Ready to supercharge your AI agents?

Install any skill in seconds. Free to start, no credit card required.

Agent Orchestrator · sickn33 | DecimalAI

Agent Orchestrator

SkillScore50Maintained

agent-orchestrator

Meta-skill que orquestra todos os agentes do ecossistema. Scan automatico de skills, match por capacidades, coordenacao de workflows multi-skill e registry management.

agent-toolingby sickn33

Links this skill to your agents and keeps it current with the author’s updates.

Automatic

AI Engineer pack

1 · One-time — install the CLI (docs ↗)

pip install decimalai

2 · Get the skill — writes .claude/skills/agent-orchestrator/SKILL.md

decimalai skills pull agent-orchestrator --out .claude/skills/

No CLI? Get the same file — curl · raw file

curl -fsSL --create-dirs -o .claude/skills/agent-orchestrator/SKILL.md https://app.decimal.ai/s/agent-orchestrator/SKILL.md

Raw file: /s/agent-orchestrator/SKILL.md ↗ · machine-readable summary at /s/agent-orchestrator.json ↗

In productionGlobal

how this skill behaves on real traffic · last 30 days

No production data for this skill yet — usage numbers appear here once agents start running it.

Anonymized aggregate across every org using this skill — proof from real production use, not a demo.

Does this skill help? · Benchmark: with vs. withoutsign in to run this on your agents

22 test cases from the publisher’s eval.yaml · each run twice on gemini-3.6-flash — with the skill injected, then without · last run 61d ago

—+77% tokens0% turns50% of whole cases pass with skill (11/22)

Test case	Without → With	Effect	Δ tokens	Δ turns
case-12	✗→✓	▲ Improved	—	—
case-14	✗→✓	▲ Improved	—	—
case-17	✗→✓	▲ Improved	—	—
case-08	✗→✓	▲ Improved	—	—
case-19	✗→✓	▲ Improved	—	—

Showing 5 of 22 cases

SkillSafety

✓ 3 of 3 passed

Code scan15 of 15 checks clean

0 critical · 0 warning · 0 info — scanner v4 — 7/30/2026

live_secretremote_code_executionreverse_shelldata_exfiltrationssrf_metadataagent_snoopinganti_refusaldestructive_commandsobfuscated_unicodeunicode_homoglyphopaque_blobsuspicious_urltool_overreachtrigger_abuseprompt_injection_phrasing

IntentSafe

LLM judge · does the skill do what it claims

ContentClean

LLM judge · policy & harmful-content review

Source

Imported

sickn33 / antigravity-awesome-skills

skills/agent-orchestrator/SKILL.md

View on GitHub ↗

License MITImported 8/2/2026Version v1Bundled 6 files · scripts

Skill contents

scripts/

references/

SKILL.md

Agent Orchestrator

Overview

Meta-skill que orquestra todos os agentes do ecossistema. Scan automatico de skills, match por capacidades, coordenacao de workflows multi-skill e registry management.

When to Use This Skill

When you need specialized assistance with this domain

Do Not Use This Skill When

The task is unrelated to agent orchestrator
A simpler, more specific tool can handle the request
The user needs general-purpose assistance without domain expertise

How It Works

Meta-skill que funciona como camada central de decisao e coordenacao para todo o ecossistema de skills. Faz varredura automatica, identifica agentes relevantes e orquestra multiplos skills para tarefas complexas.

Principio: Zero Intervencao Manual

SEMPRE faz varredura antes de processar qualquer solicitacao
Novas skills sao auto-detectadas e incluidas ao criar SKILL.md em qualquer subpasta
Skills removidas sao auto-excluidas do registry
Nenhum comando manual e necessario para registrar novas skills

Workflow Obrigatorio (Toda Solicitacao)

Execute estes passos ANTES de processar qualquer request do usuario. Os scripts usam paths relativos automaticamente - funciona de qualquer diretorio.

