Document control system management for medical device QMS. Covers document numbering, version control, change management, and 21 CFR Part 11 compliance. Use for document control procedures, change control workflow, document numbering, version management, electronic signature compliance, or regulatory documentation review.
86
73%
Does it follow best practices?
Impact
94%
1.17xAverage score across 6 eval scenarios
Passed
No known issues
Optimize this skill with Tessl
npx tessl skill review --optimize ./ra-qm-team/quality-documentation-manager/SKILL.mdQuality
Discovery
100%Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.
This is a strong skill description that clearly defines its domain (medical device QMS document control), lists specific capabilities, and provides explicit trigger guidance via a 'Use for...' clause. The regulatory specificity (21 CFR Part 11) and domain focus (medical device) make it highly distinctive and easy for Claude to select appropriately.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Lists multiple specific concrete actions: document numbering, version control, change management, and 21 CFR Part 11 compliance. These are clearly defined capabilities within a well-scoped domain. | 3 / 3 |
Completeness | Clearly answers both 'what' (document control system management covering numbering, version control, change management, Part 11 compliance) and 'when' (explicit 'Use for...' clause listing six specific trigger scenarios). | 3 / 3 |
Trigger Term Quality | Includes strong natural keywords users would say: 'document control', 'change control', 'document numbering', 'version management', 'electronic signature', '21 CFR Part 11', 'regulatory documentation', 'QMS'. These cover common variations a user in this domain would naturally use. | 3 / 3 |
Distinctiveness Conflict Risk | Highly distinctive with a clear niche: medical device QMS document control with 21 CFR Part 11 compliance. The combination of regulatory specificity and domain focus makes it very unlikely to conflict with generic document or version control skills. | 3 / 3 |
Total | 12 / 12 Passed |
Implementation
47%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This skill is a comprehensive document control reference but suffers from excessive verbosity—it reads like a QMS training manual rather than a concise skill for Claude. The workflow clarity is strong with explicit validation checkpoints at each process, but the sheer volume of reference tables (regulatory clauses, category codes, KPIs, audit findings) inflates token cost significantly. Much of this content should be moved to reference files, leaving a lean overview in the main skill.
Suggestions
Move regulatory requirement tables (ISO 13485 clauses, FDA 21 CFR 820 sections), category codes, KPI tables, and common audit findings to reference files, keeping only the essential workflow steps and validation checkpoints in the main skill.
Remove or drastically condense explanatory tables that Claude can infer (e.g., comment disposition types, signature requirements, document lifecycle stages) and focus on the specific conventions and rules unique to this organization's QMS.
Add executable code or concrete output examples for the document_validator.py tool—show what a validation pass/fail looks like so Claude knows how to interpret results.
Consolidate the approval matrix and reviewer tables into a single concise reference rather than repeating approval requirements across multiple sections.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The skill is extremely verbose at ~350+ lines, with extensive tables covering regulatory requirements, category codes, KPIs, and audit findings that Claude already knows or could infer. Much of this is reference material (ISO clause numbers, FDA CFR sections, common audit findings) that adds token cost without providing novel, actionable guidance. The document reads more like a training manual than a concise skill instruction. | 1 / 3 |
Actionability | The skill provides structured workflows with numbered steps and includes a concrete tool example (document_validator.py with sample JSON input and CLI commands). However, most guidance is procedural/organizational rather than executable—tables describe what should happen but don't provide copy-paste-ready implementations. The validator script is referenced but not shown, and much content is descriptive rather than instructive. | 2 / 3 |
Workflow Clarity | Multi-step workflows are clearly sequenced with numbered steps, and each workflow ends with an explicit validation checkpoint (e.g., 'Validation: Document accessible at point of use; obsolete versions removed'). The change control process includes classification-based routing and an impact assessment checklist. The lifecycle stages table provides clear state transitions. | 3 / 3 |
Progressive Disclosure | The skill references external files (references/document-control-procedures.md, references/21cfr11-compliance-guide.md) and includes a table of contents, which is good. However, the main file itself is monolithic with extensive inline content (regulatory requirement tables, KPIs, audit findings, category codes) that should be in reference files. The overview-to-detail ratio is poor—too much detail is kept inline. | 2 / 3 |
Total | 8 / 12 Passed |
Validation
90%Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.
Validation — 10 / 11 Passed
Validation for skill structure
| Criteria | Description | Result |
|---|---|---|
frontmatter_unknown_keys | Unknown frontmatter key(s) found; consider removing or moving to metadata | Warning |
Total | 10 / 11 Passed | |
a96cc20
Table of Contents
If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.