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

81%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.

The body is a well-structured, actionable workflow with a confirmation checkpoint guarding the destructive edit and thorough edge-case handling. Minor gains are available by tightening restated principles and fixing the code-fence markers in the example.

Dimension	Reasoning	Score
Conciseness	The body is lean and assumes Claude's competence, with concrete tables and short rules rather than padded explanation. It is not 5 because the rules-vs-agents principle is restated across sections and a few explanatory sentences could be trimmed further.	4 / 5
Actionability	It provides concrete guidance: a scope-to-file table, format examples, and a specific confirmation prompt ('Add this rule to ...? (y/n)'). It is not 5 because the table-driven code example uses broken fence markers and there are no fully copy-paste-ready templates for every case.	4 / 5
Workflow Clarity	A clear five-step sequence with an explicit confirmation checkpoint before the destructive Edit ('Present the Change' then 'Apply on Confirmation') and a post-apply verification step, satisfying the validation requirement for destructive edits. It fully matches the anchor with explicit checkpoints and feedback for error recovery via the edge cases section.	5 / 5
Progressive Disclosure	Content is well-organized into Purpose, Input, Instructions, and Edge Cases with no nested references and no bundle files to navigate. It is not 5 because there are no signaled references to deeper material, though the simple-skill exception makes this a minor gap.	4 / 5
	Total	17 / 20 Passed

Description

53%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.

The description conveys a clear purpose and target but lacks an explicit 'when to use' trigger and only names a single concrete action. Adding a 'Use when...' clause with natural trigger phrases would lift completeness and trigger_term_quality.

Suggestions

Append an explicit trigger clause, e.g. 'Use when capturing a team convention, best practice, or correction that should apply automatically across the project.'

Expand specificity by listing 2-3 concrete actions (e.g. 'parses the convention, selects the right rules/agents file, drafts the addition, and applies it on confirmation').

Add natural user-facing trigger terms like 'add a rule', 'team convention', 'coding standard', or 'project guideline'.

Dimension	Reasoning	Score
Specificity	Names the domain ('team convention or best practice') and one concrete action ('adds it to the appropriate .claude/rules/ or .claude/agents/ file'), but stops short of listing multiple specific actions. It is below 4 because only a single action is described rather than several.	3 / 5
Completeness	It clearly states what the skill does (captures and adds a convention to rules/agents files) but provides no explicit 'when' trigger; per the guidelines a missing 'Use when...' clause caps completeness at 3. It is above 2 because the 'what' is clear and concrete.	3 / 5
Trigger Term Quality	Contains relevant natural terms ('team convention', 'best practice', 'rule') but lacks the common trigger phrases a user would actually say and has no 'Use when...' guidance. It is not 4 because synonyms and natural user phrasings are largely missing.	3 / 5
Distinctiveness Conflict Risk	The narrow focus on .claude/rules/ and .claude/agents/ file management gives it a clear niche with minimal overlap risk. It is not 5 because the phrasing is broad enough ('team convention or best practice') that it could mildly overlap with general memory or documentation skills.	4 / 5
	Total	13 / 20 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: ccabad6

Reviewed: about 12 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.