Passo 1: Auto-Discovery (Varredura)

bash
python agent-orchestrator/scripts/scan_registry.py

Ultra-rapido (<100ms) via cache de hashes MD5. So re-processa arquivos alterados. Retorna JSON com resumo de todos os skills encontrados.

Passo 2: Match De Skills

bash
python agent-orchestrator/scripts/match_skills.py "<solicitacao do usuario>"

Retorna JSON com skills ranqueadas por relevancia. Interpretar o resultado:

| Resultado | Acao | |:-----------------------|:--------------------------------------------------------| | matched: 0 | Nenhum skill relevante. Operar normalmente sem skills. | | matched: 1 | Um skill relevante. Carregar seu SKILL.md e seguir. | | matched: 2+ | Multiplos skills. Executar Passo 3 (orquestracao). |

Passo 3: Orquestracao (Se Matched >= 2)

bash
python agent-orchestrator/scripts/orchestrate.py --skills skill1,skill2 --query "<solicitacao>"

Retorna plano de execucao com padrao, ordem dos steps e data flow entre skills.

Passo Rapido (Atalho)

Para queries simples, os passos 1+2 podem ser combinados em sequencia:

bash
python agent-orchestrator/scripts/scan_registry.py && python agent-orchestrator/scripts/match_skills.py "<solicitacao>"

Skill Registry

O registry vive em:

agent-orchestrator/data/registry.json

Locais De Busca

O scanner procura SKILL.md em:

.claude/skills/*/ (skills registradas no Claude Code)
*/ (skills standalone no top-level)
*/*\ (skills em subpastas, ate profundidade 3)

Metadata Por Skill

Cada entrada no registry contem:

| Campo | Descricao | |:---------------|:---------------------------------------------------| | name | Nome da skill (do frontmatter YAML) | | description | Descricao completa (triggers inclusos) | | location | Caminho absoluto do diretorio | | skill_md | Caminho absoluto do SKILL.md | | registered | Se esta em .claude/skills/ (true/false) | | capabilities | Tags de capacidade (auto-extraidas + explicitas) | | triggers | Keywords de ativacao extraidas da description | | language | Linguagem principal (python/nodejs/bash/none) | | status | active / incomplete / missing |

Comandos Do Registry

bash

## Scan Rapido (Usa Cache De Hashes)

python agent-orchestrator/scripts/scan_registry.py

## Tabela De Status Detalhada

python agent-orchestrator/scripts/scan_registry.py --status

## Re-Scan Completo (Ignora Cache)

python agent-orchestrator/scripts/scan_registry.py --force

Algoritmo De Matching

Para cada solicitacao, o matcher pontua skills usando:

| Criterio | Pontos | Exemplo | |:-----------------------------|:-------|:--------------------------------------| | Nome do skill na query | +15 | "use web-scraper" -> web-scraper | | Keyword trigger exata | +10 | "scrape" -> web-scraper | | Categoria de capacidade | +5 | data-extraction -> web-scraper | | Sobreposicao de palavras | +1 | Palavras da query na description | | Boost de projeto | +20 | Skill atribuida ao projeto ativo |

Threshold minimo: 5 pontos. Skills abaixo disso sao ignoradas.

Match Com Projeto

bash
python agent-orchestrator/scripts/match_skills.py --project meu-projeto "query aqui"

Skills atribuidas ao projeto recebem +20 de boost automatico.

Padroes De Orquestracao

Quando multiplos skills sao relevantes, o orchestrator classifica o padrao:

1. Pipeline Sequencial

Skills formam uma cadeia onde o output de uma alimenta a proxima.

Quando: Mix de skills "produtoras" (data-extraction, government-data) e "consumidoras" (messaging, social-media).

Exemplo: web-scraper coleta precos -> whatsapp-cloud-api envia alerta

user_query -> web-scraper -> whatsapp-cloud-api -> result

2. Execucao Paralela

Skills trabalham independentemente em aspectos diferentes da solicitacao.

