Beagle receive-feedback
Process 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.
install
source · Clone the upstream repo
git clone https://github.com/existential-birds/beagle
Claude Code · Install into ~/.claude/skills/
T=$(mktemp -d) && git clone --depth=1 https://github.com/existential-birds/beagle "$T" && mkdir -p ~/.claude/skills && cp -r "$T/plugins/beagle-core/skills/receive-feedback" ~/.claude/skills/existential-birds-beagle-receive-feedback && rm -rf "$T"
manifest:
plugins/beagle-core/skills/receive-feedback/SKILL.mdsource content
Receive Feedback
Overview
Process code review feedback with verification-first discipline. No performative agreement. Technical correctness over social comfort.
Quick Reference
┌─────────────┐ ┌──────────────┐ ┌─────────────┐ │ VERIFY │ ──▶ │ EVALUATE │ ──▶ │ EXECUTE │ │ (tool-based)│ │ (decision │ │ (implement/ │ │ │ │ matrix) │ │ reject/ │ └─────────────┘ └──────────────┘ │ defer) │ └─────────────┘
Core Principle
Verify before implementing. Ask before assuming.
When To Use
- Receiving code review from another LLM session
- Processing PR review comments
- Evaluating CI/linter feedback
- Handling suggestions from pair programming
Workflow
For each feedback item:
- Verify - Use tools to check if feedback is technically valid
- Evaluate - Apply decision matrix to determine action
- Execute - Implement, reject with evidence, or defer
Command Workflow
Use this skill from the
/receive-feedback command or by invoking it directly with a feedback file path.
- Read the feedback file at
$ARGUMENTS - Parse individual feedback items, whether numbered, bulleted, or freeform
- Load this skill:
Skill(skill: "beagle-core:receive-feedback") - Process each item through verify → evaluate → execute
- Produce the structured response summary defined in
RESPONSE.md
Expected Feedback File Format
The feedback file may contain numbered or bulleted items:
1. Remove unused import on line 15 2. Add error handling to the API call 3. Consider using a generator for large datasets 4. Fix typo in variable name: `usr` → `user`
Freeform prose is also acceptable; extract actionable items from the text.
Example
/receive-feedback reviews/pr-123-feedback.md
Reads the file, processes each item with technical verification, and outputs a structured response table.
Files
- Tool-based verification workflowVERIFICATION.md
- Decision matrix and rulesEVALUATION.md
- Structured output formatRESPONSE.md
- Using with code-review skillsreferences/skill-integration.md