Skill Installer v3.0

Overview

This public intake copy packages

plugins/antigravity-awesome-skills-claude/skills/skill-installer

https://github.com/sickn33/antigravity-awesome-skills

Use it when the operator needs the upstream workflow, support files, and repository context to stay intact while the public validator and private enhancer continue their normal downstream flow.

This intake keeps the copied upstream files intact and uses

metadata.json

ORIGIN.md

Skill Installer v3.0

Imported source sections that did not map cleanly to the public headings are still preserved below or in the support files. Notable imported sections: How It Works, Principio: Redundancia Maxima, Localizacao, Cenario 1: Apos Skill-Creator Finalizar, Cenario 2: Usuario Pede Para Instalar Uma Skill Especifica, Cenario 3: Simular Instalacao Sem Fazer Nada (Dry-Run).

When to Use This Skill

Use this section as the trigger filter. It should make the activation boundary explicit before the operator loads files, runs commands, or opens a pull request.

• When the user mentions "instalar skill" or related topics
• When the user mentions "install skill" or related topics
• When the user mentions "registrar skill" or related topics
• When the user mentions "nova skill" or related topics
• When the user mentions "new skill" or related topics
• When the user mentions "adicionar skill ao ecossistema" or related topics

Operating Table

metadata.json

ORIGIN.md

references/known-locations.md

scripts/detect_skills.py

## Related Skills

Workflow

This workflow is intentionally editorial and operational at the same time. It keeps the imported source useful to the operator while still satisfying the public intake standards that feed the downstream enhancer flow.

1. Comando - Descricao
2. --source <path> - Instalar skill de caminho
3. --source <path> --force - Sobrescrever se existir
4. --source <path> --name <nome> - Nome customizado
5. --source <path> --dry-run - Simular sem alterar
6. --detect - Auto-detectar skills pendentes
7. --detect --auto - Detectar e instalar automaticamente

Imported Workflow Notes

Imported: Workflow Principal

Quando esta skill for ativada, siga estes passos na ordem:

Imported: Install_Skill.Py

--source <path>

--source <path> --force

--source <path> --name <nome>

--source <path> --dry-run

--detect

--detect --auto

--uninstall <nome>

--rollback <nome>

--reinstall-all

--health

--health --repair

--status

--log [N]

--json

Imported: Overview

Instala, valida, registra e verifica novas skills no ecossistema. 10 checks de seguranca, copia, registro no orchestrator e verificacao pos-instalacao.

Imported: How It Works

Agente instalador enterprise-grade que garante que toda skill criada (via skill-creator ou manualmente) seja corretamente instalada, registrada e verificada no ecossistema. Inclui auto-repair, rollback, dry-run, dashboard, e diagnostico avancado.

Examples

Example 1: Ask for the upstream workflow directly

Use @skill-installer to handle <task>. Start from the copied upstream workflow, load only the files that change the outcome, and keep provenance visible in the answer.

Explanation: This is the safest starting point when the operator needs the imported workflow, but not the entire repository.

Example 2: Ask for a provenance-grounded review

Review @skill-installer against metadata.json and ORIGIN.md, then explain which copied upstream files you would load first and why.

Explanation: Use this before review or troubleshooting when you need a precise, auditable explanation of origin and file selection.

Example 3: Narrow the copied support files before execution

Use @skill-installer for <task>. Load only the copied references, examples, or scripts that change the outcome, and name the files explicitly before proceeding.

Explanation: This keeps the skill aligned with progressive disclosure instead of loading the whole copied package by default.

Example 4: Build a reviewer packet

Review @skill-installer using the copied upstream files plus provenance, then summarize any gaps before merge.

Explanation: This is useful when the PR is waiting for human review and you want a repeatable audit packet.

Best Practices

Treat the generated public skill as a reviewable packaging layer around the upstream repository. The goal is to keep provenance explicit and load only the copied source material that materially improves execution.

• Provide clear, specific context about your project and requirements
• Review all suggestions before applying them to production code
• Combine with other complementary skills for comprehensive analysis
• Keep the imported skill grounded in the upstream repository; do not invent steps that the source material cannot support.
• Prefer the smallest useful set of support files so the workflow stays auditable and fast to review.
• Keep provenance, source commit, and imported file paths visible in notes and PR descriptions.
• Point directly at the copied upstream files that justify the workflow instead of relying on generic review boilerplate.

