From reviewer
Review implementation against a spec using git diffs to catch mismatches, missing work, and bugs. Supports iterative review+fix with --fix flag and parallel multi-angle review. Use after implementing a feature to verify spec coverage.
How this skill is triggered — by the user, by Claude, or both
Slash command
/reviewer:resultThe summary Claude sees in its skill listing — used to decide when to auto-load this skill
Review implementation against a spec by analyzing git diffs and cross-referencing with spec requirements.
Review implementation against a spec by analyzing git diffs and cross-referencing with spec requirements.
Provide spec file paths and optionally a base branch:
$result docs/plans/auth-flow/
$result spec.md tasks.md --base develop
$result docs/plan/ -b main
With iterative auto-fix:
$result docs/plan/ --fix
$result docs/plan/ --fix --base main -n 5 --fix-all
$result docs/plan/ --fix --parallel "security,coverage"
If no paths are given, ask which spec files to review against.
--fix)Without --fix: use the companion result-reviewer.md in this directory as the agent prompt.
With --fix: dispatch reviewer:result-fix-orchestrator with parameters (spec_paths, working_directory, base_branch, max_iterations, parallel, angles, fix_all, review-angles template content).
The agent will cd to the git root automatically. Provide it with:
npx claudepluginhub shdennlin/agent-plugins --plugin reviewerReviews code changes since a fixed point (commit, branch, tag) against coding standards and spec requirements, reporting results side by side.
Reviews code changes against specifications, plans, quality heuristics, and repo rules, then appends a remediation phase if gaps are found. Invoke via /review.
Reviews code changes by comparing diff to coding standards and spec/issue requirements using parallel sub-agents.