SKILLEMALL.ai
GitHub ↗ RU Sign in

AB errand-ai

Send a real person to a physical place in Seoul (Gangnam area) to check, photograph, verify, queue, or pick something up, and get GPS+photo evidence back. Use when the user needs eyes or hands on site — "is this store open?", "how long is the line?", "take a photo of the menu", "is the product on the shelf?".

ClawHub Agent Skills author: Chloe Park v2.0.0 MIT-0 2 files body ≈ 2 434 tokens Open the sourceclawhub.ai↗ analyzed 5 d ago

As a process B 70/100 · Nearly there — weak spots: result and completion, inputs and preconditions

AnalyzerInfrastructuretype 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%
95
Quality 40%
89
Run on models
none yet
Process rating
B
70/100
Nearly there
Inputs and preconditions w 11
0
Result and completion w 14
40
Tools and files w 18
60
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 · 5

    ✓ No critical or high findings

    Medium and low: 5
    • low Exfiltration net-credential-use SKILL.md:81
      Credential used in a network call (verify the destination is the intended service) (the skill's own vendor host)
      curl -s https://errand.be/api/v1/capabilities -H "Authorization: Bearer $ERRANDAI_API_KEY"
      vendor-host
    • low Exfiltration net-credential-use SKILL.md:125
      Credential used in a network call (verify the destination is the intended service) (the skill's own vendor host)
      curl -s https://errand.be/api/v1/dispatches/$DISPATCH_ID -H "Authorization: Bearer $ERRANDAI_API_KEY"
      vendor-host
    • low Exfiltration net-credential-use SKILL.md:136
      Credential used in a network call (verify the destination is the intended service) (the skill's own vendor host)
      curl -s https://errand.be/api/v1/dispatches/$DISPATCH_ID/result -H "Authorization: Bearer $ERRANDAI_API_KEY"
      vendor-host
    • low Exfiltration net-credential-use SKILL.md:161
      Credential used in a network call (verify the destination is the intended service) (the skill's own vendor host)
      curl -s -X POST https://errand.be/api/v1/dispatches/$DISPATCH_ID/cancel -H "Authorization: Bearer $ERRANDAI_API_KEY"
      vendor-host
    • low Exfiltration net-credential-use SKILL.md:168
      Credential used in a network call (verify the destination is the intended service) (the skill's own vendor host)
      curl -s https://errand.be/api/v1/dispatches -H "Authorization: Bearer $ERRANDAI_API_KEY"
      vendor-host

    Files scanned: 2. 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 70/100

    • 0Inputs and preconditions. Does not say what the process needs to start
    • 40Result and completion. Does not say what the result is
    • 60Tools and files. Uses tools (bash, web) that frontmatter does not declare
    • 70When it triggers. States when to use, but not when not to
    • 100Steps. 14 steps
    • 100Failures and branches. 4 branches, has a failure section
    • 100Consistency. Name and required fields are in place
    • 100Execution cost. Instruction body is 2434 tokens
    • 100Running it twice. Mutating operations check current state
    • 100Progress reporting. Reports progress

    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 4 example trigger phrases
    • +3Description length 310: enough signal without eating the budget
    • +4Structure: 13 headings
    • +3Step-by-step instructions: 14 items
    • +4Has examples (10 code blocks)

    Quality base 70; lint remarks subtract, signals add up to 100. Result: 89.

    External checks

    ClawHub: clean
    This skill is a disclosed Errand API integration for dispatching a real worker in limited Seoul areas, with explicit price confirmation required before spending money.
    LLM: benign (high) · VirusTotal: · 8 Sept 2026