write-a-skill
Crie novas skills de agente com estrutura adequada, disclosure progressivo e recursos empacotados.
Skill by hcb2019
Install
Works with Claude Code, Claude apps, Codex, Cursor, Gemini CLI, GitHub Copilot, VS Code, OpenCode, Goose, Windsurf. Read the repository before you give any tool access to your data.
npx agentmarket install skill/hcb2019-write-a-skill
Asks which of your tools to add it to (Claude Code, Codex, Cursor, VS Code, Windsurf, Gemini CLI, Claude Desktop) and shows the change first. See https://agentmart.dev/cli.
Get the weekly diff
The weekly diff: one email a week with new agent tools, notable updates and grade changes, plus security alerts for tools you follow. Double opt-in, one-click unsubscribe.
About
Use cases: writing
Reviews
Write a reviewNo reviews yet. Installed it? Reviews come from verified installers only. How reviews work
Permissions
What this skill can do and what it asks for, from its SKILL.md. Checked Oct 25, 2026.
- Tools
- No tools found
- Secrets
- None asked for
- Install scripts
- None found
Network hosts it talks to 1
codeload.github.com· found in install command
Files it touches
~/.claude/skills/write-a-skill
What's inside
- Skill name
write-a-skill- Description
- Crie novas skills de agente com estrutura adequada, disclosure progressivo e recursos empacotados. Use quando o usuário quiser criar, escrever ou construir uma nova skill.
- License
- MIT
- Instructions
- 114 lines in SKILL.md · view on GitHub
Agent Skills spec issues
- name: "write-a-skill" does not match folder "criar-skill"
Files (1)
- SKILL.md
SKILL.md (first lines)
# Writing Skills
## Process
1. **Gather requirements** — ask the user about:
- What task/domain does the skill cover?
- What specific use cases should it handle?
- Does it need executable scripts or just instructions?
- Any reference material to include?
2. **Draft the skill** — create:
- SKILL.md with concise instructions
- Additional reference files if content exceeds 500 lines
- Utility scripts if deterministic operations are needed
3. **Review with the user** — present the draft and ask:
- Does this cover your use cases?
- Anything missing or confusing?
- Should any section have more/less detail?
## Skill Structure
```
skill-name/
├── SKILL.md # Core instructions (required)
├── REFERENCE.md # Detailed documentation (if needed)
├── EXAMPLES.md # Usage examples (if needed)
└── scripts/ # Utility scripts (if needed)
└── helper.js
```
## SKILL.md Template
```md
---
name: skill-name
description: Brief description of the capability. Use when [specific triggers].
---
# Skill Name
## Quick start
[Minimal working example]
## Workflows
[Step-by-step processes with checklists for complex tasks]
## Advanced features
[Link to separate files: See [REFERENCE.md](REFERENCE.md)]
```
## Description Requirements
The description is **the only thing your agent sees** when deciding which skill to load. It appears in the system prompt alongside all other installed skills. Your agent reads these descriptions and picks the relevant skill based on the user's request.
**Goal**: Give the agent enough information to know:
1. What capability this skill provides
2. When/why to trigger it (specific keywords, contexts, file types)
**Format**:
- Maximum 1024 characters
- Write in third person
- First sentence: what it does
- Second sentence: "Use when [specific triggers]"
**Good example**:
```
Extracts text and tables from PDF files, fills forms, merges documents. Use when working with PDF files or when the user mentions PDFs, forms, or document extraction.
```
**Bad example**:
```
Helps with documents.
```
The bad example gives the agent no way to distinguish this skill from other document skills.
## When to Add Scripts
Add utility scripts when:
- The operation is deterministic (validation, formatting)
- The same code would be generated repeatedly
- Errors need explicit handling
Scripts save tokens and improve reliability compared to generated code.
## When to Split Files
Split into separate files when:
- SKILL.md exceeds 100 lines
- Content has distinct domains (e.g., finance vs sales schemas)
- Advanced features are rarely needed
## Review Checklist
After drafting, verify:
- [ ] Description includes triggers ("Use when...")
- [ ] SKILL.md under 100 lines
- [ ] No time-sensitive information
- [ ] Consistent terminology
- [ ] Concrete examples included
- [ ] References one level deepFrom hcb2019/claude-code-skills, MIT.
