Prepares and requests code review with proper context. Searches EC for reviewer preferences and past feedback patterns. Use before finishing a branch or when ready for feedback on implementation.
Prepares and requests code reviews by gathering context, checking readiness, and dispatching to reviewers.
npx claudepluginhub merewhiplash/engram-cogitatorThis skill inherits all available tools. When active, it can use any tool Claude has access to.
Prepare changes for review with clear context.
Announce: "I'm using the requesting-review skill to prepare this for review."
Verify Ready → Load Context → Prepare → Dispatch Reviewer → Handle Response
Load project config:
ec_search:
query: project config
type: config
Before requesting review:
{test_command}
{lint_command}
{build_command}
If failures: Stop. Fix first using @debugging.
Search EC for relevant review history:
ec_search:
query: code review feedback
type: learning
ec_search:
query: review pattern
type: pattern
Note any prior feedback patterns to proactively address.
Gather what the reviewer needs:
git log --oneline main..HEAD
git diff --stat main..HEAD
Identify:
Use the code-reviewer agent:
Task: Code review for [feature name]
Agent: code-reviewer
## Context
[Brief description of what was implemented]
## Changes
[Output from git diff --stat]
## Key Decisions
- [Decision 1 and rationale]
- [Decision 2 and rationale]
## EC Context Consulted
- [Relevant decisions/patterns from EC]
## Areas Needing Attention
- [Specific file or pattern to scrutinize]
## Plan Reference
docs/plans/YYYY-MM-DD-<topic>.md
When reviewer returns:
If issues found:
@receiving-review to process feedbackIf approved:
"Code review passed. Ready to finish the branch?"
If yes → Use @finishing-branch
If review reveals a pattern worth remembering:
ec_add:
type: learning
area: code-review
content: [What reviewers commonly catch or request]
rationale: Recurring review feedback
Examples worth storing:
| Do | Don't |
|---|---|
| Provide context on decisions | Dump code without explanation |
| Highlight risk areas | Assume reviewer knows everything |
| Reference the plan | Skip verification before requesting |
| Keep scope focused | Request review of WIP code |
| Note EC context consulted | Ignore prior decisions |
@executing-plans (Step 5)code-reviewer agent, @receiving-review, @finishing-branchActivates 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.
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.
This skill should be used when the user wants to "create a skill", "add a skill to plugin", "write a new skill", "improve skill description", "organize skill content", or needs guidance on skill structure, progressive disclosure, or skill development best practices for Claude Code plugins.