collection-compliance

Diagnose and fix `.catalog/` validation failures (schema, roster, banners, sample workflows, JSON mirror). Use when: - `make validate` or CI reports collection compliance errors - A PR adds skills but catalog was not updated - `collection.json` is out of sync with `collection.yaml` - Catalog metadata/fragments might have drifted from README/CLAUDE/SKILL golden sources Remediation is via the create-collection workflow and `catalog_yaml_to_json.py`—not by weakening checks.

Quality

81%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Low

Low-risk findings worth noting

Quality

Content

75%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.

A well-structured, actionable workflow body that assumes competence and gives concrete commands with an end-to-end validation checkpoint. It could be tightened by deduplicating Common Issues against the Classify step and making the retry loop explicit.

Suggestions

Make the validation feedback loop explicit: after step 4 'Re-validate', add 'If failures remain, return to Classify (step 2) with the new errors' to reach the top workflow_clarity anchor.

Dedupe the Common Issues section against the Classify bullets, or collapse Common Issues into short cross-references so the classification logic lives in one place.

For abstract remediation steps like 'align YAML with schema.yaml', add the one concrete command or field check that performs the alignment.

Dimension	Reasoning	Score
Conciseness	The body is dense and information-rich with no padding or explanation of basic concepts, assuming Claude's competence; minor redundancy between the Classify bullets and the Common Issues section keeps it just below the lean anchor.	4 / 5
Actionability	Provides copy-paste-ready commands (`uv run python scripts/validate_collection_compliance.py`, `make catalog-mirror-json`) and a concrete example block, but a few remediation steps remain abstract ('align YAML with schema.yaml', 'AI semantic alignment review').	4 / 5
Workflow Clarity	A clear four-step sequence (Re-run → Classify → AI review → Re-validate) with an explicit validation checkpoint at the end; the error-recovery loop is implied rather than spelled out ('if still failing, repeat from Classify'), so it sits below the feedback-loop anchor.	4 / 5
Progressive Disclosure	Well-organized into labeled sections with clearly signaled one-level-deep references ([COLLECTION_SPEC.md], catalog/schema.yaml, create-collection skill); no bundle files exist to verify, and most detail is appropriately inline for a workflow skill.	4 / 5
	Total	16 / 20 Passed

Description

87%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, specific description that clearly states what the skill does and gives explicit, natural trigger conditions. The only modest gap is that the action verbs are general ('diagnose and fix') while the specificity is carried mostly by the enumerated failure types.

Dimension	Reasoning	Score
Specificity	Names the domain ('Diagnose and fix `.catalog/` validation failures') and enumerates concrete failure types (schema, roster, banners, sample workflows, JSON mirror), but the verbs themselves are limited to 'diagnose and fix' rather than a list of distinct actions, leaving minor coverage gaps relative to the comprehensive anchor.	4 / 5
Completeness	Explicitly answers both 'what' (diagnose and fix .catalog/ validation failures) and 'when' via a dedicated 'Use when:' block with four concrete trigger conditions, matching the anchor for clearly and explicitly answering both.	5 / 5
Trigger Term Quality	The 'Use when' bullets include natural trigger phrases a contributor would actually encounter ('make validate or CI reports collection compliance errors', 'collection.json is out of sync with collection.yaml'), with good keyword coverage including file names and commands, though a few natural synonyms are missing.	4 / 5
Distinctiveness Conflict Risk	It occupies a clear niche (`.catalog/` collection compliance for a specific toolchain) with distinct triggers (make validate, CI, JSON/YAML drift) and minimal overlap risk with other skills.	5 / 5
	Total	18 / 20 Passed

Validation

81%

Warnings & errors only

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

Validation — 13 / 16 Passed

Validation for skill structure

Criteria	Description	Result
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning
relative_links	Relative link issues: 4 suspicious	Warning
referenced_paths_exist	Referenced path issues: 6 missing	Warning

	Total	13 / 16 Passed

Repository: RHEcosystemAppEng/agentic-plugins
Path: .claude/skills/collection-compliance/SKILL.md
Commit: e46c4fa

Reviewed: 1 day ago

Table of Contents

Discovery Implementation Validation

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.