SKILLEMALL.ai
GitHub ↗ RU Sign in

BD medical-device-postmarket

医疗器械上市后监管（Post-Market Surveillance, PMS）实操手册——中美欧日四市场上市后义务对照（不良事件报告、PSUR 定期安全报告、FSCA/召回现场安全纠正、PMCF 上市后临床跟踪）、各市场报告时限与流程清单（美国 21 CFR 803 致死 30 天/严重 90 天、欧盟 MDCG 2022-21 PSUR 频率、中国 2018 年 1 号令报告时限、日本 PMDA）、PMS 计划与 PSUR 撰写框架、监测-报告-纠正闭环落地，附零依赖本地工具一键查询义务对照、报告时限与生成 PMS/PSUR 框架。面向医械法规、质量与临床负责人，拿证后的持续合规一站理清。

ClawHub Hermes author: zhaoxinghua09-cell v1.1.0 MIT-0 11 files body ≈ 569 tokens Open the sourceclawhub.ai↗ analyzed 3 d ago

医疗器械上市后监管（Post-Market Surveillance, PMS）实操手册——中美欧日四市场上市后义务对照（不良事件报告、PSUR 定期安全报告、FSCA/召回现场安全纠正、PMCF 上市后临床跟踪）、各市场报告时限与流程清单（美国 21 CFR 803 致死 30 天/严重 90 天、欧盟 MDCG…

As a process D 46/100 · Unfinished process — weak spots: result and completion, when it triggers, inputs and preconditions

ProcedureInfrastructuretype and topics are labelled automatically from the skill text
Runs in: OpenClaw Hermes Agent
JSON
Technical rating
B
81/100
safety, quality, tests
Safety 60%
90
Quality 40%
68
Run on models
none yet
Process rating
D
46/100
Unfinished process
Result and completion w 14
0
Inputs and preconditions w 11
0
Failures and branches w 10
0
the three weakest of ten parameters · all ten

What is at stake

Medium-severity findings: the skill is probably honest, but read what alarmed the scanner.

Obfuscation medium severity

Below is the worst case for this category. The finding here is medium: the guard saw a sign, not a proof.

If you install

The files contain invisible characters, encoded commands or comments hidden from readers but visible to the model. What you read differs from what the agent sees.

For the author

Remove invisible characters (they usually sneak in through copy-paste) and encoded strings: no catalog will pass them. Instructions for the model must be readable by a human too.

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. For Hermes the description must be one sentence under 60 characters; move the conditions to a "When to Use" section.
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
  • medium Obfuscation obf-base64-blob references/上市后监管知识库.md:75
    Long base64-looking blob
    | 2018 年第 1 号令全文（PDF） | [samr.gov.cn 不良事件监测和再评价管理办法 PDF](https://www.samr.gov.cn/cms_files/filemanager/samr/www/samrnew/samrgkml/nsjg/bgt/202106/W020…pdf) |
  • medium Obfuscation obf-base64-blob skill-card.md:41
    Long base64-looking blob
    - [SAMR medical device adverse event monitoring measures](https://www.samr.gov.cn/cms_files/filemanager/samr/www/samrnew/samrgkml/nsjg/bgt/202106/W020…pdf)

Files scanned: 11. Evidence is masked. Grey chips explain why severity was lowered.

Against the Agent Skills spec

  • warning description-long-hermes description is 300 chars; the Hermes authoring standard requires ≤ 60 (one sentence, ending with a period)
  • warning description-no-when neither description nor a "## When to Use" section says when to use the skill
  • note frontmatter-key unknown frontmatter key "slug"
  • note frontmatter-key unknown frontmatter key "display_name"
  • note frontmatter-key unknown frontmatter key "displayName"
  • note frontmatter-key unknown frontmatter key "title"
  • note frontmatter-key unknown frontmatter key "description_en"

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. 16 steps
  • 100Consistency. Name and required fields are in place
  • 100Execution cost. Instruction body is 569 tokens
  • 100Running it twice. No mutating operations

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
  • +2Single-language instructions
  • +3Description length 300: enough signal without eating the budget
  • +4Structure: 10 headings
  • +3Step-by-step instructions: 16 items
  • +4Has examples (1 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: 68.

External checks

ClawHub: suspicious
The skill appears locally scoped and purpose-aligned, but its security audit contains copied references to a different package, so its safety assurances should be reviewed carefully.
LLM: suspicious (high) · VirusTotal: · 27 Aug 2026