A command is the one you type. It runs exactly when you ask it to, and never before.
4,574 commands across 357 plugins.
Healthcheck + drift detect + rotation-reminder across all MCP servers in ~/.claude/mcp-registry.json
Catch mock/live divergence in MCP eval golden tests (anti-pattern #2 from eval-mock-mode-discipline)
Catch the github-mcp class of bug — CallTools handlers that exist but are invisible to Claude because ListTools never advertises them (orphaned), or ListTools…
Manage the project's instinct library — view, promote, evolve, export, or import atomic learned behaviors captured automatically by PostToolUse observations.
Socratic interview flow — explores requirements, identifies edge cases, clarifies scope, and outputs a structured feature brief before any coding begins.
Review accumulated session learnings, extract recurring patterns, and draft new skills from session data.
**Command:** `/devteam:issue-new "<description>"`
Manage backlog items — ideas not ready for active planning. Add, review, promote, or remove.
Start a new project. Deep questioning, research, requirements, and roadmap.
Execute all plans in a phase. Spawns agents to build in parallel, commits atomically.
GitHub PR review lifecycle - analyze, discuss, post inline comments, follow-up, respond, approve
Initialize LETS in current project - creates .lets/ structure, config, statusline, beads; offers user-scope global-rules install when the plugin is user-scoped
First-time global setup - install plugins, configure environment, explain workflow
Evaluate whether a research idea is worth pursuing before investing months of effort. Stress-tests ideas along 7 dimensions (novelty, impact, timing,…
Export the current paper draft to production-ready LaTeX (.tex) and PDF using the arxiv-style template. Converts draft.md + references.bib + figures/ into a…
Generate an academic diagram from a text description using PaperBanana. Provide a section of your paper or a methodology description and get a…
Health-check the scaffolding install and report install problems plus exact fixes (diagnose-only, never mutates).
Enter explore mode - think through ideas, investigate problems, clarify requirements
Create a change and generate all artifacts needed for implementation in one go
Advance Evaluator-side actions only. Auto-selects review, QA, retest, or final report from status.md. /auto-harness:qa [sprint]
Advance parallel Evaluator-side actions only. Auto-selects review, QA, retest, or final report from status.md. /auto-harness:qa-parallel [sprint]
How to brief Claude for good UI: references, screenshots, constraints, and iterating instead of re-rolling
Cart UX, payment forms, guest checkout, trust signals, order confirmation
Paste any file or error — get a plain language explanation with no developer jargon
Set up AKA Security — calibrate notifications and detection posture from Claude's real activity.
把批量委派编排成 dynamic workflow——N 个 item 各派一个委派模型子进程并行处理。适合 50 个文件各转一次、N 个模块各审一次等同构批量。
Run Specwright eval suite. Spawns subagents to run skills in fixture workdirs, then grades results.
Project setup. Creates constitution and charter. Configures gates.
Audit a deployed contract on a live chain. Pulls verified source from the block explorer, optionally forks the chain for live-state simulation.
Diff the on-chain configuration of one contract deployed across multiple chains — owner, oracle, fees, timelock, pause state, proxy impl — and flag the chain…
Multi-pass consensus audit — runs the audit twice with different prompts, only reports consensus findings. Aggressively cuts false positives.
© 2026 Flowy · Free and open source
Built for Claude Code · Not affiliated with Anthropic