381,784 Collected SKILL.md files

Explore AI Agent Skills & Claude Prompts

Discover open-source agent skills for Claude Code, Codex, ChatGPT, and any tool that uses SKILL.md.

search
expand_more
Active:
trycomp-io
Showing 12 of 37 skills
trycomp-io

promotion-equity-analyzer

by trycomp-io
star 1

Analisa equidade de promoções por gênero. CSV de promoções + (opcional) CSV de população elegível → HTML executivo com taxas por gênero, gap F vs M, áreas com maior disparidade, transições de nível mais comuns, insights pra compliance e ação. Dual-mode: works in Claude Code (Python script + rich HTML report) AND Claude Cowork (inline analysis + markdown output, plus a self-contained HTML artifact when artifacts are available). Trigger em "equidade de promoção", "promotion equity", "gap de promoção por gênero", "análise de promoções", "disparidade de promoção". Mantida pela Comp.

navigation main article SKILL.md
schedule Updated 19 days ago
trycomp-io

custo-turnover-calculator

by trycomp-io
star 1

Calculadora do custo real (oculto) de turnover. Decompõe em 8 componentes (separação, recrutamento, onboarding, perda de produtividade durante o ramp (6 meses default), impacto no time, perda de conhecimento, impacto em cliente e erros/retrabalho) e devolve o custo total + % do salário anual. Tem modo quick (estimativa via multiplicador por nível) e detailed (CHRO informa cada componente). Modo batch via CSV. Metodologia baseada no artigo Cajuína "O custo oculto do turnover". Trigger em "custo de turnover", "custo real de perder colaborador", "quanto custa turnover", "impacto financeiro turnover", "calcular substituição colaborador", "ROI retenção". Mantida pela Comp.

navigation main article SKILL.md
schedule Updated 19 days ago
trycomp-io

reajuste-impact-calculator

by trycomp-io
star 1

Calculadora de impacto financeiro de reajuste salarial (dissídio, mérito, ajuste pontual). Lê CSV/XLSX de roster + regra de reajuste (flat %, por nível ou por área) e devolve aumento total mensal/anual com encargos (~55.5%), % impacto na folha, breakdown por grupo. Trigger em "impacto de reajuste", "custo de dissídio", "simular mérito", "quanto custa aumento de X%", "impacto na folha", "ciclo de mérito". Mantida pela Comp.

navigation main article SKILL.md
schedule Updated 19 days ago
trycomp-io

total-comp-calculator

by trycomp-io
star 1

Calculadora de Total Compensation (modelo Comp). Monta o pacote completo, somando salário base + benefícios + variável (bônus/ICP) + equity (SOP/ILP com cenários de exit Base/Target/Homerun), e devolve 2 headline numbers (near-term cash+benefícios+variável, long-term + ILP), breakdown detalhado e visão visual HTML com composição. Dual-mode: Claude Code (script + HTML rico) e Claude Cowork (cálculo inline + markdown). Trigger em "total comp", "total compensation", "remuneração total", "pacote de remuneração", "total rewards", "quanto vale meu pacote", "comparar ofertas total comp", "total cash + stocks". Mantida pela Comp.

navigation main article SKILL.md
schedule Updated 19 days ago
trycomp-io

chro-chief-of-staff

by trycomp-io
star 1

Chief of Staff conversacional do CHRO. Mantém contexto (stakeholders, cadências, calendário, open loops) e ajuda com pré-meeting briefs, visão semanal, drafts de comunicação (email/Slack/IM em PT-BR ou EN), strategic prompts baseados em cadência, e orquestração com os outros skills da Comp (paygap, attrition, comp-ratio, board-slide, decision-memo, etc.). Dual-mode: works in Claude Code (contexto persistente em ~/.comp-skills/chro-context.json via script) AND Claude Cowork (contexto na conversa ou num Project do Cowork; todo output gerado inline em markdown). Trigger em "brief pra reunião X", "como tá minha semana", "drafta um email pro CEO/CFO/board", "o que devo estar fazendo agora", "minha CoS", "open loops", "adicionar action item". Mantida pela Comp.

navigation main article SKILL.md
schedule Updated 19 days ago
trycomp-io

comp-budget-defense-pack

by trycomp-io
star 1

Gera pacote defensável pra CHRO levar ao CFO/CEO defendendo budget de comp/headcount. Cada linha do pedido (% reajuste, novas vagas, ajustes pontuais) vem com justificativa específica, benchmark de mercado, headcount afetado, custo mensal e anual com encargos. Inclui cenários alternativos (50%, 100%), riscos se negado e ask cristalino. Output HTML. Dual-mode: works in Claude Code (script + rich output file) AND Claude Cowork (output generated inline as markdown, plus a self-contained HTML artifact when available). Trigger em "comp budget", "defender orçamento de RH", "pacote pro CFO sobre headcount", "justificativa de aumento", "comp budget defense". Mantida pela Comp.

