Agent-Skills.md

Agent Skills: Code Review Reception

>-

UncategorizedID: jagreehal/jagreehal-claude-skills/code-review-reception

Repository

jagreehal/jagreehal-claude-skills
jagreehalLicense: MIT
31

Install this agent skill to your local

pnpm dlx add-skill https://github.com/jagreehal/jagreehal-claude-skills/tree/HEAD/skills/code-review-reception

Skill Files

Browse the full folder contents for code-review-reception.

Download Skill

Loading file tree…

skills/code-review-reception/SKILL.md

Skill Metadata

Name
code-review-reception
Description
>-

Code Review Reception

Critical rules

  • Verify before implementing. A suggestion is a hypothesis, not a command.
  • Technical correctness before social comfort. No performative agreement.
  • If any item is unclear: STOP; ask before implementing anything.
  • Implement one item at a time; test each; confirm no regressions.
  • Acknowledge correct feedback through action, not praise.
  • Before drafting replies or pushback, read references/examples.md.

Workflow

  1. READ all feedback without reacting.
  2. UNDERSTAND: restate each requirement (or ask).
  3. VERIFY each suggestion against the codebase.
  4. EVALUATE: technically sound for THIS codebase?
  5. RESPOND: technical acknowledgment or reasoned pushback with evidence.
  6. IMPLEMENT in order: blocking → simple → complex; test each fix.

Resources

  • references/examples.md — unclear feedback, pushback, YAGNI, acknowledgment, rationalizations. Read when responding or unsure.

Validation

Before responding:

  • [ ] All feedback read; requirements restated or clarified
  • [ ] Each suggestion checked against the codebase

Before claiming done:

  • [ ] One item at a time; each tested; no regressions
  • [ ] Correct items acknowledged factually; wrong ones pushed back with evidence

Constraints

  • Not for authoring reviews of others' code.
  • Related: verification-before-completion, tdd-workflow, debugging-methodology, critical-peer.