AGENT SKILL

receiving-code-review

Use when you receive review feedback on your own code or changes. Triggers on: 'reviewer said', 'PR feedback', 'review comments', 'address the feedback', 'fix the review'. Classifies feedback into must-fix / optional / reject-with-reason.

License 许可
Apache-2.0
最近更新
2026-11-11
Stars
★ 13
Forks
1

01 前言 Front Matter

name
receiving-code-review
description
Use when you receive review feedback on your own code or changes. Triggers on: 'reviewer said', 'PR feedback', 'review comments', 'address the feedback', 'fix the review'. Classifies feedback into must-fix / optional / reject-with-reason.

03 SKILL.md 正文

Receiving Code Review Skill

Review feedback is not a to-do list to blindly execute. Classify each item, act on what matters, and justify what you decline.

When to use this skill

  • You receive review comments on a PR or diff you wrote
  • Someone flags issues in code you produced
  • User asks you to "address the feedback" or "fix the review comments"

Step 1 — Read all feedback before acting

Do not start editing on the first comment. Read everything first. Build a complete picture of what the reviewer is asking.

Step 2 — Classify each comment

Category Definition Action
Must fix Correctness bug, security issue, data loss risk Fix immediately
Should fix Real concern, reasonable improvement Fix unless there's a strong reason not to
Optional Style, preference, minor nitpick Fix if fast (<5 min), otherwise note and move on
Reject Disagrees with an intentional design choice Respond with reasoning, do not change code

Step 3 — Act

For each must-fix and should-fix:

  1. Make the change
  2. Confirm the fix with evidence (diff or test output)
  3. Reply to the reviewer with what you changed

For each optional:

  • If fast: do it
  • If not: "Noted, deferring — [why]"

For each reject:

  • Write a clear explanation: "This is intentional because [X]. I'm keeping it as is."
  • Do not change the code under social pressure alone

Step 4 — Do not over-accept

Signs you are over-accepting:

  • Applying every comment without reading context
  • Changing code you are confident was correct
  • Letting the reviewer's style override your project's conventions

If a comment would break something or contradict a documented decision: push back.

Response format (for PR reply)

Thanks for the review. Here's what I did:

**Fixed:**
- [comment ref] [what I changed] — [file:line]

**Deferred:**
- [comment ref] [why — e.g. out of scope, separate ticket]

**Not changing:**
- [comment ref] [reason — e.g. this is intentional because X]

After applying changes

Run tests and use verify-before-done before marking the PR ready again.

04 同仓库更多 Skills

Horonomos-laps
Horonomos-laps/Yana-AI

openai--sentry--sentry

Use when the user asks to inspect Sentry issues or events, summarize recent production errors, or pull basic Sentry health data via the Sentry API; perform read-only queries with the bundled script and require `SENTRY_AUTH_TOKEN`.

★ 13
Horonomos-laps
Horonomos-laps/Yana-AI

ito-basket-compare

Compare Itô prediction-market baskets against a user's knowledge base, portfolio notes, financial context, watchlist, or research thesis. Use for read-only basket comparison and gap analysis without investment advice or live trading.

★ 13
Horonomos-laps
Horonomos-laps/Yana-AI

implementing-network-traffic-baselining

Build network traffic baselines from NetFlow/IPFIX data using Python pandas for statistical analysis, z-score anomaly detection, and hourly/daily traffic pattern profiling

★ 13
Horonomos-laps
Horonomos-laps/Yana-AI

detecting-evasion-techniques-in-endpoint-logs

Detects defense evasion techniques used by adversaries in endpoint logs including log tampering, timestomping, process injection, and security tool disabling. Use when investigating suspicious endpoint behavior, building detection rules for evasion tactics, or conducting threat hunting for stealthy adversary activity. Activates for requests involving evasion detection, defense evasion analysis, log tampering detection, or MITRE ATT&CK TA0005.

★ 13
Horonomos-laps
Horonomos-laps/Yana-AI

implementing-microsegmentation-with-guardicore

Implementing microsegmentation using Akamai Guardicore Segmentation to map application dependencies, create granular network policies, visualize east-west traffic flows, and enforce least-privilege communication between workloads across data centers and cloud.

★ 13
Horonomos-laps
Horonomos-laps/Yana-AI

ramdisk-tmpfs-patterns

暂无简介

★ 13