wiki-agents-md

Generates AGENTS.md files for repository folders — coding agent context files with build commands, testing instructions, code style, project structure, and boundaries. Only generates where AGENTS.md is missing.

Quality

81%

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

77%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 skill body is highly actionable and clearly sequenced with validation checkpoints for the destructive/batch generation operation. Its weaknesses are verbosity (redundant guard restatements across a long document) and a monolithic structure with no progressive disclosure via separate reference files.

Suggestions

Extract the large templates (e.g., the wiki AGENTS.md template and the full root/nested templates) into a references/template.md file and link to them, keeping the body as a lean overview.

Consolidate the 'only generate if missing' guard into one authoritative section and reference it elsewhere instead of restating it three times to reduce token cost.

Trim redundant prose around the Quality Principles and Anti-Patterns tables, which partially repeat guidance already conveyed by the template examples.

Dimension	Reasoning	Score
Conciseness	The body is mostly efficient with tight template blocks and examples, but it runs ~370 lines and includes some redundant restatement (e.g., the only-if-missing guard is explained in three separate sections) that could be tightened.	3 / 5
Actionability	Provides fully executable, copy-paste-ready bash commands and markdown templates with concrete examples covering the common cases (existence check, build commands, testing, structure, code style, boundaries).	5 / 5
Workflow Clarity	The generation process is a clearly numbered six-step sequence with an explicit existence-check validation step ('If it exists, stop') and a final validate step with feedback-style checks ('Every command references a real script'), satisfying the validation requirement for a batch/destructive operation.	5 / 5
Progressive Disclosure	The content is monolithic within a single SKILL.md with no bundle files and no one-level-deep references; the large templates (especially the ~40-line wiki template) are inlined rather than split into separate reference files, leaving organization only at the section-header level.	3 / 5
	Total	16 / 20 Passed

Description

75%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 is specific and distinctive, clearly conveying what the skill does and its output format. Its main weakness is the absence of an explicit 'Use when...' trigger clause, which limits the completeness score.

Suggestions

Add an explicit 'Use when...' trigger clause (e.g., 'Use when setting up coding agent context for a repository, when AGENTS.md is missing, or when the user asks to generate agent instructions for project folders.').

Include common synonyms or natural phrasings users would say (e.g., 'agent context files', 'onboarding agents to a codebase') to broaden trigger-term coverage.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions ('build commands, testing instructions, code style, project structure, and boundaries') and specifies exactly what the file contains, with comprehensive coverage of the AGENTS.md scope.	5 / 5
Completeness	It has a clear 'what' (generates AGENTS.md files with specific contents) and a weakly implied 'when' (only generates where AGENTS.md is missing), but no explicit 'Use when...' trigger clause, capping completeness at 3 per the guidelines.	3 / 5
Trigger Term Quality	Includes natural terms a user might say ('AGENTS.md', 'coding agent context files', 'build commands', 'testing instructions') and the file name itself, but lacks synonyms or common variations users would naturally phrase.	4 / 5
Distinctiveness Conflict Risk	The description carves a clear niche (generating AGENTS.md context files specifically) that is unlikely to trigger for unrelated skills; the filename-anchored scope gives minimal conflict risk.	5 / 5
	Total	17 / 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: freightCognition/linehaulai-claude-marketplace
Path: plugins/deep-wiki/skills/wiki-agents-md/SKILL.md
Commit: 88571a6

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.