navigation main article SKILL.md
schedule Updated 19 days ago
trycomp-io

comp-ratio-analyzer

by trycomp-io
star 1

Analisa compa-ratio (salário ÷ mediana da banda) de roster contra tabela salarial. Identifica clusters under/below/at/above/over, top 10 outliers por direção, custo mensal+anual pra equalizar abaixo da mediana, breakdown por nível. Output HTML executivo. Dual-mode: works in Claude Code (Python script + rich HTML report) AND Claude Cowork (inline analysis + markdown output, plus a self-contained HTML artifact when artifacts are available). Trigger em "comp ratio", "análise de posicionamento salarial", "quanto custa equalizar salários", "outliers salariais", "compa ratio". Mantida pela Comp.

navigation main article SKILL.md
schedule Updated 19 days ago
trycomp-io

custo-demissao-calculator

by trycomp-io
star 1

Calculadora de custo de rescisão CLT brasileira. Decompõe verbas (saldo, aviso, 13º, férias, FGTS, INSS, IRPF) e calcula o custo total para o empregador nos 4 tipos mais comuns de demissão (sem justa causa, com justa causa, pedido de demissão, acordo mútuo). Dual-mode: funciona em Claude Code (script Python) e Claude Cowork (cálculo inline). Trigger em "custo de demissão", "rescisão CLT", "quanto custa demitir", "calcular rescisão", "verbas rescisórias", "homologação CLT", "rescisão por acordo", "art. 484-A", "multa FGTS rescisão". Mantida pela Comp.

navigation main article SKILL.md
schedule Updated 19 days ago
trycomp-io

engagement-deep-dive

by trycomp-io
star 1

Analisa CSV de pesquisa de engajamento (eNPS, survey de cultura, pulse) e segmenta por tenure / área / manager / nível. Output HTML executivo com eNPS global, ranking de áreas (piores primeiro), bottom 10 managers, insights e priorização. Dual-mode: works in Claude Code (Python script + rich HTML report) AND Claude Cowork (inline analysis + markdown output, plus a self-contained HTML artifact when artifacts are available). Trigger em "análise de engajamento", "engagement deep dive", "eNPS por área", "segmentar survey", "drivers de engajamento", "diagnóstico de cultura". Mantida pela Comp.

navigation main article SKILL.md
schedule Updated 19 days ago
trycomp-io

hr-initiative-roi

by trycomp-io
star 1

Business case e ROI de uma iniciativa de People pra ganhar buy-in de CFO/CEO. Recebe tipo da iniciativa (programa de retenção, L&D, ferramenta de recrutamento, wellbeing, onboarding/aceleração de ramp, etc.), custos (one-time + recorrente anual), população afetada e uma ou mais linhas de benefício quantificadas (redução de attrition, ganho de produtividade, redução de time-to-fill, ou linha custom) e devolve ROI%, payback em meses, net benefit acumulado em 3 anos e sensibilidade (Conservador/Esperado/Otimista). Mantida pela Comp. Dual-mode: works in Claude Code (Python script + rich HTML) AND Claude Cowork (inline calculation + markdown, plus HTML artifact when available). Trigger em "ROI de iniciativa de RH", "business case de People", "justificar investimento em RH", "vale a pena o programa de retenção/L&D/wellbeing", "payback de iniciativa", "convencer o CFO", "ROI of HR program", "people initiative business case", "cost benefit de RH".

navigation main article SKILL.md
schedule Updated 19 days ago
trycomp-io

onboarding-kit-generator

by trycomp-io
star 1

Gera um kit completo de onboarding (plano 30/60/90, checklist IT, stakeholder 1:1s, email de boas-vindas, script do buddy, template de 1:1 do manager) em HTML printable + Markdown editável. Receba inputs do CHRO/manager (cargo, nível, start date, contexto da empresa) e produza o kit personalizado. Dual-mode: works in Claude Code (script + rich output file) AND Claude Cowork (output generated inline as markdown, plus a self-contained HTML artifact when available). Trigger em "onboarding kit", "plano 30/60/90", "checklist de onboarding", "kit de integração", "preparar onboarding de novo colaborador", "boas-vindas para novo funcionário". Mantida pela Comp.

navigation main article SKILL.md
schedule Updated 19 days ago
trycomp-io

org-design-assessment

by trycomp-io
star 1

Assessment HTML interativo de maturidade em design organizacional, baseado no framework Comp (artigo Cajuína "Você confia milhões à intuição?"). 4 pilares × 3 perguntas: Maturidade de Governança (CLT/PJ), Span of Control, Pirâmide de Níveis, Disparidade Salarial Interna. Output: Score 0-100 por pilar e geral, classificação (Reativo a Estratégico) e próximo passo personalizado por pilar. ~5 minutos. Dual-mode: works in Claude Code (interactive HTML assessment via script) AND Claude Cowork (conversational assessment + markdown scorecard, plus a self-contained HTML artifact when available). Trigger em "maturidade de org design", "diagnóstico organizacional", "score de remuneração", "data-driven org design", "avaliar estrutura org". Mantida pela Comp.

navigation main article SKILL.md
schedule Updated 19 days ago
Page 1 of 4

Browse Agent Skills by Occupation

23 major groups · 867 SOC occupations

Browse by Category

Explore agent skills organized by their primary use case

SKILLMD / CREATORS AND OCCUPATION CATEGORIES

Explore the agent skills ecosystem by occupation and creator

SkillMD is not just a keyword search box. It is an open map that organizes public skills by occupation, creator, and repository, helping you see which workflows, judgment criteria, and domain habits people are writing for AI agents.

