SKILLEMALL.ai
RU Sign in

CF ct-registry

跨源检索全球临床试验注册库并归一化聚合。可自动化直连：ClinicalTrials.gov v2、PubChem（公开 REST API，零保密数据或信息输入）。中国 CDE 因 WAF 拦截自动化浏览器，改为外部工作流自动化检索（第三方端点，仅公开查询词出域，需 Bearer token，已实测无 token 返回 401）；ChiCTR 经统一端点（source=chictr，第三方，共享 Bearer）检索，用户粘贴页面仅作本地解析兜底；EU CTIS 仅支持按号 retrieve（无搜索）；ISRCTN 公开 API 已失效，但可经统一端点（source=isrctn）取。聚合分期/状态/申办方/时间线/竞品格局，产出 JSON / Markdown（可选 PNG；可选经 download_docs.py 拉取 EU-CTR 文档 PDF 到本地 --out-dir）。CDE 亦支持可选商业 API key（--cde-api-key，仅发往官方 CDE API）。零保密数据或信息输入，B 档（普通数据输入 + 对外检索），可快速推广技能。 / Cross-source search of global clinical-trial registries, normalized and aggregated. Auto-direct sources: ClinicalTrials.gov v2, PubChem (public REST, ordinary input + public retrieval). China CDE blocks automated browsers via WAF → external workflow for automatable retrieval (third-party endpoint, public query terms only egress, Bearer token REQUIRED — verified: HTTP 401 without it); ChiCTR retrieved via unified endpoint (source=chictr, third-party, shared Bearer), with user-pasted page as a local-parse fallback. EU CTIS supports retrieve-by-number only (no search). ISRCTN public API is dead but retrievable via unified endpoint (source=isrctn). Aggregates phase / status / sponsor / timeline / competitor landscape into JSON / Markdown (optional PNG; optional EU-CTR PDF download via download_docs.py to a local --out-dir). CDE also supports an optional commercial API key (--cde-api-key, sent only to the official CDE API). B-tier (ordinary input + public retrieval), quickly-adoptable.

ClawHub Agent Skills author: Wintone Zhang v0.9.0 MIT-0 52 files body ≈ 4 096 tokens Open the sourceclawhub.ai↗ analyzed 2 d ago

跨源检索全球临床试验注册库并归一化聚合。可自动化直连：ClinicalTrials.gov v2、PubChem（公开 REST API，零保密数据或信息输入）。中国 CDE 因 WAF 拦截自动化浏览器，改为外部工作流自动化检索（第三方端点，仅公开查询词出域，需 Bearer token，已实测无 token…

As a process F 49/100 · Will not run — References files that are not bundled: references/*.md

ProcedureInfrastructureData and analyticsAI and agentstype 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
73/100
safety, quality, tests
Safety 60%
97
Quality 40%
37
Run on models
none yet
Process rating
F
49/100
Will not run
References files that are not bundled: references/*.md
Tools and files w 18
0
Result and completion w 14
0
Progress reporting w 2
0
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.
  2. Shorten the description to 1024 characters.
  3. The text references files that are not there: add them or drop the references.
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 · 3

✓ No critical or high findings

Medium and low: 3
  • low Obfuscation obf-base64-blob adapters/bug_report.py:72
    Long base64-looking blob (detector / deny-list definition)
    "Bg1n…XQs
    detector
  • low Obfuscation obf-base64-blob config/keys.py:47
    Long base64-looking blob (quoted — discussed, not commanded)
    "coze_unified": "Bg1n…QjY
    quoted
  • low Obfuscation obf-base64-blob config/keys.py:49
    Long base64-looking blob (quoted — discussed, not commanded)
    "ictrp": "Bg1n…WGk
    quoted

Files scanned: 52. Evidence is masked. Grey chips explain why severity was lowered.

Against the Agent Skills spec

  • error description-long description is 1479 chars, limit 1024
  • warning description-no-when description does not say WHEN to use the skill (no "use when")
  • warning missing-ref reference to a missing file: references/*.md
  • 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"

Process rating: all ten parameters 49/100

Will not run. References files that are not bundled: references/*.md
  • 0Tools and files. 1 referenced file(s) missing: references/*.md
  • 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. 9 mutating operations with no state check
  • 70Inputs and preconditions. Inputs and preconditions are listed
  • 70Execution cost. Instruction body is 4096 tokens
  • 100Steps. 38 steps
  • 100Failures and branches. 2 branches, has a failure section
  • 100Consistency. Name and required fields are in place
  • medium Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
  • low 13 top-level sections: this looks like several domains in one skill
  • low The response is described with custom markup (3 tags): a typed call is more reliable

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)
  • +3Description length 1479: 120–800 characters recommended
  • +3Output format is not stated: the model decides each time
  • -38 of 15 scripts are never mentioned in SKILL.md
  • +2Single-language instructions
  • +4Structure: 14 headings
  • +3Step-by-step instructions: 38 items
  • +4Has examples (1 code blocks)
  • +4Reference files are cited in the instructions (3 of 8)
  • +1License stated

Quality base 70; lint remarks subtract, signals add up to 100. Result: 37.

External checks

ClawHub: suspicious
This clinical-trial search skill is mostly purpose-aligned, but it ships recoverable shared Bearer tokens and pre-approves third-party outbound endpoints, so users should review the data-flow tradeoffs before installing.
LLM: suspicious (high) · 23 Aug 2026