Skip to main content
ClaudeWave
Skill3.5k estrellas del repoactualizado today

detect-framework

The detect-framework Claude Code skill scans Python source files for import statements to identify which agent framework a user's existing code uses, then recommends the appropriate Omnigent executor type. Use this when integrating existing Python agent code into Omnigent to automatically configure the correct runtime environment for Claude SDK, OpenAI Agents SDK, or other supported frameworks.

Instalar en Claude Code
Copiar
git clone --depth 1 https://github.com/omnigent-ai/omnigent /tmp/detect-framework && cp -r /tmp/detect-framework/omnigent/onboarding/agent/skills/detect-framework ~/.claude/skills/detect-framework
Después abre una sesión nueva de Claude Code; el skill carga automáticamente.

SKILL.md

# Framework Detection

When the user has existing Python code they want to integrate into
Omnigent, detect the framework from import statements and recommend
the appropriate executor type.

## Detection Procedure

1. Ask the user for the path to their agent code (or look for Python
   files in the current directory if filesystem access is enabled).

2. Scan Python files for import patterns. Check in this priority order:

| Import pattern | Framework | Executor type |
|---------------|-----------|---------------|
| `import anthropic` or `from anthropic` + agent patterns (e.g. `Agent`, `tool`, system prompt setup) | Claude SDK | `claude_sdk` |
| `import openai` or `from openai` + agents patterns (e.g. `Agent`, `Runner`, `function_tool`) | OpenAI Agents SDK | `agents_sdk` |
| `from langgraph` or `import langgraph` | LangGraph | Not natively supported yet |
| `from deepagents` or `import deepagents` | DeepAgents | Not natively supported yet |
| `from langchain` or `import langchain` | LangChain | Not natively supported yet |
| `from crewai` or `import crewai` | CrewAI | Not natively supported yet |
| `from autogen` or `import autogen` | AutoGen | Not natively supported yet |
| None of the above | Unknown | Not natively supported yet |

3. Report what you found and recommend the executor type.

## What to generate for each executor type

### `llm` (default — no existing code)

Generate a standard agent directory:
```yaml
executor:
  type: llm  # or omit entirely (llm is the default)
```

### `claude_sdk`

The user's Claude SDK code runs directly. Generate config that points
to their entry module:
```yaml
executor:
  type: claude_sdk
```

### `agents_sdk`

The user's OpenAI Agents SDK code runs directly:
```yaml
executor:
  type: agents_sdk
```

## Asking about unsupported frameworks

If the user's framework is not natively supported, let them know:
- Explain that Omnigent does not currently have a supported executor for that framework.
- Offer to show them a pre-filled GitHub issue URL requesting first-class
  support for their framework.
- If they want to start fresh instead, recommend generating a standard `llm` agent.
- The issue URL format: `https://github.com/dbczumar/omnigent/issues/new?title=...&body=...`
antigravity-sdk-e2e-devSkill

Spin up a live local Omnigent server and exercise the Antigravity (Gemini) SDK harness end-to-end — build antigravity agents, run real turns, smoke-test, and bug-bash. Load when developing, testing, or debugging the antigravity harness (omnigent/inner/antigravity_executor.py, antigravity_harness.py, omnigent/onboarding/antigravity_auth.py) or its auth / model / tool-bridge behavior.

cursor-sdk-e2e-devSkill

Spin up a live local Omnigent server and exercise the Cursor SDK harness end-to-end — build cursor agents, run real turns, smoke-test, and bug-bash. Load when developing, testing, or debugging the cursor harness (omnigent/inner/cursor_executor.py, cursor_harness.py, cursor_auth.py) or its auth / model / tool-bridge behavior.

deploy-docker-composeSkill

Run the Omnigent server as a Docker compose stack (server + Postgres) on any Docker host — your laptop, a VPS, EC2 by hand, or as the base layer of any container-platform deploy. Invoke when the user wants to build the image, bring up the compose stack, debug the stack on a host they already have, or extend the stack for a new platform.

debateSkill

Have the Claude and GPT partners critique each other's answers across a configurable number of rounds (default 1) before converging on a synthesis. Use when the user wants the two perspectives stress-tested against each other, not just shown side by side.

cross-reviewSkill

Verify an implementer's diff with an INDEPENDENT, different-vendor sub-agent (diff plus contract only); turn blocking issues into fix-tasks and loop until clean.

fanoutSkill

Run independent subtasks in parallel — one git worktree and one implementation sub-agent per task, each opening its own PR — then cross-review every PR. polly never merges; the human does.

investigateSkill

Delegate read-only investigation, debugging, audit, search, or code-understanding tasks to sub-agents; synthesize only from their structured reports.

build-omnigentSkill

Patterns and templates for generating valid Omnigent agent directories. Load when ready to create files.