do
CommandSmart router: classify requests and route to the correct agent + skill
11,199 slash commands. The ones you type, shipped in plugins found in public marketplaces and GitHub repositories. A command runs exactly when you ask, never before.
Smart router: classify requests and route to the correct agent + skill
Builds an advocacy activation plan (references, stories, community, advisory boards) with logistics and incentives.
Turns VoC themes into advocacy campaigns, advisory boards, and reference plays.
Converts advocacy candidates into live programs with approvals, incentives, and scheduling.
Guide for developing monday.com platform API tools in the agent-toolkit package. Use when creating, modifying, or debugging tools…
Create smart commit with quality checks and conventional format
Search MemStack memory for past sessions, insights, and project context.
Analyze vendor security questionnaire responses
Deep dive analysis of ISO 27001 Annex A control domains with implementation guidance
You are helping the user work with Station - the self-hosted AI agent orchestration platform.
Check if {{DEV_MACHINE}} Docker environment needs updating
Export sprite to PNG, GIF, or spritesheet with optional scaling
Create a new pixel art sprite with optional size and palette presets
Execute Phase 7 - Actions on Objectives and Goal Achievement
Execute Phase 6 - Command and Control Infrastructure Setup
Crash → root cause → reachability → empirical exploitability verdict (native bugs)
Deep performance analysis with extended thinking and parallel optimization
Comprehensive code review with actionable feedback using extended thinking
Complete architecture design and documentation workflow using simple-architect and simple-architecture-documenter agents in…
Perform a non-destructive cross-artifact consistency and quality analysis across spec.md, plan.md, and tasks.md after task…
Start a project's dev servers (backend, frontend, or any services listed in its map) in the background, with port checks first
Interview Boss about the project, then reason from first principles to design the ideal ATLAS operating identity/system-prompt…
Gate a deploy — tests, missing secrets for the target env, migration review, local build, and a complete DEPLOY.md — and report…
Meta-skill that loads all llmwiki governance docs and exposes the three maintainer slash commands.
Run the canonical llmwiki code review against a pull request and post findings.
Read-only Databricks health check: CLI, profiles, auth validity via one API call. Add `full` after the command to also check…
Set up Databricks CLI auth: install check, then an OAuth / PAT / service-principal profile (workspace or account-level), then…
Read-only Databricks health check: CLI, profiles, auth validity via one API call. Add `full` after the command to also check…
Run cs doctor to diagnose why the status bar isn't showing what you expect
Render the three status-bar looks using your real cached data
Validate CODE_TASK technical feasibility with critical analysis using mcp__abcoder.
Design implementation plan using mcp__abcoder analysis and code exploration.
You MUST use this before any creative work - creating features, building components, adding functionality, or modifying behavior.…
Address code review feedback — corroborate, validate, and implement changes from a review's final.md.
对指定股票执行完整的投资尽调研究,从问题细化到最终报告生成。执行8阶段投资研究流程:公司事实底座、行业周期分析、业务拆解、财务质量、股权治理、市场分歧、估值护城河、综合报告。
AgentRecall on-demand recall — surface past fixes, decisions, and patterns mid-session without leaving your flow.
AgentRecall consolidation & reflection — periodic triage of recurring corrections; proposes rule changes, never applies them…
AgentRecall full save — journal + palace + awareness + insights in one shot.
Workflow for the rest of tasks: lightweight documentation, build, track, synchronize, etc.
Workflow for backend API test automation: TMS / Issue Tracker test cases → automated API tests, HITL-gated.
Provides guided feature development capability with codebase understanding and architecture focus. Use when implementing a new…
Provides guided bug fixing and debugging capability with systematic root cause analysis. Use when encountering bugs, errors, or…
Generates and manages project changelog following Keep a Changelog standard with Git integration and Conventional Commits…
View Claude Nights Watch execution logs with filtering and follow options
Restart the Claude Nights Watch daemon to apply configuration changes
Interactive setup wizard for Claude Nights Watch configuration
Summarize completed work, current risks, and next actions.
Find and fix bugs that break OpenLore's first-run experience by dogfooding the real install flow on a clean repo (the method that…
Architecture review for a PRD. Analyzes codebase through separation-of-concerns and tactical-ddd lenses, surfaces architectural…
Facilitated discussion of all 3 design phases, producing an Architecture Decision Record
Check whether the Agent Office server is up and show how to start it
Generate A/B test design variants from an existing Figma screen — alternate layouts, CTA placements, color treatments, and copy…
Full WCAG AA accessibility audit on an HTML file — contrast ratios, keyboard navigation, semantic HTML, ARIA usage, touch…
Generate a complete brand kit from a logo and 1-2 brand colors — full palette, type scale, icon style, component tokens, and…
Assess your Claude Code level (0-10) and get a personalized roadmap to the next one
**Navigation**: [← Main Workflow](../workflow-steps.md) | [Step 2: Triage →](2-triage.md)
**Navigation**: [← Step 1: Analyze](1-analyze.md) | [Main Workflow](../workflow-steps.md) | [Step 3: Plan →](3-plan.md)
**Navigation**: [← Step 2: Triage](2-triage.md) | [Main Workflow](../workflow-steps.md) | [Step 4: Fix →](4-fix.md)
Start, resume, inspect, report, or pause a measured experiment loop
Start Manus-style file-based planning. Creates task_plan.md, findings.md, progress.md for complex tasks.
Lock the current task_plan.md content with a SHA-256 attestation. Prompt hooks warn when the file diverges without injecting its…
Bridge Claude Code's /goal to the active plan. Derives a goal condition from task_plan.md and invokes /goal so Claude keeps…
Slash-command wrapper for the decision-map skill. `/decision-map chart` plus a loose idea opens a decision map for an effort too…
Review open GitHub issues for priority, feasibility, project alignment, and risks.
Review open pull requests for code quality, project alignment, and risks.
Analyze all open issues across GitHub Issues and Seeds, cross-reference with codebase health, and recommend the top ~5 issues to…
© 2026 Flowy
Built for Claude Code · Not affiliated with Anthropic
Logos are trademarks of their owners.