What exactly does the debug-review skill check?

It validates skill structure, cross-references between orchestrators and perspectives, project-specific content density, instruction clarity, and compliance with mandatory review templates.

What happens if a skill fails the validation check?

The debug-review skill generates a detailed report identifying missing mandatory elements or structural issues, allowing you to refine your generation parameters or fix the skill manually.

When is the best time to use this skill?

It is designed to run automatically after the build-skills process, but you can trigger it manually whenever you update your project's knowledge base or review patterns.

How does it ensure reviews aren't generic?

The skill includes a Specificity Validation check that flags skills if they lack project-specific references like file paths, module names, or unique architectural patterns found in your knowledge base.

Does it check for all technical concerns?

Yes, it verifies the presence of the 8 mandatory technical concerns: execution-flow, resource-management, concurrency, security, platform-constraints, implementation-quality, code-health, and strategic-alignment.

Skill Debug Review

Name: Skill Debug Review
Author: suzuki0keiichi

bysuzuki0keiichi

0•

開発者ツール

Validates and audits the quality of generated Claude Code review skills to ensure they are project-specific, structurally sound, and instructionally clear.

The debug-review skill is an essential quality assurance tool for the tailored-reviewer plugin, designed to verify that generated review skills in the .claude/skills/ directory meet rigorous standards. It performs deep audits of structural integrity, cross-reference consistency, and project-specific depth, ensuring that AI-driven reviews aren't just generic templates but are grounded in your actual codebase. By checking for instruction compliance, agent delegation logic, and template adherence, it guarantees that your automated review pipeline functions reliably and provides high-value technical feedback.

主な機能

01Template compliance verification against mandatory archetypes and technical concerns

02Specificity scoring to ensure skills contain project-specific file paths and module names

03Detection of vague instructions or ambiguous logic that could lead to LLM skip errors

04Automated structural validation of YAML frontmatter and Markdown formatting

05Cross-reference integrity checks between entry-point skills and perspective perspectives

060 GitHub stars

ユースケース

01Ensuring custom domain perspectives correctly reference the project's internal knowledge base

02Automatically validating newly generated review skills after a build-skills execution

03Debugging AI review agents that are providing generic or surface-level feedback

主な機能

01Template compliance verification against mandatory archetypes and technical concerns

02Specificity scoring to ensure skills contain project-specific file paths and module names

03Detection of vague instructions or ambiguous logic that could lead to LLM skip errors

04Automated structural validation of YAML frontmatter and Markdown formatting

05Cross-reference integrity checks between entry-point skills and perspective perspectives

060 GitHub stars

ユースケース

01Ensuring custom domain perspectives correctly reference the project's internal knowledge base

02Automatically validating newly generated review skills after a build-skills execution

03Debugging AI review agents that are providing generic or surface-level feedback