andretauan/tao-onboarding
skills/en/tao-onboarding/SKILL.md
Guide new users through TAO framework setup, concepts, and first execution. Use when someone asks about TAO, how to get started, or needs help understanding the workflow.
$ install --global
skillsauthnpx skillsauth add andretauan/tao tao-onboardingInstall this skill globally with one command. Works with Claude Code, Cursor, and Windsurf.
Security Scan Results
3 of 9 scanners reported clean
Some scanners were skipped, did not run, or reported a non-clean status. Review each row below.
3
Scanners Passed
9
Scanners in report
Clean
TrivyContainer and dependency vulnerability scanner
95%
Clean
SemgrepStatic code analysis for vulnerabilities
95%
Clean
mcp-scan (Snyk)Model Context Protocol security validation
95%
Skipped
Snyk (dep)Open source security scanning
50%
Skipped
Socket.devSupply chain security analysis
50%
Skipped
VirusTotalMulti-engine malware detection
50%
Skipped
CrowdStrikeAdvanced threat intelligence
50%
Skipped
OSV-ScannerOpen Source Vulnerability database check
50%
Skipped
OWASP Dep-Check
50%
Last scanned: Apr 23, 2026, 2:36 PM370.9s1 file scanned
SKILL.md
- name:
- tao-onboarding
- description:
- Guide new users through TAO framework setup, concepts, and first execution. Use when someone asks about TAO, how to get started, or needs help understanding the workflow.
- user-invocable:
- false
TAO Onboarding Guide
When to use this skill
Use when someone is new to TAO, asks how it works, or needs help setting up their first project.
What is TAO?
TAO (Trace · Align · Operate) is an AI-native development framework that organizes coding with AI agents into three layers:
- Trace (Think) — Brainstorm ideas, evaluate trade-offs, make decisions
- Align (Plan) — Decompose work into phases with tasks, acceptance criteria, and effort estimates
- Operate (Execute) — Execute tasks in an autonomous loop with quality gates
Key Files
| File | Purpose |
|------|---------|
| CLAUDE.md | Project identity + code patterns (root) |
| .github/tao/tao.config.json | Single source of truth for config |
| .github/tao/CONTEXT.md | Current state — active phase, decisions |
| .github/tao/CHANGELOG.md | History — what changed, when, by whom |
| .github/tao/RULES.md | Framework rules (R0-R7) |
| .github/skills/INDEX.md | Skill catalog (if exists) |
| .github/agents/*.agent.md | Agent definitions |
First Execution Checklist
- Review
.github/tao/tao.config.json— customize models, paths, lint - Edit
CLAUDE.md— add project-specific rules and code patterns - Set first phase in
.github/tao/CONTEXT.md - Enable
chat.useCustomAgentHooksin VS Code settings - In Copilot Chat: select
@Execute-Taoand say "execute"
The Loop
@Execute-Tao → reads CONTEXT.md → finds active phase
→ reads PLAN.md → picks next task
→ routes to right model (Sonnet/Opus/GPT-4.1)
→ executes task → runs lint → updates CONTEXT.md
→ commits → picks next task → repeats
Agents
| Agent | When to use |
|-------|-------------|
| @Execute-Tao | Full autonomous execution loop |
| @Brainstorm-Wu | Planning, ideation, trade-off analysis |
| @Investigate-Shen | Complex debugging, architecture decisions, security audits |
Rules (R0-R7)
- R0: Compliance check at start of every code-modifying response
- R1: Lint check after every edit
- R2: Handoff audit on session end
- R3: Skill check before any code task
- R4: Timestamp in all documentation (YYYY-MM-DD HH:MM)
- R5: NEVER edit without reading first
- R6: Update CONTEXT.md after every file edit
- R7: Session must end with clean git status
Related Skills
andretauan/tao-test-strategy
testing
VerifiedTrustedCommunity
Estratégia de pirâmide de testes com análise de cobertura, identificação de edge cases e planejamento de testes. Use ao planejar testes, melhorar cobertura, identificar edge cases ou escrever especificações de teste.
18SKILL.mdUpdated Apr 23, 2026
andretauan/tao-security-audit
development
VerifiedTrustedCommunity
Auditoria de segurança alinhada ao OWASP Top 10 com checklist para injection, XSS, autenticação, autorização, gestão de secrets e vulnerabilidades comuns. Use ao auditar segurança, revisar código de auth ou hardening de aplicação.
18SKILL.mdUpdated Apr 23, 2026
andretauan/tao-refactoring
development
VerifiedTrustedCommunity
Metodologia de refatoração segura com detecção de code smells, transformação passo-a-passo e prevenção de regressão. Use ao refatorar código, reduzir dívida técnica ou melhorar estrutura.
18SKILL.mdUpdated Apr 23, 2026
andretauan/tao-plan-writing
testing
VerifiedTrustedCommunity
Decomposição expert de tarefas para criar PLAN.md no TAO. Quebra features em fases e tarefas com critérios de aceite, estimativas e dependências. Use ao planejar trabalho, criar fases ou decompor features.
18SKILL.mdUpdated Apr 23, 2026