add-rule

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

Quality

74%

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.

This is a well-structured, highly actionable instruction skill: an unambiguous five-step workflow with confirmation and verification checkpoints, a precise scope-to-file mapping, and thoughtful edge-case handling. Its only real weaknesses are minor redundancy in the rules-vs-agents explanation and a malformed nested code-fence in the format examples.

Dimension	Reasoning	Score
Conciseness	The body is efficient and table-driven with no padding about concepts Claude already knows; only minor over-explanation remains, e.g. step 5's "rules are auto-loaded when matching files are touched, and agents inherit the full context" repeats the rules-vs-agents principle already established in step 2.	4 / 5
Actionability	Concrete guidance throughout — the exact scope-to-file table, verbatim user prompts ("Add this rule to `.claude/rules/testing.md`? (y/n)"), and format examples — but the "Rule with example" block uses a malformed escaped fence ("` ``go") that Claude could replicate literally, a minor gap versus fully copy-paste-ready.	4 / 5
Workflow Clarity	A clear five-step sequence (understand → find target → draft → present → apply) with an explicit confirmation checkpoint before the file edit and a post-apply verification step ("Verify the file is still well-structured"), plus an Edge Cases section covering duplicates, conflicts, and over-broad rules.	5 / 5
Progressive Disclosure	Sections are well-organized and all content is appropriately inline with no bundle files or nested references, but at ~95 lines it exceeds the under-50-line simple-skill case, and the scope table plus format examples could arguably live in a reference file.	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 communicates a clear, distinct capability with concrete file destinations, but it omits any explicit 'when to use this' trigger guidance and lacks the natural keyword "rule" that users would most likely say. It reads as a functional one-liner rather than a fully discoverable trigger description.

Suggestions

Add an explicit trigger clause, e.g. "Use when the user asks to add a rule, save a convention, or make a correction permanent for the team."

Include the natural keywords users would say — "add a rule", "save this convention", "team convention" — in the description itself rather than only in the .claude/rules/ path.

Briefly name the key sub-actions (draft the rule, confirm with the user, apply to the file) to lift specificity from 1-2 actions toward comprehensive coverage.

Dimension	Reasoning	Score
Specificity	"Captures a team convention or best practice and adds it to the appropriate .claude/rules/ or .claude/agents/ file" names two concrete actions with specific destinations, but stops short of the several-action coverage of the 4 anchor; the draft/confirm/apply workflow is absent.	3 / 5
Completeness	The 'what' is clear (capture a convention and write it to a rules/agents file), but there is no 'Use when...' clause or equivalent explicit trigger guidance, which caps completeness at 3 per the judging guidelines.	3 / 5
Trigger Term Quality	"team convention" and "best practice" are phrases a user might naturally say, but the most common trigger phrasing ("add a rule", "rule", "convention") is missing or only implicit in the path string, matching the 'some relevant keywords but missing common variations' anchor.	3 / 5
Distinctiveness Conflict Risk	The .claude/rules/ and .claude/agents/ targets give it a clear niche that is mostly distinct from other skills; only minor overlap risk with memory/preference-capture skills keeps it below 5.	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: 4c866b5

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.