cy-fix-reviews
Fix Reviews
Execute the review remediation workflow in a strict sequence. The review files already exist and define the full scope for the run.
Required Inputs
- The scoped issue files listed in
<batch_issue_files>. - The PRD review round directory and
_meta.md. - The repository verification workflow required by
cy-final-verify.
Workflow
-
Gather round context.
- Read
_meta.mdfrom the review round directory to understand the provider, round number, and issue counts. - Read
<batch_scope>to identify the PRD name, review round, code files in scope, and conditional flags such as auto-commit.
- Read
-
Read and triage the scoped issue files.
- Read every listed issue file completely before editing code.
- Update each issue file frontmatter
statusfrompendingtovalidorinvalid. - Record concrete technical reasoning in
## Triage: state why the issue is valid or invalid, identify the root cause if valid, and outline the intended fix approach.
-
Fix valid issues completely.
- Fix issues in severity order: critical first, then high, medium, low. This ensures the most impactful fixes land even if the batch is interrupted.
- Implement production-quality fixes for every
validissue in scope. - Add or update tests when behavior changes or regressions are possible. Test file edits are always in scope when they validate a fix.
- Keep code changes constrained to the files listed in
<batch_scope>code files. If a fix absolutely requires touching a file not listed there, limit the change to the minimum needed and document why in the issue file's## Triagesection. - Do not refactor, clean up, or improve code that is unrelated to the issues being fixed.
-
Close out issue files correctly.
- For a
validissue, set frontmatterstatus: resolvedonly after the code and verification are done. - For an
invalidissue, document why it is invalid and then set frontmatterstatus: resolvedonce the analysis is complete.
- For a
-
Verify before completion.
- Use
cy-final-verifybefore any completion claim or automatic commit. - Run the repository’s real verification commands; do not stop at partial checks.
- If verification fails, fix the failing checks in the code you changed. Do not revert your fixes to pass verification -- find the root cause of the failure and address it. If the failure is in pre-existing code unrelated to your changes, document it in the relevant issue file’s
## Triagesection and proceed. If two fixes conflict with each other and verification cannot pass after two attempts, document the conflict in both issue files and report the situation rather than looping indefinitely. - If all issues in the batch are invalid and no code was changed, skip the commit step entirely -- do not create an empty commit. Still run verification to confirm no regressions.
- Leave the diff ready for manual review unless
<batch_scope>shows "Automatic commits: enabled".
- Use
Critical Rules
- Do not fetch or export reviews inside this workflow.
fetch-reviewsalready produced the round files. - Do not call provider-specific scripts or
ghmutations. Compozy resolves provider threads after the batch succeeds. - Do not modify issue files outside the scoped batch.
- Do not mark an issue
resolvedbefore the underlying work and verification are actually complete.
More from compozy/kb
kb
Comprehensive skill for the `kb` CLI and the Karpathy Knowledge Base pattern. Covers the full KB lifecycle — topic scaffolding, multi-source ingestion (URLs, files, YouTube, bookmarks, codebases), wiki article compilation, cross-article querying with file-back, lint-and-heal passes, QMD indexing, and hybrid search. Also covers codebase-specific analysis via inspect commands for complexity, coupling, blast radius, dead code, circular dependencies, symbol/file lookups, backlinks, and code smells. Use when working with kb CLI commands, knowledge base workflows, code vault generation, code graph analysis, code metrics inspection, wiki compilation, or the ingest-compile-query-lint cycle. Do not use for general code review, linting, formatting, building Go projects, or writing application code.
14systematic-qa
Executes full-project QA like a real user by discovering the repository verification contract, running build, lint, test, and startup commands, exercising core workflows end-to-end, creating realistic fixtures when needed, fixing root-cause regressions, and rerunning the full gate. Use when validating a branch, release candidate, migration, refactor, or risky commit. Do not use for static code review only, one-off unit test edits, or architecture brainstorming without execution.
1cy-create-tasks
Decomposes PRDs and TechSpecs into detailed, independently implementable task files with enrichment from codebase exploration. Use when a PRD or TechSpec exists and needs to be broken down into executable tasks, or when task files need enrichment with implementation context. Do not use for PRD creation, TechSpec generation, or direct task execution.
1find-skills
Helps users discover and install agent skills when they ask questions like "how do I do X", "find a skill for X", "is there a skill that can...", or express interest in extending capabilities. This skill should be used when the user is looking for functionality that might exist as an installable skill.
1lesson-learned
Analyze recent code changes via git history and extract software engineering lessons. Use when the user asks 'what is the lesson here?', 'what can I learn from this?', 'engineering takeaway', 'what did I just learn?', 'reflect on this code', or wants to extract principles from recent work.
1git-rebase
Intelligently handle git rebase operations and resolve merge conflicts while preserving features and maintaining code quality. Use when rebasing feature branches, resolving conflicts across commits, and ensuring clean linear history without losing changes.
1