feO2x/guided-coding / skills/guided-coding-review-plan
guided-coding-review-plan
UnverifiedReview a completed Guided Coding plan draft against the codebase before its Planning Phase ends. Run only when explicitly requested by the user or by another Guided Coding skill.
Review a Plan
Review the plan named by the user or by the invoking skill. If none is named, proceed only when exactly one uncommitted plan draft exists in ai-plans/. Otherwise, ask for its path. Report findings only. Never edit the plan or any other file.
Read the plan, applicable repository instructions, the code it discusses, and every earlier document for the same issue, including legacy filenames. Verify assertions about existing types, members, files, APIs, and extension points. Do not reject files or types merely because the plan intends to create them.
Check at least the following:
- Acceptance criteria: Each criterion describes an observable, verifiable outcome rather than an implementation step. Behavior changes require appropriate automated test coverage.
- Verifiability: The required feedback loops exist in repository instructions, build files, scripts, or CI configuration.
- Technical decisions: Data structures, abstractions, and framework mechanisms fit the surrounding architecture without unnecessary indirection.
- Level of detail: The plan records non-obvious decisions and interactions without prescribing routine implementation.
- Omissions: Check whether the plan addresses risks relevant to the change, including error handling, compatibility, migration, performance, security boundaries, and observability.
- History: A follow-up plan explicitly identifies and explains any earlier decisions it supersedes.
Say explicitly when there are no findings. If the plan is already frozen (timestamp in its filename and a *Frozen at ...* line below its title), note that it can no longer be edited. Changes are decided in the Guiding Phase and recorded in a Follow-Up Plan.
Related skills
| Skill | Stars | Updated | Works with | Status | Install |
|---|---|---|---|---|---|
| reverse-engineer-anythingmorluto/reaReverse engineer native, managed, Electron/JavaScript, packaged, firmware, and browser targets with REA, and build agent environments (AgentEnv bundles) of web applications from a live instance or a capture, and of Linux desktop apps with a task from a request. Use shipped-artifact or requested runtime evidence to explain features, compare versions, decompile code, or guide a reconstruction. Skip REA for ordinary source-repository architecture analysis. | Stars: 467k | Updated | Claude CodeCodex | Verified | Install |
| diagnosing-superpowersobra/superpowersUse when a superpowers session went wrong and your human partner wants to know why — repeated work, ignored plans, stumbles, poor results, a skill that didn't fire, "it took too long", "why is it so expensive", "what is it doing" — or wants to build a bug report for the superpowers maintainers, for the current session or a past one identified by id or path, on any harness. | Stars: 319k | Updated | Claude CodeCodex | Verified | Install |
| dispatching-parallel-agentsobra/superpowersUse when facing 2+ independent tasks that can be worked on without shared state or sequential dependencies | Stars: 319k | Updated | Claude CodeCodex | Verified | Install |
| executing-plansobra/superpowersUse when executing an implementation plan in the current session as the implementer yourself — your human partner chose inline execution, or no subagent tool is available | Stars: 319k | Updated | Claude CodeCodex | Verified | Install |