add-rule

Captures a team convention or best practice and adds it to the appropriate .claude/rules/ or .claude/agents/ file

Quality

67%

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/add-rule/SKILL.md

Quality

Content

85%

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 well-structured, actionable instruction skill with clear sequencing, a confirmation gate, and error-recovery handling; only mild redundancy in the rules-vs-agents principle keeps conciseness from the top anchor. Tightening the repeated explanations would raise it further.

Suggestions

Consolidate the rules-vs-agents principle into a single statement in section 2 and reference it from sections 5 and the bolded note rather than restating it.

Consider trimming the explanatory rationale in section 1 ('the why is critical for future developers') to a shorter clause, since the instruction already requires capturing the reason.

Dimension	Reasoning	Score
Conciseness	Lean and free of generic concept explanation, but the rules-vs-agents principle is restated across section 2, the bolded note, and section 5, which could be tightened.	2 / 3
Actionability	Provides copy-paste-ready rule-format examples, a concrete scope-to-target-file table, exact target file paths, and a literal confirmation prompt, giving fully actionable guidance for an instruction-only skill.	3 / 3
Workflow Clarity	A clear five-step sequence includes an explicit confirmation checkpoint before the destructive file edit and error-recovery loops in Edge Cases (duplicate and contradiction handling), satisfying the feedback-loop requirement.	3 / 3
Progressive Disclosure	A single-purpose, self-contained skill with no external references and well-organized sections (Purpose, Input, five-step Instructions, Edge Cases) qualifies for the top score under the no-external-references allowance.	3 / 3
	Total	11 / 12 Passed

Description

50%

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 conveys the core purpose and target file type clearly, but it lacks an explicit 'Use when' trigger clause and natural trigger-term coverage, leaving all dimensions at the mid-level. Adding explicit usage triggers and more natural keyword variations would lift it toward the top anchors.

Suggestions

Add an explicit 'Use when...' trigger clause, e.g. 'Use when a team member states a convention, best practice, or correction to formalize into .claude/rules or .claude/agents.'

Include natural trigger-term variations users would actually say, such as 'add a rule', 'save this convention', 'enforce this practice', or 'remember this standard'.

List a couple of concrete distinct actions (e.g. 'Drafts the rule, matches it to the right scope file, and confirms before applying') to push specificity toward score 3.

Dimension	Reasoning	Score
Specificity	Names the domain ('team convention or best practice') and a concrete action path ('Captures... and adds it to the appropriate .claude/rules/ or .claude/agents/ file'), but does not list multiple distinct concrete actions like the score-3 anchor.	2 / 3
Completeness	Clearly states what the skill does but provides no 'Use when...' clause or equivalent explicit trigger guidance, capping completeness at 2 per the rubric guideline.	2 / 3
Trigger Term Quality	Includes some natural keywords ('team convention', 'best practice') but misses common user variations like 'add a rule', 'save this convention', or 'remember this'.	2 / 3
Distinctiveness Conflict Risk	Specifies a target niche (.claude/rules/ or .claude/agents/ files) but lacks distinct explicit triggers and the broad 'convention or best practice' phrasing could overlap with general memory/convention skills.	2 / 3
	Total	8 / 12 Passed

Validation

100%

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 — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository: stacklok/toolhive
Path: .claude/skills/add-rule/SKILL.md
Commit: cd373ec

Reviewed: 2 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.