メニュー
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.
Codex または Claude でインストール この Prompt をコピーして Codex、Claude、または他のアシスタントに貼り付けると、Skill ページを確認してインストールできます。
SOC 職業分類に基づく
Inject reviewer-aligned rules into openspec/config.yaml so generated specs pass review on first attempt. Use to reduce review round-trips after /opsx:ff or spectra-propose.
Dual-engine spec review — Claude and Codex review the same change in parallel, then a Workflow loops fixes until BOTH engines are MEDIUM-clean. Use when a spec is high-stakes and you want two different models to cross-check for blind spots before implementation. Requires the openai-codex plugin for the Codex engine.
Review a spec, proposal, or design before implementation to catch gaps, risks, and ambiguities. Runs multi-angle parallel review by default; scans codebase for context first. Use --fix for iterative review+fix loop (agent escalates design-judgment issues to you), --angles to narrow the angle set.
Frame a feature, bug, or design question before building: scout the codebase, surface assumptions or interview, compare options, and converge on an explicit decision. Use when an idea needs sharpening before a spec or plan exists. Read-only — never implements.
Synthesize git activity across multiple projects over a time window into themed recall notes. Clusters commits into themes (features, fixes, refactors, infra, learning surface, tickets, side quests), auto-hides empty sections, and surfaces work that PM tools don't track. Use when the user asks 'what did I do last week', wants a multi-project activity summary, or needs to recall their development history.
Merge git branches with auto-generated Conventional Commits messages. Use when merging branches, finishing feature work, or creating merge commits.
| name | reviewer:result |
| description | 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. |
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, and provide log_script_path — resolve ${CLAUDE_PLUGIN_ROOT}/scripts/log-findings.sh to an absolute path.
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, log_script_path — resolve ${CLAUDE_PLUGIN_ROOT}/scripts/log-findings.sh to an absolute path).
The agent will cd to the git root automatically. Provide it with: