O que agent-skills faz?
Habilidades de agente escritas manualmente, organizadas para o CLI skills da Vercel (skills///SKILL.md).
Habilidades de agente escritas manualmente, organizadas para o CLI `skills` da Vercel (skills/<categoria>/<habilidade>/SKILL.md).
Este repositório contém uma coleção de habilidades (skills) para agentes de IA, escritas manualmente e seguindo a estrutura de diretórios esperada pela ferramenta de linha de comando `skills` da Vercel. Cada habilidade é organizada em uma pasta própria dentro de `skills/<categoria>/<habilidade>/SKILL.md`, permitindo que desenvolvedores criem, compartilhem e reutilizem comportamentos específicos para agentes como Claude Code ou Cursor. A abordagem artesanal garante que cada skill seja precisa e otimizada para tarefas específicas, sem depender de geração automática. Suporta múltiplas plataformas de agentes, desde que respeitem o formato de arquivo SKILL.md, e oferece uma maneira modular de estender as capacidades de agentes de IA em fluxos de trabalho de desenvolvimento.
npx skills add Ephasme/agent-skillsInstalled? Explore more Programação e Desenvolvimento skills: steipete/bluebubbles, steipete/eightctl, steipete/blucli · View all 6 →
Habilidades de agente escritas manualmente, organizadas para o CLI skills da Vercel (skills///SKILL.md).
This repo contains 3 individual skills — each has its own dedicated page.
Senior counsel on French insurance law, grounded in primary sources (Code des assurances, Code civil, Code de la mutualité, Code de la sécurité sociale book IX, Cour de cassation case law, EU texts, ACPR doctrine). Use for French-law insurance questions: refusal of cover, nullity for false declaration, forfeiture (déchéance), exclusion clauses, two-year limitation period, proportional rule, termination and the Hamon / Chatel / Lemoine laws, motor claims and the Badinter law, dommages-ouvrage...
Rewrites one document — README, AGENTS.md, design note, runbook, spec — so it is free of legacy (no history, no backstory), factual (every claim verified against a primary source or marked, nothing invented), concise (one fact in one place), organized (critical information first), and tuned to a declared reader. Takes --target=agent (default), for an LLM that reads the document as context, or --target=human; the two produce deliberately different documents, each following the measured...
>- Scans a codebase for structural quality issues (architecture incoherence, design-principle violations, dead code, excessive complexity, unclear naming, hidden state) and produces an evidence-backed, severity-ranked report with concrete, non-breaking refactor suggestions. Detects the stack and adds that stack's current, sourced rules as extra lenses where a stack pack exists (Swift/iOS, React). Each aspect gets its own reviewer on a capable model; a cheaper checker verifies and ranks every...
Send and manage iMessages via BlueBubbles, including attachments, tapbacks, edits, replies, and groups.
Control Eight Sleep pods (status, temperature, alarms, schedules).
BluOS CLI (blu) for discovery, playback, grouping, and volume.
Create, search, and manage Bear notes via grizzly CLI.
Capture frames or clips from RTSP/ONVIF cameras.
Search GIF providers with CLI/TUI, download results, and extract stills/sheets.