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

83%

Does it follow best practices?

Impact

—

No eval scenarios have been run

Securityby

Advisory

Suggest reviewing before use

Quality

Content

77%

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 skill with clear workflow sequencing and concrete executable commands throughout. Its main weakness is moderate verbosity — some guidance is repeated across sections, and the behavioral notes partially duplicate constraints already stated in the steps. The progressive disclosure is adequate but the document is on the longer side for a skill that could potentially offload some detail.

Suggestions

Consolidate the 'only fix what was requested' guidance — it appears in Step 4 and Behavioral Notes; keep it in one place to reduce redundancy.

Consider trimming the Input section — Claude doesn't need the instruction 'Do not use shell variable expansion' explained at length; a single line like 'Use literal values from the prompt (no $VAR expansion)' suffices.

Dimension	Reasoning	Score
Conciseness	The skill is mostly efficient and avoids explaining concepts Claude already knows, but some sections are verbose — the behavioral notes repeat guidance already implicit in the steps (e.g., 'only fix what was requested' appears in both Step 4 and Behavioral Notes), and the input parsing section over-explains literal value usage.	2 / 3
Actionability	The skill provides fully executable commands throughout — specific gh CLI commands, git commands, and API calls with concrete syntax. The examples include exact command structures with placeholders clearly tied to extracted input values, making them copy-paste ready.	3 / 3
Workflow Clarity	The 7-step workflow is clearly sequenced with explicit branching (question vs. file edit paths), a verification step (Step 5), progress tracking via comment updates at milestones, and clear guidance on when to stop early. The behavioral notes provide error recovery guidance (ask when unclear, skip meaning-changing fixes).	3 / 3
Progressive Disclosure	The skill references `docs/CLAUDE.md` and `/doc-help` appropriately, but the content is fairly long (~150 lines) and some sections like the behavioral notes could potentially be split out. However, with no bundle files provided, the single-file approach is reasonable though the inline detail is heavy for an overview document.	2 / 3
	Total	10 / 12 Passed

Description

89%

Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.

This is a strong description with excellent completeness and distinctiveness. It clearly defines when to use the skill (and when not to), includes natural trigger terms, and distinguishes itself from a related skill. The main weakness is that the specific actions ('applies fixes') could be more concrete about what types of fixes are performed.

Suggestions

Specify the types of fixes applied (e.g., 'corrects grammar, fixes formatting, updates links, restructures content') to improve specificity from generic 'applies fixes'.

Dimension	Reasoning	Score
Specificity	It names the domain (documentation PRs) and some actions ('reads the writer's request', 'applies fixes and commits'), but the core action 'applies fixes' is vague — it doesn't specify what kinds of fixes (e.g., formatting, grammar, link repair, content restructuring).	2 / 3
Completeness	Clearly answers both 'what' (reads requests and review comments, applies fixes and commits on documentation PRs) and 'when' (whenever a writer tags @claude on a documentation PR, not for interactive help). The explicit 'Use this skill whenever...' clause and the negative boundary ('not for interactive help') are strong.	3 / 3
Trigger Term Quality	Includes strong natural trigger terms: '@claude comments', 'PRs targeting dev', 'documentation PR', 'doc-pr review comment', 'tags @claude'. These are terms a user or CI system would naturally use when this skill should activate.	3 / 3
Distinctiveness Conflict Risk	Highly distinctive — it explicitly differentiates itself from 'doc-help' for interactive use, scopes to autonomous CI fixes on documentation PRs triggered by @claude, and targets a very specific workflow niche unlikely to conflict with other skills.	3 / 3
	Total	11 / 12 Passed

Validation

90%

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 — 10 / 11 Passed

Validation for skill structure

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

	Total	10 / 11 Passed

Repository: netwrix/docs
Commit: 6b797b3

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.