A command is the one you type. It runs exactly when you ask it to, and never before.
1,875 commands across 626 plugins.
Bridge Claude Code's /goal to the active plan. Derives a goal condition from task_plan.md and invokes /goal so Claude keeps working until the plan is complete.…
Run a planning-aware cadence with Claude Code's /loop. Default tick checks plan status, runs check-complete, nudges progress.md update if stalled. Available…
启动 Manus 风格的文件规划。为复杂任务创建 task_plan.md、findings.md、progress.md。
Build competitive analysis matrices with scoring and gap analysis. Usage: /competitive-matrix <analyze> [options]
Stage, commit, and push the current branch following git governance rules.
/cs:aeo — Answer Engine Optimization workflow. Audit content for E-E-A-T + structure signals that drive LLM citation (ChatGPT, Perplexity, Claude, Gemini,…
Send a message to a running agent session. Use this to correct or direct a live agent mid-stream without killing and respawning it.
Manage agent sessions: list, inspect, rename, kill, restore, clean up, and claim PRs.
Set up Repowise for this codebase. Installs if needed, asks about your preferences, and runs the indexing.
Rebuild the Repowise vector store by re-embedding all wiki pages. No LLM calls — only embedding API calls.
Score the defect risk of a change — a commit or a base..head range — as a single 0–10 with drivers.
Create an Android ViewModel with proper state management and data flow.
Write an Architecture Decision Record documenting a significant technical decision.
Detect which packages in a monorepo are affected by recent changes.
**See what you've built, what's validated, what's installed, and what's next.**
**Install a generated hook to Claude Code settings (user-level or project-level).**
**Step-by-step guide to install your generated skills and agents to the correct locations.**
Update spec files methodically after execution (requirements -> design -> tasks)
Optional scenario lens such as extension, integration, analytics, or AI
Optional runtime context such as Cloud Foundry, Kyma, BAS, or local development
Optional symptom such as no logs, missing metrics, high cardinality, auth error, or delayed ingestion
Provides comprehensive GitHub pull request review with code quality, security, and best practices analysis. Use when reviewing a PR before merging.
Validates Java application architecture focusing on Clean Architecture, DDD, and Spring Boot patterns. Use when reviewing architectural decisions or before…
Validates Java code quality for enterprise Spring applications with security, performance, architecture and best practices analysis. Use when reviewing code…
Generate or load a session handoff. Usage: /handoff [create|resume]
© 2026 Flowy · Free and open source
Built for Claude Code · Not affiliated with Anthropic