SKILLEMALL.ai
GitHub ↗ RU Sign in

CC ct-safety

Screen drug–event safety signals via disproportionality analysis (PRR / ROR / IC / EBGM with 95% CIs) on FDA FAERS, with Safety Signal Score (0–100, T1–T4). Sources: FDA FAERS (openFDA drug/event.json), FDA Label (drug/label.json), China NMPA PV bulletins (cdr-adr.org.cn), DailyMed SPL, RxClass MED-RT, openFDA enforcement recalls, Hong Kong ADR Alerts. Public data only; zero confidential input. / 基于 FDA FAERS 筛查药物-事件安全信号，计算 disproportionality（PRR / ROR / IC / EBGM，含 95% CI）与安全信号评分（0–100，T1–T4）。数据源：FDA FAERS（openFDA drug/event.json）、FDA 标签（drug/label.json）、中国 NMPA 药物警戒通报（cdr-adr.org.cn）、DailyMed 说明书、RxClass MED-RT、openFDA 召回执法、香港 ADR 警报。仅公开数据，零保密输入。

ClawHub Agent Skills author: Wintone Zhang v0.10.0 MIT-0 73 files · 41 scripts body ≈ 3 827 tokens Open the sourceclawhub.ai↗ analyzed 6 d ago

Screen drug–event safety signals via disproportionality analysis (PRR / ROR / IC / EBGM with 95% CIs) on FDA FAERS, with Safety Signal Score (0–100, T1–T4).

As a process C 58/100 · Has gaps — weak spots: result and completion, when it triggers, running it twice

AnalyzerExcelGitHubData and analyticstype 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
C
87/100
safety, quality, tests
Safety 60%
98
Quality 40%
71
Run on models
none yet
Process rating
C
58/100
Has gaps
Result and completion w 14
0
When it triggers w 12
20
Running it twice w 4
30
the three weakest of ten parameters · all ten

How to improve

  1. Say in the description WHEN to use the skill ("use when…", example requests): that is the agent's main cue.
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
  • low Obfuscation obf-base64-blob adapters/nmpa_coze.py:74
    Long base64-looking blob (quoted — discussed, not commanded)
    "Bg1n…CBs
    quoted
  • low Secrets in code secret-high-entropy-token SKILL.md:58
    High-entropy token-like string (may be an id, hash or a credential) (documentation table row)
    | appId | `wbap…Vwl` · deploy metadata: `workbench/app.config.json` |
    table

Files scanned: 73. Evidence is masked. Grey chips explain why severity was lowered.

Against the Agent Skills spec

  • warning description-no-when description does not say WHEN to use the skill (no "use when")
  • note frontmatter-key unknown frontmatter key "slug"
  • note frontmatter-key unknown frontmatter key "displayName"
  • note frontmatter-key unknown frontmatter key "cn_name"
  • note frontmatter-key unknown frontmatter key "invocable"
  • note frontmatter-key unknown frontmatter key "required_commands"
  • note frontmatter-key unknown frontmatter key "summary"
  • note frontmatter-key unknown frontmatter key "triggers"
  • note frontmatter-key unknown frontmatter key "permissions"
  • note edit-residue the text marks something as outdated (lines 123): check that old rules are not kept next to new ones — the full check reads the text for contradictions

Process rating: all ten parameters 58/100

  • 0Result and completion. Does not say what the result is
  • 20When it triggers. No condition that starts the skill
  • 30Running it twice. 18 mutating operations with no state check
  • 50Failures and branches. 0 branches, has a failure section
  • 60Tools and files. Uses tools (web, python, node) that frontmatter does not declare
  • 70Inputs and preconditions. Inputs and preconditions are listed
  • 100Steps. 31 steps
  • 100Consistency. Name and required fields are in place
  • 100Execution cost. Instruction body is 3827 tokens
  • 100Progress reporting. Reports progress
  • medium Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
  • low 18 top-level sections: this looks like several domains in one skill

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
  • -329 of 34 scripts are never mentioned in SKILL.md
  • +2Single-language instructions
  • +3Description length 656: enough signal without eating the budget
  • +4Structure: 22 headings
  • +3Step-by-step instructions: 31 items
  • +4Has examples (1 code blocks)
  • +4Reference files are cited in the instructions (12 of 19)
  • +1License stated

Quality base 70; lint remarks subtract, signals add up to 100. Result: 71.

External checks

ClawHub: suspicious
This is mostly a public drug-safety analysis tool, but it needs review because it sends a persistent device-derived identifier to remote services and has broader endpoint behavior than the docs imply.
LLM: suspicious (high) · 9 Oct 2026