Quando: Todas as skills tem o mesmo papel (todas produtoras ou todas consumidoras).

Exemplo: instagram publica post + whatsapp envia notificacao (ambos recebem o mesmo conteudo)

user_query -> [instagram, whatsapp-cloud-api] -> aggregated_result

3. Primario + Suporte

Uma skill principal lidera; outras fornecem dados de apoio.

Quando: Uma skill tem score muito superior as demais (>= 2x).

Exemplo: whatsapp-cloud-api envia mensagem (primario) + web-scraper fornece dados (suporte)

user_query -> whatsapp-cloud-api (primary) + web-scraper (support) -> result

Detalhes Em `References/Orchestration-Patterns.Md`

Gerenciamento De Projetos

Atribuir skills a projetos permite boost de relevancia e contexto persistente.

Arquivo De Projetos

agent-orchestrator/data/projects.json

Operacoes

Criar projeto: Adicionar entrada ao projects.json:

json
{
  "name": "nome-do-projeto",
  "created_at": "2026-02-25T12:00:00",
  "skills": ["web-scraper", "whatsapp-cloud-api"],
  "description": "Descricao do projeto"
}

Adicionar skill a projeto: Atualizar o array skills do projeto.

Remover skill de projeto: Remover do array skills.

Consultar skills do projeto: Ler o projects.json e listar skills atribuidas.

Adicionando Novas Skills

Para adicionar uma nova skill ao ecossistema:

Criar uma pasta em qualquer lugar sob skills root:
Criar um SKILL.md com frontmatter YAML:

yaml
---
name: minha-nova-skill
description: "Descricao com keywords de ativacao..."
---

## Documentacao Da Skill

Pronto! O auto-discovery detecta automaticamente na proxima solicitacao.

Opcionalmente, para discovery nativo do Claude Code:

Copiar o SKILL.md para .claude/skills/<nome>/SKILL.md

Tags De Capacidade Explicitas (Opcional)

Adicionar ao frontmatter para matching mais preciso:

yaml
capabilities: [data-extraction, web-automation]

Ver Status De Todos Os Skills

bash
python agent-orchestrator/scripts/scan_registry.py --status

Interpretar Status

| Status | Significado | |:-----------|:---------------------------------------------------| | active | SKILL.md com name + description presentes | | incomplete | SKILL.md existe mas falta name ou description | | missing | Diretorio existe mas sem SKILL.md |

Skills Atuais Do Ecossistema

| Skill | Capacidades | Status | |:-------------------|:--------------------------------------|:--------| | web-scraper | data-extraction, web-automation | active | | junta-leiloeiros | government-data, data-extraction | active | | whatsapp-cloud-api | messaging, api-integration | active | | instagram | social-media, api-integration | partial |

Esta tabela e atualizada automaticamente via scan_registry.py --status.

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

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

Related Skills

multi-advisor - Complementary skill for enhanced analysis
task-intelligence - Complementary skill for enhanced analysis

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.

Illustrative Want to see what agent-orchestrator would put in front of your model? Preview the rendered body and check its trigger phrases — no LLM call, no signup.

Latest benchmark · publisher runVerified

7/28/2026, 15:13 UTC · 22 cases

Measured on 19 comparable cases — below the 22 needed to publish a lift, so this result is shown here but not on the registry card or leaderboard.

