flowbit

Initialize Flowbit with intelligent project analysis and documentation generation

Creates Mermaid diagrams for planning flows, component communication, and architecture views with adaptive detail selection (including C4 levels). This skill should be used when the user asks for a workflow, interaction, or architecture visualization from provided task context.

Internal engine for managing project documentation and technical standards in .flowbit/docs/. Handles file operations, INDEX.md generation, and .github/copilot-instructions.md integration. Invoked by flowbit-init, standards-update, and standards-discover skills.

Quick bug fix with TDD red/green gates and complexity escalation

Implement task directly with AI SDLC standards awareness (no planning mode)

Enter planning mode with AI SDLC standards awareness

Discover coding standards from project configuration files, code patterns, documentation, and external sources (PRs, CI/CD)

Update or create project standards from conversation context or explicit description

Unified orchestrator for all development tasks. ALWAYS execute when invoked — never skip for 'straightforward' tasks. Phases adapt based on detected task characteristics rather than predetermined types. Use for any development work that modifies code.

Orchestrates the complete migration workflow from current state analysis through implementation to compatibility verification. Handles technology migrations, platform changes, and architecture pattern transitions with adaptive risk assessment, incremental execution, and rollback planning. Use when migrating technologies, platforms, or architecture patterns.

Shared orchestration patterns for all workflow orchestrators. NOT an executable skill - provides reference documentation for phase execution, state management, interactive mode, and initialization. All orchestrators reference these patterns.

Orchestrates performance optimization workflows using static code analysis to identify bottlenecks (N+1 queries, missing indexes, O(n^2) algorithms, blocking I/O, memory leaks). Accepts optional user-provided profiling data. Reuses standard specification, planning, implementation, and verification phases.

Interactive product/feature design orchestrator. Transforms fuzzy ideas into structured product briefs through collaborative exploration, iterative refinement, and visual prototyping. Adaptive phases detect design complexity and adjust depth.

Orchestrates comprehensive research workflows from question definition through findings documentation. Handles technical, requirements, literature, and mixed research types with adaptive methodology, multi-source gathering, pattern synthesis, and evidence-based reporting. Supports standalone research tasks and embedded research phase in other workflows.

Render a markdown plan, idea, RFC, or design note into a self-contained, share-ready HTML file using the warm editorial visual system bundled under `references/`. Use this skill whenever the user asks to "render", "convert", "turn into HTML", "make a nice HTML version", "share this as a page", or "make this look good" for a markdown file containing a plan, proposal, idea, brief, RFC, design note, or pitch — even if they don't explicitly say "HTML". The output is a single .html file with all CSS inlined, written next to the source .md, that visually matches the reference layout in `references/index.html` and uses tokens from `references/tokens.json`.

Executes implementation plans by delegating each task group to task-group-implementer. Coordinates context preparation, progress tracking, and work-log updates with lazy standards loading from INDEX.md.

Orchestrates post-implementation quality verification by delegating to specialized subagents. Read-only — reports issues without fixing. Use after implementation is complete.

Incident response orchestrator for production outages and degradation. Handles triage, evidence, mitigation, code-fix gating, verification, and postmortem.

Critically reviews any project artifact (diagram, plan, architecture, workflow, idea, skill definition, review report) to challenge assumptions, expose risks, and recommend safer alternatives with clear acceptance conditions. Use when manually requesting a second opinion before approval or execution.

Analyzes codebase using adaptive parallel Explore subagents based on task complexity. Selects agent roles from a pool, launches Explore agents, then delegates report generation to codebase-analysis-reporter subagent.

Collect incident evidence and build a timeline for root-cause analysis and mitigation decisions.

Normalize incident reports into a structured brief with severity, impact, and immediate context.

Produce blameless postmortem and actionable follow-up backlog from incident artifacts.

Run automated code quality, security, and performance analysis on your code

Run pragmatic code review to detect over-engineering and ensure code matches project scale

Verify production deployment readiness with comprehensive checks

Comprehensive reality assessment of completed work to verify it actually works and is production-ready

Independent specification audit to verify completeness and clarity before implementation

Unified entry point — auto-classifies tasks and routes to appropriate workflow. ALWAYS execute when invoked via slash command.