doc-maintenance

Audit README, SPEC, and PRODUCT docs against recent git history for drift and make minimal PR-ready edits. Use when asked to review docs for accuracy, after major feature merges, or on a schedule.

Quality

83%

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

Quality

Content

78%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 well-structured, highly actionable doc-maintenance workflow with clean progressive disclosure into two real reference files. The main weakness is redundancy between the prose steps and the consolidated tables/sections, which inflates token cost without adding guidance.

Suggestions

Deduplicate change classification: keep either the Step 2 prose bullets or the 'Change Classification Rules' table (which adds the 'Doc update needed?' column) and reference it from the other location rather than restating both.

Merge 'Patch Style Guide' into Step 5's edit rules (or vice versa) since they overlap heavily; keep one canonical list of patch principles to cut tokens.

Add an explicit post-edit verification checkpoint in Step 5 or 6 (e.g., re-run each edited doc's quickstart/commands mentally, or re-check edited entries against audit-checklist.md) before committing and opening the PR.

Dimension	Reasoning	Score
Conciseness	The body avoids explaining concepts Claude already knows and stays mostly efficient, but change classification is stated twice (Step 2 prose and the 'Change Classification Rules' table) and patch guidance is stated twice (Step 5 rules and the 'Patch Style Guide'), so it could be tightened; not severe enough for 2 but not the lean 4.	3 / 5
Actionability	Fully executable, copy-paste-ready bash is provided for every operational step (cursor read, git log, branch creation, commit, push, and a complete gh pr create heredoc with PR body), covering the common cases as the 5 anchor requires.	5 / 5
Workflow Clarity	A clearly sequenced 7-step workflow with checkpoints (skip-to-Step-7 when no notable changes, cursor update at the end) and validation via the audit checklist in Step 4; the only gap is an explicit post-edit verification before opening the PR, which keeps it at 4 rather than 5.	4 / 5
Progressive Disclosure	The SKILL.md body is a well-organized overview that signals one-level-deep references to real bundle files ('Use references/audit-checklist.md as the structured checklist', 'Use references/section-map.md'), with the detailed checklist and section map appropriately split into separate files for easy navigation.	5 / 5
	Total	17 / 20 Passed

Description

87%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 strong description that clearly states both capability and trigger conditions with concrete, natural language. The only soft spot is trigger-term coverage, where a few common synonyms would push it from good to comprehensive.

Dimension	Reasoning	Score
Specificity	Names the domain (README, SPEC, PRODUCT docs) and several concrete actions ('Audit ... for drift', 'make minimal PR-ready edits') with only minor coverage gaps, fitting the 4 anchor above the 3 anchor which expects just 1-2 actions.	4 / 5
Completeness	It explicitly answers both what ('Audit README, SPEC, and PRODUCT docs ... for drift and make minimal PR-ready edits') and when ('Use when asked to review docs for accuracy, after major feature merges, or on a schedule') with concrete trigger phrases, matching the 5 anchor.	5 / 5
Trigger Term Quality	Natural trigger phrases are present ('asked to review docs for accuracy', 'after major feature merges', 'on a schedule'), giving good keyword coverage, but synonyms like 'documentation', 'stale', or 'out of date' are missing so it stops short of 5.	4 / 5
Distinctiveness Conflict Risk	The niche is clearly scoped to auditing specific doc types against git history for drift, with distinct schedule/merge triggers, yielding minimal conflict risk with other skills.	5 / 5
	Total	18 / 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: paperclipai/paperclip
Path: .agents/skills/doc-maintenance/SKILL.md
Commit: bd1fdc2

Reviewed: 5 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.