CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

ra-qm-skills

Router/index for the 15 regulatory & quality-management skills bundled in this plugin (ISO 13485 QMS, EU MDR 2017/745, FDA submissions under QMSR, ISO 14971 risk, CAPA, document control, ISO 27001/ISMS, ISO 42001 AIMS, EU AI Act, GDPR/DSGVO, SOC 2, auditing). Use when a compliance request doesn't obviously match one skill and you need to pick the right one (e.g., 'prepare us for an ISO 13485 audit', 'is my AI system high-risk under the AI Act').

70

Quality

88%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide
SecuritybySnyk

Passed

No findings from the security scan

The canonical home for this skill is ra-qm-skills in alirezarezvani/claude-skills

SKILL.md
Quality
Evals
Security

Quality

Content

88%Weight 40%Scale 1-5

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

An exemplary router skill body: token-efficient, assumption of competence, a fully concrete routing table with a tie-breaker rule and a citation-verification checkpoint. The only flaws are cosmetic — inconsistent path prefixes between the routing table and the instruction/quick-start lines.

Suggestions

Unify path prefixes: the routing table's Path column ('skills/<skill>/') should match the instruction line and quick start ('ra-qm-team/skills/<skill>/') so the load target is unambiguous.

State what to do when no row matches (e.g., 'if no row matches, say so and ask for more detail') to close the routing decision tree.

DimensionReasoningScore

Conciseness

The ~40-line body is lean and functional: a dense signal→skill→path routing table, a two-line quick start, and three terse rules. It assumes Claude's competence — no padding explaining what the standards are or how compliance works — so every token earns its place, matching anchor 5.

5 / 5

Actionability

Concrete, executable guidance throughout: an exact routing table with paths, a copy-pasteable quick-start command ('cat ra-qm-team/skills/risk-management-specialist/SKILL.md'), and a tie-breaker rule for multi-match cases. The minor gap is a path-prefix inconsistency — the table's Path column says 'skills/...' while the instruction line and quick start use 'ra-qm-team/skills/...' — so anchor 4 rather than fully unambiguous anchor 5.

4 / 5

Workflow Clarity

This is a simple single-purpose skill (route to exactly one skill) and the single action is unambiguous: match request signals in the table, load the named SKILL.md, ask one clarifying question on multi-match, and a citation-verification checkpoint ('Verify regulatory citations against the current text'). Per the simple-skill exception, this warrants 5; no destructive or batch operations apply a cap.

5 / 5

Progressive Disclosure

The router correctly delegates all detail to the 15 sibling skills — one level deep, clearly signaled via the routing table — with well-organized sections (Routing table / Quick start / Rules). However, the referenced paths are given with inconsistent prefixes ('skills/...' vs 'ra-qm-team/skills/...') and no bundle is present to verify them, which is a minor organization gap matching anchor 4 rather than 5.

4 / 5

Total

18

/

20

Passed

Description

83%Weight 40%Scale 1-5

Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.

A strong description: explicit what/when with concrete example triggers, third-person voice, and good keyword coverage of the compliance domain. Its only weaknesses are the narrow single-action framing (routing) and inherent trigger overlap with the very skills it indexes.

Suggestions

Add one or two more of the underlying actions a router performs (e.g., 'matches request signals to a skill and delegates') to move from one action to multiple concrete actions.

Include a few missing natural trigger terms such as 'quality management system', '510(k)', or 'technical file' to widen keyword coverage.

Sharpen the 'when' clause to also exclude direct matches (e.g., 'skip when a request clearly names one skill') to further reduce overlap with the bundled skills' own triggers.

DimensionReasoningScore

Specificity

The description states a concrete function ('Router/index for the 15 regulatory & quality-management skills') and comprehensively enumerates the covered frameworks (ISO 13485 QMS, EU MDR 2017/745, FDA submissions under QMSR, ISO 14971 risk, CAPA, ...), but the action set is narrow — a single routing function rather than multiple concrete actions, so it fits anchor 4 better than 5.

4 / 5

Completeness

It explicitly answers both 'what' ('Router/index for the 15 regulatory & quality-management skills bundled in this plugin') and 'when' ('Use when a compliance request doesn't obviously match one skill and you need to pick the right one') with concrete example trigger phrases — a direct match to the anchor-5 example pattern.

5 / 5

Trigger Term Quality

It includes verbatim natural user phrases ('prepare us for an ISO 13485 audit', 'is my AI system high-risk under the AI Act') plus a broad set of standard names users actually cite (GDPR/DSGVO, SOC 2, CAPA, EU MDR). A few natural terms are missing (e.g., 'quality management system', '510(k)'), placing it at anchor 4 rather than comprehensive anchor 5.

4 / 5

Distinctiveness Conflict Risk

The router niche is clear and differentiated by the 'doesn't obviously match one skill' qualifier, but the description names all 15 domains, which overlap the trigger terms of each bundled skill (e.g., 'ISO 13485 audit' could directly match the ISO 13485 skill). This is minor overlap risk with closely related skills — anchor 4, not the minimal-conflict anchor 5.

4 / 5

Total

17

/

20

Passed

Validation

93%

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation — 15 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

frontmatter_unknown_keys

Unknown frontmatter key(s) found; consider removing or moving to metadata

Warning

Total

15

/

16

Passed

Repository

alirezarezvani/claude-skills

Path

.gemini/skills/ra-qm-skills/SKILL.md

Reviewed

Table of Contents

Is this your skill?

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.