Skip to content
Open
Changes from all commits
Commits
File filter

Filter by extension

Filter by extension

Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
21 changes: 20 additions & 1 deletion skills/receiving-code-review/SKILL.md
Original file line number Diff line number Diff line change
@@ -1,6 +1,6 @@
---
name: receiving-code-review
description: Use 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
description: Use when receiving review feedback from humans, GitHub comments, or subagent/spec-review passes before implementing suggestions; verify first, acknowledge concretely, and avoid performative agreement or blind implementation
---

# Code Review Reception
Expand Down Expand Up @@ -85,6 +85,25 @@ IF conflicts with your human partner's prior decisions:

**your human partner's rule:** "External feedback - be skeptical, but check carefully"

### From Subagent Reviews (especially subagent-driven-development)
Treat subagent feedback as first-class technical input, not casual chatter.

```
FOR each subagent finding:
1. Quote the exact finding in your own words
2. Classify it: spec mismatch / code-quality / test gap / false positive
3. Verify against plan + code before changing anything
4. Respond with concrete disposition:
- FIXED: what changed + where
- DISAGREE: technical reason + evidence
- NEEDS CLARIFICATION: exact question

NEVER dismiss findings with vague language like:
"not a big problem" / "looks fine" / "excellent discovery" (without action)
```
Comment on lines +91 to +103
Copy link

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

⚠️ Potential issue | 🟡 Minor

Add a language to this fenced block.

Line 91 currently violates MD040, so this section will keep failing markdownlint until the fence is annotated.

Suggested fix
-```
+```text
 FOR each subagent finding:
   1. Quote the exact finding in your own words
   2. Classify it: spec mismatch / code-quality / test gap / false positive
   3. Verify against plan + code before changing anything
   4. Respond with concrete disposition:
      - FIXED: what changed + where
      - DISAGREE: technical reason + evidence
      - NEEDS CLARIFICATION: exact question

 NEVER dismiss findings with vague language like:
   "not a big problem" / "looks fine" / "excellent discovery" (without action)
</details>

<details>
<summary>🧰 Tools</summary>

<details>
<summary>🪛 markdownlint-cli2 (0.21.0)</summary>

[warning] 91-91: Fenced code blocks should have a language specified

(MD040, fenced-code-language)

</details>

</details>

<details>
<summary>🤖 Prompt for AI Agents</summary>

Verify each finding against the current code and only fix it if needed.

In @skills/receiving-code-review/SKILL.md around lines 91 - 103, The fenced code
block that begins with "FOR each subagent finding:" needs a language annotation
to satisfy MD040; update the fence by adding a language token (e.g., change totext) so the block is explicitly marked as a text code block, leaving the
block contents unchanged; locate the fenced block containing the exact "FOR each
subagent finding:" lines and modify only the opening backticks to include the
language.


</details>

<!-- fingerprinting:phantom:triton:grasshopper -->

<!-- This is an auto-generated comment by CodeRabbit -->


When feedback came from a specialized review pass, keep the response in the same frame (spec-compliance or code-quality) and explicitly tie your action to that frame.

## YAGNI Check for "Professional" Features

```
Expand Down