SKILLEMALL.ai
GitHub ↗ RU Sign in

AA data-evidence-finder

为方案、PPT 或市场判断查找可引用的数据和研究证据，适用于市场规模、 增长率、统计口径核对、数据来源追溯和观点验证；交付数据表、引用及相反证据。 / Find citable statistics and research evidence for a claim, proposal, or market question. Verify market size, growth rates, measurement scope, and conflicting findings; deliver evidence tables and citation text, retained in JishuDB.

ClawHub Agent Skills author: bowen-aijishu v0.1.7 MIT-0 10 files · 2 scripts body ≈ 4 941 tokens Open the sourceclawhub.ai↗ analyzed 6 d ago

为方案、PPT 或市场判断查找可引用的数据和研究证据，适用于市场规模、 增长率、统计口径核对、数据来源追溯和观点验证；交付数据表、引用及相反证据。 / Find citable statistics and research evidence for a claim, proposal, or market…

As a process A 87/100 · Runs to the end — no weak spots found

AnalyzerData and analyticsAI and agentsResearchtype 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
96/100
safety, quality, tests
Safety 60%
99
Quality 40%
91
Run on models
none yet
Process rating
A
87/100
Runs to the end
When it triggers w 12
50
Result and completion w 14
60
Execution cost w 6
70
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 · 1

    ✓ No critical or high findings

    Medium and low: 1
    • low Secrets in code secret-high-entropy-token references/jishudb-setup/scripts/install-macos.sh:287
      High-entropy token-like string (may be an id, hash or a credential) (quoted — discussed, not commanded)
      exactKeys(candidate.signing, ['certificateExpiresAt', 'cert…256', 'nativeFileCount'], 'candidate.signing');
      quoted

    Files scanned: 10. 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 87/100

    • 50When it triggers. No condition that starts the skill
    • 60Result and completion. Output format stated, no completion criterion
    • 70Execution cost. Instruction body is 4941 tokens
    • 100Tools and files. No external tools needed
    • 100Steps. 42 steps
    • 100Inputs and preconditions. Inputs and preconditions are listed
    • 100Failures and branches. 1 branches, has a failure section
    • 100Consistency. Name and required fields are in place
    • 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

    • +5Description has no quoted example phrases that should trigger the skill
    • +4Description does not say when NOT to use the skill (false activations)
    • +1No license
    • +2Single-language instructions
    • +3Description length 307: enough signal without eating the budget
    • +4Structure: 16 headings
    • +3Step-by-step instructions: 42 items
    • +3Output format is stated explicitly
    • +4Has examples (0 code blocks)
    • +4Reference files are cited in the instructions (1 of 1)

    Quality base 70; lint remarks subtract, signals add up to 100. Result: 91.

    External checks

    ClawHub: clean
    The skill is a disclosed JishuDB-backed evidence workflow; it can install and launch JishuDB and retain selected research records, but those actions are scoped and approval-gated rather than hidden.
    LLM: benign (high) · VirusTotal: · 11 Oct 2026