research-topic
Research a topic using multi-agent-researcher skill
A command is the one you type. It runs exactly when you ask it to, and never before.
1,184 commands across 626 plugins.
Research a topic using multi-agent-researcher skill
Pre-refinement readiness check. Evaluates a work item against quality criteria and produces a readiness report with actionable flags. Standalone and…
Technical enrichment pass. Analyzes the relevant repos to identify affected components, migration concerns, testing strategy, and risks, and produces per-repo…
Single-pass story improvement — assess readiness internally, fill gaps conversationally, and produce a refined story, all in one adaptive flow. This is the…
Launch the AKA web dashboard in your browser (reads your local store)
List installed AKA detection packs, versions, and available updates
委派模型回答/分析/审/咨询。**只读不改文件**(Read/Grep/Glob + Bash(git:*))。主 Claude 会智能补 --with-context、选模型。
多模型并行对同一问题各给独立意见(发散式 brainstorming),主 Claude 综合分歧、共识、独到见解。各模型彼此看不到对方答案,避免回声室效应。
委派模型**改文件/落盘/执行**。隐含 --write(子进程获得 Edit/Write/Bash 全权)。主 Claude 会智能补 --with-context、选模型。
Self-check the Gearbox installation and print a PASS/WARN/FAIL report
Creates a project-local copy of the Gearbox routing policy. Optional — only needed if you want to customize the policy for this repo.
Hand a task to Antigravity (Gemini 3.5) and get the result back inside Claude Code.
Show the final output (and conversation id) of a finished Antigravity job.
Generate or edit an image via a Gemini (agy) session — Gemini's generate_image tool does what Claude cannot
Swarm a task across parallel Gemini (agy) sessions with automatic decomposition and model routing
Generate multiple distinct ideas/designs with parallel specialist lenses
Generate multiple distinct ideas/designs with task orchestration and @references
Implement tasks from an OpenSpec change (Experimental)
Archive a completed change in the experimental workflow
Enter explore mode - think through ideas, investigate problems, clarify requirements
Marks the cheapest Claude model and effort that still clears this task with high confidence. Still shows the full Budget, Optimal, and Splurge spread.
Marks the strongest Claude model and effort that genuinely helps this task, for high stakes or hard work. Still shows the full Budget, Optimal, and Splurge…
Effort recommendation only for this task. Shows a narrow ladder of just the effort level, from a lower setting to a higher one, for a model named in the task…
Show model-routing stats - dispatches and real token volume kept off the session model. Args - --days N (window size, default 7), --ago M (shift window M days…
Deploy remote-workstreams on this Mac — tmux + Tailscale, Deepgram/Cartesia keys into the Keychain, pairing PIN, launchd service, tailscale serve, pairing QR,…
Start an autonomous loop-engineer session to orchestrate a self-assembling multi-agent team for any goal
Extract archives from source to destination.
Generate comprehensive API documentation from source code
Handle production incidents with structured response
You are an API mocking expert specializing in creating realistic mock services for development, testing, and demonstration purposes. Design comprehensive…
Open a review-action approval window by creating the ./.review-approved flag file. Takes an optional reason string that is embedded in the receipt chain.
Walk the receipt chain in ./receipts/ verifying every signature and hash link. Detects insertions, deletions, and tampering across the entire audit trail.
Pre-deploy gate that scans built JS chunks for forbidden substring markers (saga-era / obsolete code paths) listed in a project-local forbidden-markers.txt
Clean up .a5c/runs and .a5c/processes directories. Aggregates insights from completed/failed runs into docs/run-history-insights.md, then removes old run data…
© 2026 Flowy · Free and open source
Built for Claude Code · Not affiliated with Anthropic