check
01Command Claude Code
Quick health check (git, lint, unit tests).
Command Claude Code
Quick health check (git, lint, unit tests).
Command Claude Code
Create a commit with validation (lint + tests) — optionally pass the message.
Command Claude Code
Finalize changes — quick review + check + commit.
Command Claude Code
Adversarial dual review — two independent reviewers with no shared context; both must approve before merge.
Command Claude Code
Promote accumulated learnings into a real skill, reference, or command — periodic self-improvement of this config.
Command Claude Code
List the available commands.
Command Claude Code
Start a session with project context.
Command Claude Code
Capture a reusable learning from this session — with a dedup + Save/Absorb/Drop gate so the knowledge base stays clean.
Command Claude Code
Pick the next roadmap task and prepare the environment.
Command Claude Code
Create a Pull Request with an automatic description.
Command Claude Code
Send commits to the remote.
Command Claude Code
Review the current diff against the project rules.
Command Claude Code
Consolidated status of the roadmaps and next steps.
Command Claude Code
Static and dependency audit. Use the Grep tool (not bash grep).
Command Claude Code
Check whether docs and configs reflect the real state of the code.
Command Claude Code
Mark a task as done in the roadmap.
Command Claude Code
Run tests related to the modified files.
Command Claude Code
Update this project's .claude/ to the latest "agnostic" config from the claude-skills-czl repo, preserving local learnings.
Command Claude Code
Update this project's .claude/ to the latest "langflow" config from the claude-skills-czl repo, preserving local learnings.
Command Claude Code
Definition-of-done gate — build, types, lint, tests, a secrets/debug scan, and a diff self-review before calling work done or opening a PR.
Skill Claude CodeCodex
Design and review HTTP/REST (and choose between REST/GraphQL/gRPC) APIs that are contract-first, resource-oriented, backward-compatible, and secure by default. Use whenever the task touches an API surface — designing an API, adding or changing an endpoint or route, picking an HTTP method or status code, naming…
Skill Claude CodeCodex
Build, refactor, and review frontend UI in any framework — components, accessibility, forms, client state and data fetching, responsive layout, performance, client-side security/PII, and UX/visual design (design plan, tokens, typography, color, spacing, motion). Use whenever the task touches the UI layer: creating or…
Skill Claude CodeCodex
Recover when the AGENT itself is stuck — looping, repeating the same failed action, burning tokens/budget, overflowing context, drifting from the goal, or acting on stale state. Use when a run isn't converging and reworded retries aren't helping. This is a workflow you follow, not a hidden runtime that auto-heals. For…
Skill Claude CodeCodex
Build a new feature using strict test-driven development — UNDERSTAND → DESIGN → RED → VERIFY RED → GREEN → VERIFY GREEN → REFACTOR → VALIDATE → REPEAT. Use when building a new feature with TDD, when the user says "TDD this", "tests first", "red green refactor", or asks for feature work that needs to be verifiable…
At most 3 mods per repository are shown here, and a mod shipped inside a plugin is left to that plugin's page — the rest are on their repository pages: