skills/requesting-review/SKILL.md
Use when completing plan-driven tasks, implementing major features, or before merging to verify work meets requirements.
npx skillsauth add sipengxie2024/superpower-planning requesting-reviewInstall this skill globally with one command. Works with Claude Code, Cursor, and Windsurf.
3 of 9 scanners reported clean
Some scanners were skipped, did not run, or reported a non-clean status. Review each row below.
Dispatch superpower-planning:code-reviewer before defects or plan drift compound.
Core principle: Review early, review often.
This skill defines when review is required and what context must be sent. The authoritative detailed reviewer contract lives in skills/requesting-review/code-reviewer.md. Do not maintain competing detailed review checklists elsewhere.
Mandatory:
Optional but valuable:
Every review request must ask for:
The review request must be diff-bounded and include:
{WHAT_WAS_IMPLEMENTED}{PLAN_OR_REQUIREMENTS}{BASE_SHA}{HEAD_SHA}{DESCRIPTION}When a plan or spec file exists, also provide:
PLAN_PATHSPEC_PATHREVIEW_MODEFOCUS when a specific check deserves extra attentionLocal policy: prefer exact plan/spec file paths and task text over paraphrased summaries. Do not weaken review context to a generic request.
BASE_SHA=$(git rev-parse HEAD~1) # or origin/main / last reviewed commit
HEAD_SHA=$(git rev-parse HEAD)
Use skills/requesting-review/code-reviewer.md as the request body and replace its placeholders with the current change context.
Dispatch superpower-planning:code-reviewer with the filled template. If the environment routes through agents/code-reviewer.md, treat that file as a compatibility entrypoint only; the detailed review contract still comes from skills/requesting-review/code-reviewer.md.
WHAT_WAS_IMPLEMENTED: Task 3 - verification and repair functions
PLAN_OR_REQUIREMENTS: Task 3 from .planning/plan.md
PLAN_PATH: .planning/plan.md
SPEC_PATH: .planning/design.md
BASE_SHA: a7981ec
HEAD_SHA: 3df7661
DESCRIPTION: Added verifyIndex() and repairIndex() with 4 issue types
REVIEW_MODE: intermediate task review
FOCUS: plan alignment, tests, error handling
.planning/progress.md.planning/findings.mdCodex-Driven:
Executing Plans / Ad-Hoc Development:
Claude Code Dynamic Workflows:
Never:
development
Use when a spec or requirements exist for a multi-step task and an implementation plan needs to be written before touching code
data-ai
Use when about to claim work is complete, fixed, or passing, before committing or creating PRs.
data-ai
Use when executing implementation plans with parallel task groups or individual tasks too heavy for subagent context limits.
development
Use when implementing any feature or bugfix, before writing implementation code