AD cn-med-oa
中文医学文献开放获取(OA)检索下载与引用验证套件。通过维普OA平台(oa.cqvip.com)免登录、 免费检索中文医学期刊并下载 PDF 全文；输出完整 Vancouver/GB-T7714 元数据（标题/作者/期刊/ 年/卷/期/页/DOI/ISSN/CN刊号/摘要/关键词/基金/分类号），可直拼参考文献行；内置相关性守门 （防平台OR匹配捞回无关结果）与五态引用验证器 verify_cn_refs（防AI幻觉引用，判定语义与 pubmed-verifier 一致）。SQLite缓存/重试退避/日配额/控频，零依赖纯标准库。 触发词："下中文文献"、"找中文文献"、"中文医学文献下载"、"找OA版"、"开放获取"、"免费下载论文"、 "国内指南共识解读"、"找参考文献"、"中文文献支撑"、"补中文引文"、"验证中文引用"、"核查中文文献"、 "下载维普文献"、"找几篇中文的"、"写文献综述要中文参考"。 英文："download chinese paper"、"find OA chinese literature"、"verify chinese citations"。 即使用户只说"帮我下载这篇中文文献"或"找几篇类风湿的中文论文"也应触发。
中文医学文献开放获取(OA)检索下载与引用验证套件。通过维普OA平台(oa.cqvip.com)免登录、 免费检索中文医学期刊并下载 PDF 全文；输出完整 Vancouver/GB-T7714 元数据（标题/作者/期刊/…
As a process D 46/100 · Unfinished process — weak spots: result and completion, when it triggers, inputs and preconditions
How to improve
- Say in the description WHEN to use the skill ("use when…", example requests): that is the agent's main cue.
- 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 Exfiltration
read-dotenvscripts/yiigle_tracker.py:196Reads a .env file (detector / deny-list definition)set -a; source ~/.hermes/.env; set +a
detector
Files scanned: 15. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
- warning
description-no-whendescription does not say WHEN to use the skill (no "use when")
Process rating: all ten parameters 46/100
- 0Result and completion. Does not say what the result is
- 0Inputs and preconditions. Does not say what the process needs to start
- 0Failures and branches. Linear process with no failure handling
- 0Progress reporting. Says nothing while it works
- 20When it triggers. No condition that starts the skill
- 60Tools and files. Uses tools (python) that frontmatter does not declare
- 100Steps. 24 steps
- 100Consistency. Name and required fields are in place
- 100Execution cost. Instruction body is 2131 tokens
- 100Running it twice. No mutating operations
- low 11 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
- +4Description does not say when NOT to use the skill (false activations)
- +3Output format is not stated: the model decides each time
- -212 emoji in the instructions: noise for the model
- -31 of 3 scripts are never mentioned in SKILL.md
- +2Single-language instructions
- +5Description quotes 14 example trigger phrases
- +3Description length 533: enough signal without eating the budget
- +4Structure: 13 headings
- +3Step-by-step instructions: 24 items
- +4Has examples (5 code blocks)
- +4Reference files are cited in the instructions (1 of 1)
- +1License stated
Quality base 70; lint remarks subtract, signals add up to 100. Result: 77.