Lift

+50%

50% vs 0%

Agent turns

1.0 vs 1.0

Tokens

+77%

3,013.68 vs 1,699.79

fail → pass · 11fail → fail · 11

Per-case results (22)

Case	Status	Duration (ms)			Turns			Tokens			Tool calls
Case	Status	Without	With	Δ	Without	With	Δ	Without	With	Δ	Without	With	Δ
case-12 When matching skills for a user request, the top skill scores 24 points while the secondary relevant skill scores 10 points. Which orchestration pattern applies when one skill's relevance score is at least double the other?	fail→pass	—	—	—	—	—	—	—	—	—	—	—	—
case-05 I'm resolving a Git merge conflict in `data_loader.py` where HEAD changed a dictionary key name and feature branch changed the function signature. How should I resolve this conflict cleanly?	fail→fail	—	—	—	—	—	—	—	—	—	—	—	—
case-14 I am adding a project definition to the ecosystem configuration. In which file path must this project entry be registered, and what JSON array field tracks its associated skills?	fail→pass	—	—	—	—	—	—	—	—	—	—	—	—
case-17 A repository subdirectory has a `SKILL.md` file, but the YAML frontmatter lacks either a `name` or `description` field. What health status is logged for this skill?	fail→pass	—	—	—	—	—	—	—	—	—	—	—	—
case-03 We need to process automated user engagement for our 'campaign-2026' project. Run a targeted skill search incorporating this project context for published content and direct messaging, then present the matched skill results along with the recommended execution arrangement.	fail→fail	—	—	—	—	—	—	—	—	—	—	—	—
case-13 Where does the automatic registry scanner search for `SKILL.md` files across the repository, and up to what maximum folder depth in subdirectories does it scan?	fail→fail	—	—	—	—	—	—	—	—	—	—	—	—
case-15 Where is the compiled ecosystem registry database stored relative to the agent orchestrator skill directory?	fail→fail	—	—	—	—	—	—	—	—	—	—	—	—
case-20 How can a skill author explicitly declare capability tags in the frontmatter of `SKILL.md` to enhance matching precision beyond automated description parsing?	fail→fail	—	—	—	—	—	—	—	—	—	—	—	—
case-22 In the orchestrator's matching algorithm, how many points are awarded for general word overlap between the user query and a skill's description text?	fail→fail	—	—	—	—	—	—	—	—	—	—	—	—
case-11 We need to execute a workflow where two skills with identical roles (both social-media consumer skills) process the exact same input broadcast text simultaneously. Which orchestration pattern should be selected?	fail→fail	—	—	—	—	—	—	—	—	—	—	—	—
case-06 I need to set up a Linux cron job that runs every weekday at 6:30 AM to compress log files in `/var/log/app/`. What is the crontab line and bash command?	fail→fail	—	—	—	—	—	—	—	—	—	—	—	—
case-08 When evaluating candidate skills for query processing with active project association, how many additional points are added to a skill's match score if it is assigned to the specified project?	fail→pass	—	—	—	—	—	—	—	—	—	—	—	—
case-02 Please audit all skill directories across the workspace and generate a full inventory report. The output should display every detected skill alongside its metadata, health status, and assigned capability keywords.	fail→fail	—	—	—	—	—	—	—	—	—	—	—	—
case-19 When 2 or more skills match a query, what script is invoked to generate the execution plan, and what CLI parameters are required to pass the selected skills and prompt?	fail→pass	—	—	—	—	—	—	—	—	—	—	—	—
case-18 What single bash command sequence combines instant cache-based registry discovery and user query skill matching without generating an execution plan?	fail→pass	—	—	—	—	—	—	—	—	—	—	—	—
case-09 I just updated several `SKILL.md` frontmatter files manually, but the discovery output still returns cached MD5 metadata. Which CLI flag must be passed to the registry scanner script to bypass MD5 cache and force a complete rescan?	fail→pass	—	—	—	—	—	—	—	—	—	—	—	—
case-16 During registry scanning, a skill directory is found that contains code files but lacks a `SKILL.md` file entirely. What health status value does the scanner assign to this directory in the registry?	fail→pass	—	—	—	—	—	—	—	—	—	—	—	—
case-21 If a user query explicitly mentions the exact name of a skill (e.g. 'run web-scraper to check prices'), how many bonus points does the matching algorithm assign for this criterion?	fail→pass	—	—	—	—	—	—	—	—	—	—	—	—
case-01 I'm looking to automate a task that scrapes online auction listings and sends notifications to my chat app. Please check our ecosystem's available skills, match them to this query, and output a detailed execution plan specifying which tools to run and how data should flow between them.	fail→pass	—	—	—	—	—	—	—	—	—	—	—	—
case-04 I have a Python script `parser.py` in my workspace that has high cyclomatic complexity and duplicated loop structures. Can you refactor the code to improve readability and performance?	fail→fail	—	—	—	—	—	—	—	—	—	—	—	—
case-07 We are tuning our skill recommendation engine. A query contains an exact keyword trigger match for a skill, but no project assignment or exact skill name match. What point score does this match yield, and does it exceed the minimum threshold required for inclusion?	fail→pass	—	—	—	—	—	—	—	—	—	—	—	—
case-10 We have a workflow that combines a data producer skill (category: government-data) and a data consumer skill (category: social-media). What orchestration classification pattern should be assigned to structure their execution flow?	fail→fail	—	—	—	—	—	—	—	—	—	—	—	—

