existential-birds/beagle / plugins/beagle-core/skills/receive-feedback
receive-feedback
VerifiedProcess external code review feedback with technical rigor. Use when receiving feedback from another LLM, human reviewer, or CI tool. Verifies claims before implementing, tracks disposition.
| File | Kind | Size |
|---|---|---|
| EVALUATION.md | markdown | 3.2 KB |
| RESPONSE.md | markdown | 3.1 KB |
| SKILL.md | skill md | 10.9 KB |
| VERIFICATION.md | markdown | 2.5 KB |
| references/skill-integration.md | markdown | 1.7 KB |
VERIFICATION.md
View on GitHub# Verification Workflow
## Principle
Do not trust feedback. Verify it against the current codebase state.
## Verification by Feedback Type
| Feedback Type | Verification Method |
|---------------|---------------------|
| "Unused code" | `Grep` for usage across codebase |
| "Bug/Error" | Reproduce with test or script |
| "Missing import" | Check file, run linter |
| "Style/Convention" | Check existing patterns in codebase |
| "Performance issue" | Profile or benchmark if possible |
| "Security concern" | Trace data flow, check sanitization |
## Verification Steps
For EACH feedback item:
1. **Locate**: Find the referenced code (`Read` tool)
2. **Context**: Understand why it exists (`Grep` for usage, git blame)
3. **Validate**: Test the claim (run tests, reproduce issue)
4. **Classify**: VALID (claim holds) or INVALID (claim disproved by an artifact). If genuinely unparseable, NEEDS CLARIFICATION — but never use this to dodge a fixable item.
5. **Document**: Record the artifact (path:line, command output, grep hit) before proceeding.
A claim is INVALID only when verification produced a concrete artifact disproving it. "I don't think this matters" is not verification — it is deferral, which is forbidden.
## Using Code-Review Skills for Verification
When feedback relates to a specific domain, load the relevant skill:
| Domain | Skill to Reference |
|--------|-------------------|
| Python quality | python-code-review |
| FastAPI routes | fastapi-code-review |
| SQLAlchemy ORM | sqlalchemy-code-review |
| React components | shadcn-code-review |
| Routing | react-router-code-review |
| Database queries | postgres-code-review |
| Tests | pytest-code-review, vitest-testing |
These skills contain the authoritative patterns for this codebase.
If feedback conflicts with skill guidance, flag for discussion.
## Example
Feedback: "Remove unused `validate_user` function"
Verification:
1. `Grep` for "validate_user" across codebase
2. Found: Called in `auth/middleware.py:45`
3. Classification: **INVALID** — function is used
4. Action: Reject with evidence in the pre-dispatch summary
Contrast — feedback: "Null check missing on `session` at `auth.py:42`"
Verification:
1. Read `auth.py` around line 42
2. Confirmed: `session.user_id` is dereferenced with no prior `if session is None` guard
3. Classification: **VALID**
4. Action: Add to the `launch fixes for ...` prompt; on confirm, fix the guard — via a dedicated subagent if subagents are supported (do not edit `auth.py` from the orchestrator in that branch), otherwise apply the fix sequentially yourself.
Related skills
| Skill | Stars | Updated | Works with | Status | Install |
|---|---|---|---|---|---|
| receiving-code-reviewobra/superpowersUse when receiving code review feedback, before implementing suggestions, especially if feedback seems unclear or technically questionable - requires technical rigor and verification, not performative agreement or blind implementation | Stars: 322k | Updated | Claude CodeCodex | Verified | Install |
| requesting-code-reviewobra/superpowersUse when completing tasks, implementing major features, or before merging to verify work meets requirements | Stars: 322k | Updated | Claude CodeCodex | Verified | Install |
| using-git-worktreesobra/superpowersUse when starting feature work that needs isolation from current workspace or before executing implementation plans - ensures an isolated workspace exists via native tools or git worktree fallback | Stars: 322k | Updated | Claude CodeCodex | Verified | Install |
| verification-before-completionobra/superpowersUse when about to claim work is complete, fixed, or passing, before committing or creating PRs - requires running verification commands and confirming output before making any success claims; evidence before assertions always | Stars: 322k | Updated | Claude CodeCodex | Verified | Install |