More from hcb2019/claude-code-skills
- 0.498score
diagnose
hcb2019
Loop disciplinado de diagnóstico para bugs difíceis e regressões de performance.
SkillCFreshness: C★ 1Claude Code +9 - 0.495score
git-guardrails-claude-code
hcb2019
Configura hooks do Claude Code para bloquear comandos git perigosos (push, reset --hard, clean, branch -D, etc.) antes que sejam executados.
SkillCFreshness: C★ 1Claude Code +9 - 0.494score
setup-pre-commit
hcb2019
Configura hooks de pre-commit com Husky, lint-staged (Prettier), verificação de tipos e testes no repositório atual.
SkillCFreshness: C★ 1Claude Code +9 - 0.494score
humanizador-pt-br
hcb2019
Remove traços de escrita de IA de textos em português brasileiro, preservando a voz e expertise do autor.
SkillCFreshness: C★ 1Claude Code +9 - 0.494score
tdd
hcb2019
Desenvolvimento orientado a testes com loop red-green-refactor.
SkillCFreshness: C★ 1Claude Code +9 - 0.493score
prototype
hcb2019
Constrói um protótipo descartável para explorar um design antes de se comprometer com ele.
SkillCFreshness: C★ 1Claude Code +9 - 0.493score
improve-codebase-architecture
hcb2019
Encontra oportunidades de aprofundamento em um código, informado pela linguagem de domínio no CONTEXT.md e pelas decisões em docs/adr/.
SkillCFreshness: C★ 1Claude Code +9 - 0.490score
triage
hcb2019
Triagem de issues através de uma máquina de estados guiada por papéis de triagem.
SkillCFreshness: C★ 1Claude Code +9 - 0.490score
grill-with-docs
hcb2019
Sessão de sabatina que desafia seu plano contra o modelo de domínio existente, afia a terminologia e atualiza a documentação (CONTEXT.md, ADRs) inline…
SkillCFreshness: C★ 1Claude Code +9 - 0.490score
to-prd
hcb2019
Transforma o contexto atual da conversa em um PRD (Documento de Requisitos do Produto) e publica no tracker de issues do projeto.
SkillCFreshness: C★ 1Claude Code +9 - 0.490score
to-issues
hcb2019
Quebra um plano, spec ou PRD em issues independentes no tracker de issues do projeto usando fatias verticais tracer-bullet.
SkillCFreshness: C★ 1Claude Code +9 - 0.490score
caveman
hcb2019
Modo de comunicação ultra-comprimido.
SkillCFreshness: C★ 1Claude Code +9
Signals
- Stars
- 1
- Forks
- 0
- Open issues
- 0
- Last commit (this folder)
- Jun 8, 2026 (4 months ago)
From GitHub (fetched Oct 24, 2026).
Details
- License
- MIT
- Repository
- github.com/hcb2019/claude-code-skills
- First seen
- Oct 24, 2026
- Last checked
- Oct 24, 2026
- Source
- GitHubgithub-graphql
More from hcb2019
- 0.498score
diagnose
hcb2019
Loop disciplinado de diagnóstico para bugs difíceis e regressões de performance.
SkillCFreshness: C★ 1Claude Code +9 - 0.495score
git-guardrails-claude-code
hcb2019
Configura hooks do Claude Code para bloquear comandos git perigosos (push, reset --hard, clean, branch -D, etc.) antes que sejam executados.
SkillCFreshness: C★ 1Claude Code +9 - 0.494score
tdd
hcb2019
Desenvolvimento orientado a testes com loop red-green-refactor.
SkillCFreshness: C★ 1Claude Code +9 - 0.494score
setup-pre-commit
hcb2019
Configura hooks de pre-commit com Husky, lint-staged (Prettier), verificação de tipos e testes no repositório atual.
SkillCFreshness: C★ 1Claude Code +9 - 0.494score
humanizador-pt-br
hcb2019
Remove traços de escrita de IA de textos em português brasileiro, preservando a voz e expertise do autor.
SkillCFreshness: C★ 1Claude Code +9 - 0.493score
prototype
hcb2019
Constrói um protótipo descartável para explorar um design antes de se comprometer com ele.
SkillCFreshness: C★ 1Claude Code +9
Cite this page
write-a-skill. Agent Mart. https://agentmart.dev/skills/hcb2019-write-a-skill (last updated 2026-10-24)