These cases were also screened by the skill’s intent / safety pass.See the Trust review ↗Reproduce this benchmark in Colab ↗

How this skill was measured

DecimalAI ran this skill against gemini-3.6-flash twice over the same eval suite — once with the skill loaded and once without — and compared the two runs case by case. 22 cases were attempted, and 19 counted toward the lift figure. The other 3 produced results that are not comparable between the two arms, so they are excluded from the headline rather than averaged into it. The headline lift of +50 percentage points is the difference between those two pass rates over the 19 comparable cases.

Model measured: gemini-3.6-flash
Graded by: gemini-3.6-flash
Grading method: judged
Verification: verified
Pass rate without the skill: 0%
Pass rate with the skill: 50%
Cases attempted: 22
Cases counted toward lift: 19
Cases that regressed: 0
Skill version measured: v1
Run completed: 7/28/2026, 15:13 UTC

The per-case answers from this run were removed by the retention sweep, so the case table below shows the verdicts without the text either arm produced. The counts above were recorded at the time and are unaffected. Answers are now kept for 180 days.

SkillScore blends 4 signals1 of 4 complete

BenchmarkPass rate WITH skill on a verified run50

Live evalNeeds ≥10 evaluated traces in 30 days

AI ratingNeeds ≥10 rated traces

AdoptionNeeds ≥10 serves across ≥2 orgs in 30 days

Backed by 1 of 4 signals — each added signal makes the score more robust.

Verified on gemini-3.6-flash · re-tested 2 months ago

Other measured skills in the registry, with their headline benchmark lift.

Ready to supercharge your AI agents?

Agent Orchestrator

SkillSafety

Source

Agent Orchestrator

Overview

When to Use This Skill

Do Not Use This Skill When

How It Works

Principio: Zero Intervencao Manual

Workflow Obrigatorio (Toda Solicitacao)

Passo 1: Auto-Discovery (Varredura)

Passo 2: Match De Skills

Passo 3: Orquestracao (Se Matched >= 2)

Passo Rapido (Atalho)

Skill Registry

Locais De Busca

Metadata Por Skill

Comandos Do Registry

Algoritmo De Matching

Match Com Projeto

Padroes De Orquestracao

1. Pipeline Sequencial

2. Execucao Paralela

3. Primario + Suporte

Detalhes Em References/Orchestration-Patterns.Md

Gerenciamento De Projetos

Arquivo De Projetos

Operacoes

Adicionando Novas Skills

Tags De Capacidade Explicitas (Opcional)

Ver Status De Todos Os Skills

Interpretar Status

Skills Atuais Do Ecossistema

Best Practices

Common Pitfalls

Related Skills

Limitations

How this skill was measured

Related skills

Detalhes Em `References/Orchestration-Patterns.Md`