From flowstate
Use when requesting code review after implementing features, before merging, when stuck, or after fixing complex bugs. Structures what to provide reviewers and what output to expect.
npx claudepluginhub c-reichert/flowstate --plugin flowstateThis skill uses the workspace's default tool permissions.
**Core principle:** Give reviewers everything they need to evaluate your changes without follow-up questions.
Searches, retrieves, and installs Agent Skills from prompts.chat registry using MCP tools like search_skills and get_skill. Activates for finding skills, browsing catalogs, or extending Claude.
Searches prompts.chat for AI prompt templates by keyword or category, retrieves by ID with variable handling, and improves prompts via AI. Use for discovering or enhancing prompts.
Guides TDD-style skill creation: pressure scenarios as tests, baseline agent failures, write docs to enforce compliance, verify with RED-GREEN-REFACTOR.
Core principle: Give reviewers everything they need to evaluate your changes without follow-up questions.
Mandatory: after completing a feature, before merging to main, after fixing complex bugs.
Optional but valuable: when stuck, before refactoring, after architectural changes.
Every review request includes:
BASE_SHA=$(git merge-base origin/main HEAD)
HEAD_SHA=$(git rev-parse HEAD)
git diff --stat $BASE_SHA..$HEAD_SHA
Reviewers should return findings in this structure:
What is well done, with specific file:line references.
Critical (Must Fix): Bugs, security vulnerabilities, data loss risks, broken functionality.
Important (Should Fix): Architecture problems, missing error handling, test gaps, performance issues.
Minor (Nice to Have): Code style, minor optimizations, documentation improvements.
Each issue includes:
file:line referenceReady to merge? Yes / No / With fixes
Reasoning: One to two sentences of technical justification.
See the receiving-code-review skill for the full feedback-handling protocol.
| Workflow | When to Review |
|---|---|
| Subagent-driven development | After each task |
| Executing plans | After each batch of 3 tasks |
| Ad-hoc development | Before merge, or when stuck |