skill-comply

Visualize whether skills, rules, and agent definitions are actually followed — auto-generates scenarios at 3 prompt strictness levels, runs agents, classifies behavioral sequences, and reports compliance rates with full tool call timelines. Use when checking whether agents actually follow the skills, rules, and definitions they were given, rather than assuming they do.

Quality

84%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Passed

No findings from the security scan

Quality

Content

76%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 concise, actionable overview with strong copy-paste usage examples and a clear process sequence. The main weakness is workflow clarity: the batch agent-running pipeline lacks explicit validation or feedback-loop checkpoints, which the rubric caps at 3 for batch operations.

Suggestions

Add an explicit validation/checkpoint step to the workflow (e.g. 'after running scenarios, verify traces were captured before classifying') to introduce a feedback loop and lift the workflow_clarity cap.

Briefly signal the scripts/ bundle structure (e.g. note that run.py orchestrates runner.py, classifier.py, grader.py, report.py) so the implementation map is discoverable from SKILL.md.

Fold the one-line 'Key Concept: Prompt Independence' into the intro or Report Contents section to remove a near-empty heading.

Dimension	Reasoning	Score
Conciseness	The body is lean and well-sectioned with no padding or explanation of concepts Claude already knows, but a few lines (e.g. the standalone 'Key Concept' one-liner) could be folded into surrounding context to tighten further.	4 / 5
Actionability	The Usage block gives copy-paste-ready commands covering the common cases — full run, dry run, and custom models — so Claude knows exactly how to invoke the skill.	5 / 5
Workflow Clarity	A clear six-step sequence is present (spec generation → scenarios → run → classify → ordering → report), but there are no explicit validation checkpoints or feedback loops, and the batch agent-running step is a batch operation that the rubric caps at 3 without validation.	3 / 5
Progressive Disclosure	Well-organized sections with a concise overview and a brief inline Advanced note; however the ten-file scripts/ bundle is only implicitly referenced via `python -m scripts.run` rather than explicitly navigated, leaving minor organization gaps.	4 / 5
	Total	16 / 20 Passed

Description

92%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: concrete actions, explicit 'Use when' trigger, and a distinct compliance-measurement niche. The only minor gap is trigger-term variety, which relies on a single natural phrasing rather than synonyms or file-extension cues.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions — 'auto-generates scenarios at 3 prompt strictness levels, runs agents, classifies behavioral sequences, and reports compliance rates with full tool call timelines' — giving comprehensive coverage of what the skill does.	5 / 5
Completeness	Explicitly answers both 'what' (the four concrete actions) and 'when' ('Use when checking whether agents actually follow...'), with a concrete trigger phrase rather than a weak implication.	5 / 5
Trigger Term Quality	The 'Use when checking whether agents actually follow the skills, rules, and definitions they were given' clause is a natural phrasing a user would say, but it lacks synonyms or varied surface forms beyond the core formulation.	4 / 5
Distinctiveness Conflict Risk	Occupies a clear niche — measuring agent compliance with given skills/rules/definitions — with distinct triggers unlikely to fire for unrelated skills.	5 / 5
	Total	19 / 20 Passed

Validation

87%

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 — 14 / 16 Passed

Validation for skill structure

Criteria	Description	Result
metadata_version	'metadata.version' is missing	Warning
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	14 / 16 Passed

Repository: affaan-m/ECC
Path: skills/skill-comply/SKILL.md
Commit: 07756ce

Reviewed: 2 hours 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.