feat: add codebase-audit and architecture-review skills - #14
Merged
Conversation
Six structured audit passes across all repos in repos.json: 1. Code bugs (typos, logic errors, shell bugs, copy-paste) 2. Convention compliance (modelines, indentation, exit_error, sourcing) 3. Structural completeness (required files per implementation guides) 4. Schema validation (schema self-validation + data-against-schema) 5. Documentation accuracy (CLAUDE.md, README, stale references) 6. Cross-repo consistency (file references, workshop packages, metrics) Convention findings are aggregated per-repo for scannable output. Supports --scope, --focus, --severity, --since for targeted re-audits. Offers Jira/GitHub issue creation after report review. Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
Seven review dimensions evaluated by parallel agents: 1. Abstraction integrity (endpoint/engine/controller/plugin boundaries) 2. Coupling analysis (toolbox surface, dependency graph, implicit coupling) 3. Plugin contract completeness (undocumented assumptions, schema vs reality) 4. Error model (propagation, distributed failure, recovery) 5. Configuration architecture (format inventory, override chains, validation) 6. Data flow (metric pipeline, file transfer, log convergence) 7. Evolution and sustainability (language strategy, schema evolution, tests) Complements codebase-audit (bottom-up file defects) with top-down subsystem analysis. Supports --scope, --depth, and --repo arguments. Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
atheurer
approved these changes
Aug 3, 2026
atheurer
left a comment
atheurer
left a comment
There was a problem hiding this comment.
Approved! I have conducted a thorough structured review of the added codebase-audit and architecture-review skills. The instructions are exceptionally thorough, high-quality, and structurally consistent with the repository's patterns.
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
2 participants
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
Summary
Both are instruction-only skills (no backing Python scripts).
Test plan
/crucible-tools:codebase-audit --scope bench-sleepon the smallest benchmark to validate methodology/crucible-tools:architecture-review --scope contracts --depth surveyto validate a single-dimension review🤖 Generated with Claude Code