rulecheck

Autonomous rule adherence checker. Scans the codebase for rule violations, fixes the highest-impact ones in an isolated worktree, runs full validation, creates a PR. Uses memory to track progress across runs.

Quality

76%

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

Fix and improve this skill with Tessl

tessl review fix ./.claude/skills/rulecheck/SKILL.md

Quality

Content

85%Weight 40%Scale 1-3

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

The body is a tight, actionable orchestrator skill with a clear sequenced workflow and explicit failure handling; its main weakness is redundancy between the two sections that restate the same boundaries.

Suggestions

Merge the overlapping "Do NOT" rules into the "Your Job" steps or trim the duplicates so each boundary appears once, reducing token redundancy.

Consider a one-line explicit checkpoint noting that completion is the only validation gate (e.g. "Treat the agent's completion notification as your sole signal to proceed to reporting").

Dimension	Reasoning	Score
Conciseness	The body is lean and assumes competence, but the "Your Job" numbered steps and the "Rules for You" bullets substantially overlap (both forbid scanning, editing, and checking on the agent), so it could be tightened — the score-2 anchor for mostly efficient with some redundancy.	2 / 3
Actionability	Concrete, copy-paste-ready instructions are given ("Launch the rulecheck-agent with the focus area: $ARGUMENTS", then wait and relay), and the instruction-only guidance is fully actionable without needing code.	3 / 3
Workflow Clarity	A clear launch→wait→report sequence is laid out with explicit error-recovery handling (context-limit and missing-PR-URL cases), satisfying the feedback-loop expectation even though the destructive fixing is delegated to the agent.	3 / 3
Progressive Disclosure	At under 50 lines with no external references needed and no bundle files present, the well-organized sections (## Your Job, ## Rules for You) meet the simple-skill bar for full marks.	3 / 3
	Total	11 / 12 Passed

Description

67%Weight 40%Scale 1-3

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

The description is specific, third-person, and distinct, but it omits any explicit "Use when..." trigger guidance, which caps both completeness and trigger-term quality at the mid level.

Suggestions

Add an explicit trigger clause, e.g. "Use when the user asks to check or fix CLAUDE.md / project rule violations, or wants rule adherence enforced via PR."

Broaden natural trigger keywords to include phrases users actually say (e.g. "lint CLAUDE.md", "enforce project rules", "rule violations") alongside "CLAUDE.md".

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions — "Scans the codebase for rule violations, fixes the highest-impact ones in an isolated worktree, runs full validation, creates a PR" — matching the score-3 anchor for listing several specific actions.	3 / 3
Completeness	The "what" is clear (scan, fix, validate, PR, memory), but the "when" is only implied with no explicit trigger guidance; per the guidelines a missing "Use when..." clause caps completeness at 2.	2 / 3
Trigger Term Quality	Relevant terms like "rule violations" and "CLAUDE.md" appear, but coverage of natural user phrasings is thin and there is no "Use when..." trigger, so it lands at "some relevant keywords but missing common variations."	2 / 3
Distinctiveness Conflict Risk	The niche — autonomously checking and fixing CLAUDE.md rule adherence then opening a PR — is specific and unlikely to collide with other skills, matching the clear-niche anchor.	3 / 3
	Total	10 / 12 Passed

Validation

93%

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 — 15 / 16 Passed

Validation for skill structure

Criteria	Description	Result
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	15 / 16 Passed

Repository: coleam00/Archon
Path: .claude/skills/rulecheck/SKILL.md
Commit: ace0a41

Reviewed: 8 days 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.