Imported Operating Notes

Imported: Best Practices

• Provide clear, specific context about your project and requirements
• Review all suggestions before applying them to production code
• Combine with other complementary skills for comprehensive analysis

Troubleshooting

Problem: The operator skipped the imported context and answered too generically

Symptoms: The result ignores the upstream workflow in

plugins/antigravity-awesome-skills-claude/skills/skill-installer

metadata.json

ORIGIN.md

Problem: The imported workflow feels incomplete during review

Symptoms: Reviewers can see the generated

SKILL.md

Problem: The task drifted into a different specialization

Symptoms: The imported skill starts in the right place, but the work turns into debugging, architecture, design, security, or release orchestration that a native skill handles better. Solution: Use the related skills section to hand off deliberately. Keep the imported provenance visible so the next skill inherits the right context instead of starting blind.

Imported Troubleshooting Notes

Imported: Cenario 6: Health Check + Auto-Repair

python C:\Users\renat\skills\skill-installer\scripts\install_skill.py --health
python C:\Users\renat\skills\skill-installer\scripts\install_skill.py --health --repair

--health

--health --repair

• Skills nao registradas -> registra
• Skills faltando no registry -> atualiza
• Duplicatas -> remove

Related Skills

• @server-management

  - Use when the work is better handled by that native specialization after this imported skill establishes context.

• @service-mesh-expert

  - Use when the work is better handled by that native specialization after this imported skill establishes context.

• @service-mesh-observability

  - Use when the work is better handled by that native specialization after this imported skill establishes context.

• @sexual-health-analyzer

  - Use when the work is better handled by that native specialization after this imported skill establishes context.

Additional Resources

Use this support matrix and the linked files below as the operator packet for this imported skill. They should reflect real copied source material, not generic scaffolding.

references

references/known-locations.md

examples

examples/n/a

scripts

scripts/detect_skills.py

agents

agents/n/a

assets

assets/n/a

• known-locations.md
• detect_skills.py
• install_skill.py
• package_skill.py
• requirements.txt
• known-locations.md

Imported Reference Notes

Imported: Principio: Redundancia Maxima

Seis camadas de validacao garantem que nenhuma skill fique mal-instalada:

Imported: Localizacao

C:\Users\renat\skills\skill-installer\
├── SKILL.md              <- este arquivo
├── scripts/
│   ├── install_skill.py  <- instalador principal (11 passos) + todos os comandos
│   ├── detect_skills.py  <- scanner de skills nao-instaladas
│   ├── validate_skill.py <- validacao profunda (10 checks)
│   ├── package_skill.py  <- empacotador ZIP + verificador de integridade
│   └── requirements.txt
├── references/
│   └── known-locations.md
└── data/
    ├── install_log.json  <- log de operacoes (auto-gerado, com rotacao)
    ├── backups/          <- backups antes de sobrescrever
    └── staging/          <- area temporaria para copias seguras

Imported: Cenario 1: Apos Skill-Creator Finalizar

O skill-creator acabou de criar uma skill em algum diretorio. Execute:

python C:\Users\renat\skills\skill-installer\scripts\install_skill.py --source "<caminho-da-skill-criada>" --force

Substitua

<caminho-da-skill-criada>

Imported: Cenario 2: Usuario Pede Para Instalar Uma Skill Especifica

python C:\Users\renat\skills\skill-installer\scripts\install_skill.py --source "<caminho>" [--name "nome-override"] [--force]

Imported: Cenario 3: Simular Instalacao Sem Fazer Nada (Dry-Run)

python C:\Users\renat\skills\skill-installer\scripts\install_skill.py --source "<caminho>" --dry-run

Mostra exatamente o que seria feito em cada um dos 11 passos, sem alterar nenhum arquivo.

Imported: Cenario 4: Detectar E Instalar Skills Pendentes

python C:\Users\renat\skills\skill-installer\scripts\install_skill.py --detect
python C:\Users\renat\skills\skill-installer\scripts\install_skill.py --detect --auto

Escaneia locais conhecidos (Desktop, Downloads, Temp, workspaces) e apresenta candidatos com timestamps e tamanho. Com --auto instala todos automaticamente.

Imported: Cenario 5: Desinstalar Uma Skill

python C:\Users\renat\skills\skill-installer\scripts\install_skill.py --uninstall "nome-da-skill"

Remove de

skills/

.claude/skills/

Imported: Cenario 7: Rollback (Restaurar De Backup)

python C:\Users\renat\skills\skill-installer\scripts\install_skill.py --rollback "nome-da-skill"

Encontra o backup mais recente da skill e restaura para o estado anterior. Re-registra e atualiza o registry automaticamente.

Imported: Cenario 8: Reinstalar Todas As Skills

python C:\Users\renat\skills\skill-installer\scripts\install_skill.py --reinstall-all

Re-registra TODAS as skills em

.claude/skills/

Imported: Cenario 9: Dashboard De Status

python C:\Users\renat\skills\skill-installer\scripts\install_skill.py --status

Exibe dashboard rico com: nome, versao, saude, registro, backups de cada skill, estatisticas de operacoes (installs, uninstalls, rollbacks).

