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

—

Does it follow best practices?

Impact

—

No eval scenarios have been run

Securityby

Advisory

Suggest reviewing before use

Quality

Content

72%

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

The content is highly actionable with executable gh/git commands and a clear step sequence, but it loses points on conciseness (duplicated guidance between steps and Behavioral Notes) and workflow clarity (a soft verify step with no feedback loop for batch+push operations). Progressive disclosure is strong given the single-file, well-sectioned structure.

Suggestions

Consolidate the 'only fix what was requested' guidance into one location and have other steps reference it, removing the duplication between Step 3, Step 4, and Behavioral Notes.

Strengthen Step 5 Verify with a concrete checkpoint and a feedback loop (e.g., re-run gh pr diff to confirm only intended files changed, and if unintended edits appear, revert and retry) since the skill batches edits and pushes to a PR.

Trim the Behavioral Notes to only add net-new guidance (e.g., the 'fix what's clear, ask about what isn't' hybrid behavior) rather than restating rules already embedded in the steps.

Dimension	Reasoning	Score
Conciseness	The body is mostly lean and assumes Claude's competence, but the Behavioral Notes restate "don't fix unrequested issues" already covered in Steps 3 and 4, adding redundancy; it is not 3 because of that duplicated guidance, and not 1 because no basic concepts are over-explained.	2 / 3
Actionability	It provides fully executable gh/git commands with heredocs and a real commit-message template, plus explicit literal-value substitution guidance; it is not 2 because the examples are copy-paste ready rather than pseudocode.	3 / 3
Workflow Clarity	The 7-step sequence is clear and includes a Step 5 Verify checkpoint, but verification is a soft self-review with no concrete criterion or feedback loop for batch edits plus a push; per the rubric's destructive/batch note, the missing retry loop caps this at 2 rather than 3.	2 / 3
Progressive Disclosure	No bundle files exist, so scoring rests on organization: the body is split into clearly headed sections (Input, Steps 1–7, Behavioral Notes) with no nested references and nothing that should be split out; it is not 2 because the structure is clean and navigable rather than monolithic.	3 / 3
	Total	10 / 12 Passed

Description

100%

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 is specific, well-triggered, complete, and distinct: it names concrete actions, uses the exact @claude trigger a writer would type, gives an explicit Use-when clause, and explicitly contrasts with doc-help. It is among the strongest examples in the rubric.

Dimension	Reasoning	Score
Specificity	"Reads the writer's request and the doc-pr review comment, then applies fixes and commits" lists multiple concrete actions, matching the score-3 anchor; it is not the level below because it goes beyond naming a domain to enumerate specific operations.	3 / 3
Completeness	It states what the skill does ("applies fixes and commits") and gives an explicit "Use this skill whenever..." when-trigger, satisfying both halves; it is not the level below because the trigger is explicit, not merely implied.	3 / 3
Trigger Term Quality	"Use this skill whenever a writer tags @claude on a documentation PR" uses the exact natural trigger ("@claude") a writer would say; it is not the level below because the keywords are the real-world trigger terms rather than generic jargon.	3 / 3
Distinctiveness Conflict Risk	"not for interactive help (use doc-help for that), but for autonomous, single-shot fixes in CI" carves out a clear niche and explicitly disambiguates from doc-help; it is not the level below because the contrast removes overlap with sibling skills.	3 / 3
	Total	12 / 12 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
Commit: c229736

Reviewed: 2 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.