Name: content-fix
Rating: 96 (1 reviews)
Author: netwrix

content-fix

Autonomous fixer for documentation content issues. Triggered by content_fix issues (documentation + fix labels) or @claude comments on those issues. Reads the issue, identifies affected files, applies fixes following Netwrix writing standards, and pushes a branch. A separate workflow step creates the PR. Asks clarifying questions if the request is ambiguous.

1.60x

Quality

96%

Does it follow best practices?

Impact

96%

1.60x

Average score across 3 eval scenarios

Securityby

—

The risk profile of this skill

Quality

Content

100%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.

This is a tightly engineered skill body: executable commands throughout, an ordered workflow with explicit stop conditions and fallbacks, a machine-parseable output contract, and heavy content properly delegated to an external reference. No dimension shows meaningful weakness.

Dimension	Reasoning	Score
Conciseness	The body is ~87 lean lines with zero concept explanations and no padding — every line is instructional (commands, decision rules, output format). It assumes Claude's competence fully, matching the "every token earns its place" anchor.	5 / 5
Actionability	Fully executable, copy-paste-ready commands (gh issue view, git checkout -b, git push) with a commit message template, a precise URL-to-path mapping rule with a worked example ("10_8 → 10.8"), and an exact output contract ("BRANCH_NAME=fix/issue-<number>-<slug>") demonstrated by a full example. Covers the common cases completely.	5 / 5
Workflow Clarity	Six clearly sequenced steps with an explicit fallback strategy for file location (URL → product+search → ask and STOP), checkpoints ("Verify the file exists", clarity check, ambiguity STOP conditions), and an unambiguous termination contract ("Do NOT stop until you have either pushed a branch or posted a clarifying question"). Error-recovery paths are built in, matching the 5 anchor.	5 / 5
Progressive Disclosure	A single, well-organized overview with no bundle bloat: all sections (Input, Workflow, Rules) are appropriately placed, and the only heavy content (writing standards) is correctly externalized to a clearly-signaled one-level reference ("Read `docs/CLAUDE.md` before starting"). Nothing that belongs in a separate file is inlined.	5 / 5
	Total	20 / 20 Passed

Description

92%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.

An excellent description: third-person voice, concrete lifecycle actions, and an explicit, narrowly-scoped trigger. The only weakness is that trigger terms are repo-internal jargon (label names) rather than natural user phrasing, which slightly limits natural-language matching.

Dimension	Reasoning	Score
Specificity	"Reads the issue, identifies affected files, applies fixes following Netwrix writing standards, and pushes a branch" lists multiple specific concrete actions covering the entire lifecycle (read, locate, fix, push, escalate ambiguities). Comprehensive for its domain, matching the 5 anchor; nothing is vague or generic.	5 / 5
Completeness	Both questions are explicitly answered: the "what" is a full concrete action chain ("Reads the issue... applies fixes... pushes a branch") and the "when" is explicit ("Triggered by content_fix issues (documentation + fix labels) or @claude comments on those issues"). Matches the 5 anchor.	5 / 5
Trigger Term Quality	"content_fix issues (documentation + fix labels)" and "@claude comments" give good keyword coverage with explicit trigger conditions, but the terms are internal workflow jargon rather than natural user phrases (e.g., "docs typo", "fix the documentation"), and no synonyms or variations are offered.	4 / 5
Distinctiveness Conflict Risk	The trigger is narrowly scoped to a specific labeled issue type and @claude comments on those issues — a clear niche with distinct triggers and minimal conflict risk with other skills. Scope boundaries ("A separate workflow step creates the PR") further sharpen it.	5 / 5
	Total	19 / 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/content-fix/SKILL.md
Commit: 9dbd89e

Reviewed: 7 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.