Imported: Cenario 10: Ver Historico De Operacoes

python C:\Users\renat\skills\skill-installer\scripts\install_skill.py --log
python C:\Users\renat\skills\skill-installer\scripts\install_skill.py --log 50

Mostra as ultimas N operacoes com timestamp, tipo, skill e resultado.

Imported: Validar Uma Skill

python C:\Users\renat\skills\skill-installer\scripts\validate_skill.py "C:\caminho\para\skill"
python C:\Users\renat\skills\skill-installer\scripts\validate_skill.py "C:\caminho\para\skill" --strict

Retorna JSON com

valid

checks

warnings

errors

Imported: Detectar Skills Nao-Instaladas

python C:\Users\renat\skills\skill-installer\scripts\detect_skills.py
python C:\Users\renat\skills\skill-installer\scripts\detect_skills.py --path "C:\diretorio\especifico"
python C:\Users\renat\skills\skill-installer\scripts\detect_skills.py --all

Retorna JSON com candidatos incluindo:

name

source_path

already_installed

valid_frontmatter

last_modified

size_kb

file_count

Imported: Empacotar Zip Para Claude.Ai

python C:\Users\renat\skills\skill-installer\scripts\package_skill.py --source "C:\caminho"
python C:\Users\renat\skills\skill-installer\scripts\package_skill.py --all
python C:\Users\renat\skills\skill-installer\scripts\package_skill.py --all --output "C:\Users\renat\Desktop"

Imported: Verificar Integridade De Zips Existentes

python C:\Users\renat\skills\skill-installer\scripts\package_skill.py --verify
python C:\Users\renat\skills\skill-installer\scripts\package_skill.py --verify --output "C:\Users\renat\Desktop"

Imported: O Que O Instalador Faz (11 Passos)

1. Resolver fonte - identifica o diretorio da skill
2. Validar - roda 10 checks no SKILL.md e estrutura
3. Determinar nome - extrai do frontmatter ou usa --name, compara versoes
4. Verificar conflitos - checa se ja existe no destino
5. Backup - se sobrescrevendo, faz backup timestamped (exclui backups/ e staging/)
6. Copiar via staging - copia para area temp, valida hash, depois move
7. Registrar no Claude Code CLI - copia SKILL.md para .claude/skills/<nome>/
8. Atualizar registry - roda scan_registry.py --force (com deduplicacao por nome)
9. Verificar instalacao - confirma arquivos, registry, registro (5 checks)
10. Empacotar ZIP - cria ZIP para upload no Claude.ai web/desktop (validado)
11. Logar operacao - append em install_log.json (com rotacao automatica)

IMPORTANTE: Skills no Claude Code (CLI) e Claude.ai (web/desktop) sao SEPARADAS. O instalador cobre ambas superficies automaticamente.

Imported: Seguranca

• Backups automaticos: antes de qualquer sobrescrita, backup em

  data/backups/<nome>_<timestamp>/

• Staging area: copia para temp primeiro, valida hash, depois move (minimiza corrupcao)
• Idempotencia: rodar 2x com mesma source detecta hashes identicos, nao duplica
• Arquivos proibidos: bloqueia instalacao se encontrar .env, *.key, .pem, credentials.
• Log com rotacao: toda operacao logada; mantem ultimas 500 entradas
• Limite de backups: mantem ultimos 5 por skill, limpa automaticamente
• Anti-recursao: backup e staging excluem seus proprios subdiretorios
• Deduplicacao no registry: scan_registry.py deduplica por nome (case-insensitive)
• ZIP validado: verifica ausencia de backslashes, conteudo nao-vazio, integridade
• Dry-run: simula instalacao completa sem tocar nenhum arquivo
• Rollback: restaura de backup com re-registro automatico
• Comparacao de versao: detecta upgrade/downgrade/same antes de sobrescrever
• Hash normalizado: md5_dir usa forward slashes e exclui dirs de sistema

Imported: Integracao Com Orchestrator

Esta skill e auto-detectada pelo

scan_registry.py

match_skills.py

Alem disso, o CLAUDE.md global contem instrucao para rodar o instalador automaticamente apos o skill-creator finalizar uma skill.

Imported: Common Pitfalls

• Using this skill for tasks outside its domain expertise
• Applying recommendations without understanding your specific context
• Not providing enough project context for accurate analysis

Imported: Limitations

• Use this skill only when the task clearly matches the scope described above.
• Do not treat the output as a substitute for environment-specific validation, testing, or expert review.
• Stop and ask for clarification if required inputs, permissions, safety boundaries, or success criteria are missing.