editing-rules-and-skills

Use when editing or creating rules or skills (global or project). Routes to the correct voice and process based on whether the work is correction-driven (encoding a behavioral lesson) or informative (documenting a capability).

Quality

66%

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/editing-rules-and-skills/SKILL.md

Quality

Content

71%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, well-sequenced routing skill with good guardrails ('What this skill is NOT'). Its main weakness is progressive disclosure: the body offloads detail to three referenced files that are absent from the bundle, breaking the navigation it promises.

Suggestions

Ship the referenced bundle files (correction-driven.md, informative-capability.md, placement.md) under references/ — the body routes to them but they are missing, which is the single biggest quality gap.

Add an explicit validation checkpoint after placement (e.g., 'confirm the chosen voice and target file with Josh before writing') to close the workflow's validation gap and push workflow_clarity toward 5.

Trim the justificatory sentence 'classifying wrong is the single biggest way this skill gets misapplied' to tighten conciseness further.

Dimension	Reasoning	Score
Conciseness	The body is lean and assumes Claude's competence (no explanation of what rules/skills are), with only minor over-explanation such as 'classifying wrong is the single biggest way this skill gets misapplied' that could be trimmed, fitting 'efficient; minor instances of over-explanation'.	4 / 5
Actionability	It gives concrete directives ('Load correction-driven.md before editing', 'Load placement.md for both decisions') and a copy-paste-ready sentence to ask Josh, but the referenced files are not present in the bundle, leaving a minor gap that keeps it below fully-executable level 5.	4 / 5
Workflow Clarity	A clear classify -> load voice file -> load placement.md -> edit sequence is present with a decision-gate fallback ('If unsure, ask Josh in one sentence'); this is not a destructive/batch operation so the cap-at-3 rule does not apply, but there is no explicit post-placement validation step, so it stops at level 4.	4 / 5
Progressive Disclosure	The body is well-structured with clearly signaled one-level-deep references ('Load correction-driven.md', 'Load informative-capability.md', 'Load placement.md'), but none of these files exist in references/, scripts/, or assets/, so the navigation the overview points to is broken — per the rubric guideline to score against the actual bundle structure, this caps the score at 3.	3 / 5
	Total	15 / 20 Passed

Description

62%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 clear, third-person description that answers both what and when for a well-scoped meta-skill, with distinct triggers and low conflict risk. It is held back from the top band by a single routing action and limited synonym/trigger-phrase coverage.

Suggestions

Add a couple more concrete actions (e.g., 'drafts, reframes, and places the rule or skill in the right file and voice') to lift specificity beyond a single routing verb.

Surface the natural user phrasings already in the body ('let's document this so it doesn't happen again', 'make sure you know about X') as trigger terms to broaden trigger-term coverage.

Dimension	Reasoning	Score
Specificity	The description names the domain ('editing or creating rules or skills') and one concrete routing action ('Routes to the correct voice and process based on whether the work is correction-driven... or informative'), but does not enumerate several specific actions, so it sits at 'names domain and 1-2 concrete actions' rather than the more comprehensive level 4.	3 / 5
Completeness	It answers both what ('Routes to the correct voice and process...') and when ('Use when editing or creating rules or skills (global or project)'); the 'when' is explicit but could be more specific with concrete trigger phrases, so it is not the level-5 fully-explicit anchor.	4 / 5
Trigger Term Quality	'editing or creating rules or skills (global or project)' supplies relevant keywords, but the description omits the natural user phrasings the body itself uses ('let's document this so it doesn't happen again', 'make sure you know about X') and lacks synonym coverage, matching 'some relevant keywords but missing common variations'.	3 / 5
Distinctiveness Conflict Risk	The meta-niche of editing Claude's own rules/skills with distinct correction-driven vs informative triggers is clearly distinguishable with minimal conflict risk, though there is minor overlap with generic editing/documentation skills, placing it just below the level-5 clear-niche anchor.	4 / 5
	Total	14 / 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: joshmanders/dotfiles
Path: .claude/skills/editing-rules-and-skills/SKILL.md
Commit: 54ab5f6

Reviewed: 4 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.