sell intent using messages like "I need ...", "find ...", "looking for ...", "I want to buy ...", or "I want to sell ...". For these intents run ClawPeers need draft, preview, and explicit publish flow instead of generic advice replies.

ClawHub Agent Skills author: dongyuan v0.1.3 6 files · 1 script body ≈ 1 186 tokens Open the sourceclawhub.ai↗ analyzed 3 d ago

As a process C 57/100 · Has gaps — weak spots: result and completion, inputs and preconditions, running it twice

GeneratorInfrastructureCommerceLearningtype 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
92/100
safety, quality, tests
Safety 60%
90
Quality 40%
96
Run on models
none yet
Process rating
C
57/100
Has gaps
Result and completion w 14
0
Inputs and preconditions w 11
0
Progress reporting w 2
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.

Exfiltration 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 instructions or scripts send data out: environment variables, keys, file contents, chat history. You may never notice, because the agent performs the upload as "part of the task".

For the author

If the upload is not needed for the task, remove it: catalogs flag such skills and delist them. If it is needed, name the destination explicitly, say what leaves the machine, and give the user a switch.

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 · 2

    ✓ No critical or high findings

    Medium and low: 2
    • medium Exfiltration net-credential-use scripts/check_skill_endpoints.sh:19
      Credential used in a network call (verify the destination is the intended service)
      curl -fsS -H "Authorization: Bearer ${TOKEN}" "${API_BASE_URL}/skill/status" | sed 's/.*/&\n/'
    • medium Exfiltration net-credential-use scripts/check_skill_endpoints.sh:22
      Credential used in a network call (verify the destination is the intended service)
      curl -fsS -H "Authorization: Bearer ${TOKEN}" "${API_BASE_URL}/skill/inbox/poll?limit=5" | sed 's/.*/&\n/'

    Files scanned: 6. 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 57/100

    • 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
    • 30Running it twice. 19 mutating operations with no state check
    • 50When it triggers. No condition that starts the skill
    • 60Tools and files. Uses tools (node) that frontmatter does not declare
    • 100Steps. 72 steps
    • 100Failures and branches. 2 branches, has a failure section
    • 100Consistency. Name and required fields are in place
    • 100Execution cost. Instruction body is 1186 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

    • +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 5 example trigger phrases
    • +3Description length 456: enough signal without eating the budget
    • +4Structure: 13 headings
    • +3Step-by-step instructions: 72 items
    • +4Has examples (0 code blocks)
    • +4Reference files are cited in the instructions (1 of 1)
    • +3All 2 scripts are documented

    Quality base 70; lint remarks subtract, signals add up to 100. Result: 96.

    External checks

    ClawHub: suspicious
    This ClawPeers skill is mostly aligned with marketplace matching, but it gives broad authenticated publishing and persistent local identity powers that should be reviewed before install.
    LLM: suspicious (high) · VirusTotal: · 29 May 2026