SKILLEMALL.ai
GitHub ↗ RU Sign in

CC fda-consultant-specialist

FDA regulatory consultant for medical device companies, covering 510(k)/PMA/De Novo pathways, QSR (21 CFR 820), HIPAA, and device cybersecurity. Use for FDA submissions, predicate and substantial-equivalence analysis, and premarket strategy.

borghei/Claude-Skills Agent Skills author: borghei 9 files · 3 scripts body ≈ 8 091 tokens Open the sourcegithub.com↗ analyzed 8 h ago

FDA regulatory consultant for medical device companies, covering 510(k)/PMA/De Novo pathways, QSR (21 CFR 820), HIPAA, and device cybersecurity.

As a process C 57/100 · Has gaps — weak spots: result and completion, inputs and preconditions, execution cost

ProcedureSecuritytype and topics are labelled automatically from the skill text
Runs in: 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) OpenClaw Goose OpenCode
JSON
Technical rating
C
89/100
safety, quality, tests
Safety 60%
93
Quality 40%
82
Run on models
none yet
Process rating
C
57/100
Has gaps
Inputs and preconditions w 11
0
Progress reporting w 2
0
Running it twice w 4
30
the three weakest of ten parameters · all ten

How to improve

  1. The SKILL.md body is over 5,000 tokens: move reference detail into references/ and load it when needed.
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 · 7

✓ No critical or high findings

Medium and low: 7
  • low Risky intent intent-offensive-security references/device_cybersecurity_guidance.md:72
    Offensive-security / dual-use content (legitimate for authorised testing; review intended use)
    │   ├── Penetration testing
  • low Risky intent intent-offensive-security references/device_cybersecurity_guidance.md:104
    Offensive-security / dual-use content (legitimate for authorised testing; review intended use)
    | Penetration testing | Required | Recommended |
  • low Risky intent intent-offensive-security references/device_cybersecurity_guidance.md:504
    Offensive-security / dual-use content (legitimate for authorised testing; review intended use)
    - Bug bounty program: [if applicable]
  • low Risky intent intent-offensive-security references/device_cybersecurity_guidance.md:604
    Offensive-security / dual-use content (legitimate for authorised testing; review intended use)
    - [ ] Penetration test report
  • low Risky intent intent-offensive-security references/device_cybersecurity_guidance.md:674
    Offensive-security / dual-use content (legitimate for authorised testing; review intended use)
    | Insufficient testing | Conduct penetration testing |
  • low Risky intent intent-offensive-security SKILL.md:259
    Offensive-security / dual-use content (legitimate for authorised testing; review intended use)
    | Security Testing | Penetration testing, vulnerability scanning |
  • low Risky intent intent-offensive-security SKILL.md:468
    Offensive-security / dual-use content (legitimate for authorised testing; review intended use)
    │   ├── Penetration testing report

Files scanned: 9. Evidence is masked. Grey chips explain why severity was lowered.

Against the Agent Skills spec

  • warning body-long SKILL.md body ≈ 8091 tokens (recommended < 5000); move details to references/
  • note edit-residue the text marks something as outdated (lines 320, 322, 586, 635): check that old rules are not kept next to new ones — the full check reads the text for contradictions

Process rating: all ten parameters 57/100

  • 0Inputs and preconditions. Does not say what the process needs to start
  • 0Progress reporting. Says nothing while it works
  • 30Running it twice. 7 mutating operations with no state check
  • 40Result and completion. Does not say what the result is
  • 40Execution cost. Instruction body is 8091 tokens: crowds the task out of the window
  • 50When it triggers. No condition that starts the skill
  • 60Tools and files. Uses tools (bash) that frontmatter does not declare
  • 85Steps. 95 steps, 1 vague phrases
  • 100Failures and branches. 1 branches, has a failure section
  • 100Consistency. Name and required fields are in place
  • low 21 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
  • +2Single-language instructions
  • +3Description length 241: enough signal without eating the budget
  • +4Structure: 58 headings
  • +3Step-by-step instructions: 95 items
  • +4Has examples (8 code blocks)
  • +4Reference files are cited in the instructions (5 of 5)
  • +3All 3 scripts are documented
  • +1License stated

Quality base 70; lint remarks subtract, signals add up to 100. Result: 82.