Handles code review feedback by verifying before implementing and pushing back if incorrect. Checks EC for context on prior decisions. Use when receiving code review comments or PR feedback.
Processes code review feedback by verifying suggestions against existing decisions before implementing or pushing back.
npx claudepluginhub merewhiplash/engram-cogitatorThis skill inherits all available tools. When active, it can use any tool Claude has access to.
Technical evaluation, not emotional performance.
Announce: "I'm using the receiving-review skill to process this feedback."
Read → Understand → Check EC → Verify → Evaluate → Implement
Complete feedback without reacting.
Restate the requirement in your own words. If unclear, ask.
Before accepting or rejecting, check for relevant context:
ec_search:
query: [topic of feedback]
type: decision
ec_search:
query: [component mentioned]
type: pattern
The current implementation might be there for a reason.
Check against codebase reality:
Is the suggestion sound? Consider:
One item at a time. Test each fix (@verifying).
Push back with technical reasoning if:
Example:
"Checked EC - we decided to use X because [rationale from decision memory]. Still want to change?"
If ANY item is unclear: Stop. Ask first.
Don't implement what you understand and ask about the rest. Items may be related.
When feedback is correct:
"Fixed. [Brief description]"
"Good catch - [issue]. Fixed in [location]."
[Just fix it, show in code]
When pushing back:
"Checked EC - this was decided in [area]: [rationale]. Keep current impl?"
"Grepped codebase - nothing calls this. Remove (YAGNI)?"
"This conflicts with [pattern from EC]. Want to change the pattern?"
Never:
"You're absolutely right!"
"Great point!"
"Thanks for catching that!"
Actions speak. Just fix it or explain why not.
"You were right - checked [X] and it does [Y]. Fixing now."
State the correction factually. Move on.
If feedback reveals something worth remembering:
ec_add:
type: learning
area: [component]
content: [What the feedback taught about this codebase]
rationale: Learned during code review
Worth storing:
Search, retrieve, and install Agent Skills from the prompts.chat registry using MCP tools. Use when the user asks to find skills, browse skill catalogs, install a skill for Claude, or extend Claude's capabilities with reusable AI agent components.
Activates when the user asks about AI prompts, needs prompt templates, wants to search for prompts, or mentions prompts.chat. Use for discovering, retrieving, and improving prompts.
This skill should be used when the user asks to "create an agent", "add an agent", "write a subagent", "agent frontmatter", "when to use description", "agent examples", "agent tools", "agent colors", "autonomous agent", or needs guidance on agent structure, system prompts, triggering conditions, or agent development best practices for Claude Code plugins.