Explorar skills

Review product metrics, identify trends and anomalies, connect movements to OKRs and recent changes, and produce actionable recommendations.

Fetches AI news from smol.ai RSS. Use when user asks about AI news or daily tech updates.

Use when the user asks for a second opinion, independent review, sanity check, architecture red-team, red team critique, Codex-vs-Claude debate, GLM-vs-Claude comparison, DeepSeek-vs-Codex review, cross-model comparison, review my plan, challenge this design, evidence-checked code or PR review, or multi-agent critique of a high-stakes implementation plan, design decision, research claim, or bug ro

Use when facing 2+ independent tasks that can be worked on without shared state or sequential dependencies

Reference routed skill. Do NOT load directly unless user says so.

Implementa práticas de Engenharia de Harness da OpenAI em qualquer repositório, incluindo AGENTS.md, PLANS.md, comandos determinísticos de smoke/test/lint, limites arquitetônicos rigorosos, observabilidade desde o primeiro dia e auditorias de controle de entropia para execuções confiáveis de agentes autônomos.

Bootstrap a dev workflow session (for /stagent:start): parse flags, derive a topic from the task description, call setup-workflow.sh, and hand off to the workflow loop skill. Does NOT drive the state machine — that's stagent:stagent's job.

Stop-loss placement strategies for NSE/BSE equity trades. Covers structure-based, ATR-based, support/resistance-based, and moving average-based stops with buffer rules and hard limits. Use when the user asks: "where to set stop-loss", "stop-loss for [stock]", "how to protect this trade", "what's a good stop level", "risk management for [position]", or any question about initial stop-loss placement

Add a new sound effect to @remotion/sfx

Comprehensive document creation, editing, and analysis with support for tracked changes, comments, formatting preservation, and text extraction. When Claude needs to work with professional documents (.docx files) for: (1) Creating new documents, (2) Modifying or editing content, (3) Working with tracked changes, (4) Adding comments, or any other document tasks

Run Gemini CLI for AI queries. Use when user asks to "run/ask/use gemini", compare Claude vs Gemini, or delegate tasks to Gemini.

Import existing skills from .claude/skills/ into the Engine workspace for validation, packaging, and publishing. Auto-detects type, creates .meta.yaml, runs MCS-1 check. Use when: 'import', 'bring in', 'add existing skill', or to scan inventory.