doc-pr-fix

Autonomous fixer for documentation PRs. Triggered by @claude comments on PRs targeting dev. Reads the writer's request and the doc-pr review comment, then applies fixes and commits. Use this skill whenever a writer tags @claude on a documentation PR — not for interactive help (use doc-help for that), but for autonomous, single-shot fixes in CI.

Quality

86%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Low

Low-risk findings worth noting

Quality

Content

88%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 tight, executable runbook with a clear seven-step workflow, verification step, and feedback guidance. Progressive disclosure is good but limited by the absence of any bundle files and some redundant behavioral notes.

Dimension	Reasoning	Score
Conciseness	Mostly efficient, action-oriented prose with executable gh/git commands; a few behavioral-note repeats could be tightened, but it avoids explaining concepts Claude already knows.	4 / 5
Actionability	Provides concrete, copy-paste-ready gh API and git commands with literal-value guidance and complete bash heredocs covering the common fix cases.	5 / 5
Workflow Clarity	Seven clearly sequenced steps with an explicit verification checkpoint (Step 5), error-recovery guidance ('fix what's clear, ask about what isn't'), and a final completion update covering the destructive/batch commit-and-push path.	5 / 5
Progressive Disclosure	Well-organized sections with the workflow inline and one-level references (docs/CLAUDE.md, /doc-help) clearly signaled; no bundle files present, so minor organization gaps keep it just below 5.	4 / 5
	Total	18 / 20 Passed

Description

83%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 clearly conveys both capability and trigger conditions with concrete, third-person language and an explicit 'Use when' clause plus a negative boundary. It is slightly above the mid-anchors on specificity and trigger coverage.

Dimension	Reasoning	Score
Specificity	Names a concrete domain (documentation PRs) and several specific actions (reads request and review comment, applies fixes, commits) with only minor coverage gaps.	4 / 5
Completeness	Explicitly states both what it does (reads request and review comment, applies fixes, commits) and when to use it ('Use this skill whenever a writer tags @claude on a documentation PR'), plus a negative boundary (not for interactive help).	5 / 5
Trigger Term Quality	Includes natural phrases a writer would say ('@claude on a documentation PR', 'fixes') with good coverage, though it leans on the @claude mention rather than broad synonym coverage.	4 / 5
Distinctiveness Conflict Risk	Niche trigger (@claude on docs PRs in CI) is fairly distinct, but minor overlap risk with sibling doc-help/doc-pr review skills it explicitly disambiguates from.	4 / 5
	Total	17 / 20 Passed

Validation

93%

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 — 15 / 16 Passed

Validation for skill structure

Criteria	Description	Result
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	15 / 16 Passed

Repository: netwrix/docs
Path: .claude/skills/doc-pr-fix/SKILL.md
Commit: a2eb049

Reviewed: 3 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.