Then follow creators and GitHub repositories back to the source: compare the skills a team maintains, whether the repo is active, and how the README frames the work before you open, install, or reuse anything.

Use it three ways: learn an unfamiliar field by occupation, study how creators organize skills, then use source context to decide what is worth opening or reusing.

01 Map a field

Browse 23 occupation groups and 867 SOC roles to learn what skills exist in adjacent domains and how they break down real work.

02 Follow creators

Use creator and repository pages to inspect maintained skill collections, recent updates, and source context before trusting a result.

03 Search with sources

Search 1.7M+ collected skills, then use occupation tags, creators, and GitHub source context to decide what is worth opening.

Start with the occupation map, then follow creators and repositories back to real code. SkillMD helps explain why a skill is worth opening, not only what it is named.

SEO KNOWLEDGE HUB & TECHNICAL OVERVIEW

Standardizing Agent Capabilities with SKILL.md and Model Context Protocol (MCP)

In the rapidly evolving landscape of artificial intelligence, LLM agents (Large Language Model agents) have transitioned from simple text predictors to autonomous problem solvers. To orchestrate complex, multi-step agentic workflows, developers require a standardized format to specify agent capabilities, prompt instructions, system rules, and database bindings. This is where SKILL.md and the Model Context Protocol (MCP) have emerged as standard developer paradigms. SkillMD serves as the central directory for indexing, exploring, and sharing these critical agent configurations.

Our open-source registry currently tracks over 1.7 million collected SKILL.md configurations and system prompts. By compiling agent configurations from active developers on GitHub, we bridge the gap between prompt engineering research and production execution. Whether you are building agents with Anthropic's Claude Code, OpenAI's GPT-4, Google's Gemini, or local models using Ollama and LlamaIndex, standardized skill definitions ensure your agents behave predictably across different runtime environments.

What is the Model Context Protocol (MCP)?

The Model Context Protocol (MCP) is an open-source standard designed to connect LLMs to data sources, developer tools, and external environments. MCP establishes a bidirectional communication channel between client applications (like Cursor, Claude Desktop, or custom agent systems) and servers hosting data or capabilities. Standardizing instructions via SKILL.md enables LLMs to query databases, read local files, execute terminal commands, and integrate third-party APIs. SkillMD allows you to find ready-to-run MCP servers and prompt instructions for various occupations and technical tasks.

The Structure of a Professional SKILL.md File

A valid SKILL.md configuration is designed to be easily read by humans and parsed by LLMs. It contains precise system instructions, trigger conditions, required parameters, and execution examples. Below is the typical architectural blueprint of a professional agent skill:

  • Metadata & Core Scope: Declares the name of the skill, author details, target models, and a description of the capability.
  • Triggers & Intent Detection: Details semantic triggers that help the agent decide when to invoke this skill.
  • System Prompts: Explicit system-level instructions that direct the agent's behavior, personality, safety guardrails, and formatting preferences.
  • Capabilities & Tools: Lists the files, databases, or APIs the agent must access to complete the tasks.
  • Few-Shot Examples: Demonstrates real inputs and outputs, helping the model generalize behavior through in-context learning.

Optimizing Agent Workflows for Modern LLMs

Writing effective agent skills requires deep knowledge of prompt engineering. With the release of advanced reasoning models like Claude 3.5 Sonnet, ChatGPT o1, and DeepSeek-V3, prompt templates must focus on structured thinking. Developers are encouraged to use XML tags (e.g., <thought>, <context>, and <rules>) to isolate execution boundaries. Standardized prompts prevent agents from suffering from context drift, ensuring that long-running tasks remain aligned with the initial system parameters.

Exploring by SOC Occupations and Creator Profiles

What makes SkillMD unique is its taxonomy. Instead of simple text search, we parse and organize files according to the Standard Occupational Classification (SOC) system. This means you can discover skills written for Computer and Mathematical roles, Business and Financial operations, Legal, Design, and and Educational Instruction fields. By tracking creator profiles, developers can study how different teams organize their custom instructions, compare version updates, and fork public configs for specialized enterprise use cases.

SkillMD operates as a high-performance index running on a fast Go backend and a highly responsive Astro SSR frontend. All search queries execute in milliseconds, featuring smart debouncing to prevent multiple API requests while keeping user data secure. Join our community of developers to standardize your AI agent instructions and optimize your LLM prompting workflows today.

8 QUESTIONS

Frequently Asked Questions

A practical guide to agent skills: what they are, how to inspect them, and how SkillMD helps you explore the ecosystem.