Desenvolvimento

Create a new workflow suite from a natural-language description, or edit an existing one when --flow=<path> is passed. Dispatches the create-workflow stagent (plan → write → validate loop) — does not write files directly.

Sandbox test a product in an isolated worktree. Runs 3 scenarios (happy path, edge case, adversarial), verifies activation protocol, reports results. Use when the creator says 'test', 'try it', 'does it work', or before publishing.

Create new skills, modify and improve existing skills, and measure skill performance. Use when users want to create a skill from scratch, edit, or optimize an existing skill, run evals to test a skill, benchmark skill performance with variance analysis, or optimize a skill's description for better triggering accuracy.

Drive the dev workflow state machine: read state.md, execute the current stage (inline or subagent), transition via update-status.sh, loop until terminal. Precondition: state.md already exists (some upstream caller bootstrapped it). Does NOT bootstrap.

Research a domain before building products. Tests Claude's baseline knowledge, identifies gaps, scans the marketplace, runs deep research, and recommends the optimal product setup. Use when: 'scout', 'research domain', 'what should I build for', 'analyze domain', or before /create for any non-trivial product.

RouterOS packet capture and TZSP streaming for protocol debugging. Use when: capturing packets on RouterOS, setting up /tool/sniffer, streaming live traffic via TZSP, using firewall mangle action=sniff-tzsp, debugging network protocols on MikroTik, receiving TZSP with Wireshark or tshark, saving pcap files from RouterOS, or when the user mentions packet sniffer, TZSP, sniff-tzsp, /tool/sniffer, or

Terraform infrastructure-as-code skills from HashiCorp. Covers HCL code generation with style conventions, testing with .tftest.hcl files, and module refactoring. Use when writing, reviewing, generating, or refactoring Terraform configurations, creating tests, or designing modules.

Delegue tarefas de codificação à IA Codex para implementação, análise e soluções alternativas. Use quando precisar de uma segunda perspectiva de IA, quiser explorar abordagens diferentes ou necessitar de capacidades especializadas do Codex para tarefas de codificação complexas.

Runs multi-pass automated code review with per-issue fix subagents. Triggers when preparing a branch for PR, reviewing code changes, or when thorough automated code quality review is needed.

Run OpenAI Codex CLI for coding tasks and second-opinion audits. Use when a user asks to run/ask/use Codex, says "codex prompt", or wants Claude to delegate a logic/code review to OpenAI models. Covers direct `codex` CLI invocation (exec, review, resume, apply, doctor, mcp), the six reasoning-effort levels (none/minimal/low/medium/high/xhigh), sandbox + dangerous flags, background execution, rate-

Programmatic React video best practices for Remotion. Use this skill whenever the user is writing, debugging, or rendering Remotion code — compositions, useCurrentFrame animations, interpolate, spring, Sequence timing, <Img>/<Video>/<Audio> from @remotion/media, staticFile, calculateMetadata, the Studio preview, `npx remotion render`, captions, subtitles, voiceover, audio visualization, ffmpeg, tr

Suggests manual context compaction at logical intervals to preserve context through task phases rather than arbitrary auto-compaction.