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

investigate

The `investigate` skill delegates read-only tasks such as debugging, auditing, code understanding, and architecture analysis to specialized sub-agents while maintaining an orchestrator role that synthesizes only their structured reports. Use it when you need to decompose complex repository questions into bounded investigation tasks, dispatch them to appropriate workers with specific evidence requests, and aggregate findings without directly inspecting files or logs yourself.

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

SKILL.md

# investigate — delegated read-only work

Use for any read-only task: investigation, debugging, audit, search, code
understanding, architecture comparison, failure analysis, or answering a
repository-specific technical question.

## Procedure
1. Decompose the question into one or more bounded investigation tasks. Prefer
   two independent lenses for ambiguous or high-stakes questions.
2. Dispatch each task to `claude_code`, `codex`, or `pi`:
   `sys_session_send(agent="claude_code"|"codex"|"pi",
   title="explore-<task_slug>", args={purpose: "explore", input: "<question +
   exact scope + evidence requested>"})`. Use a task-based title such as
   `explore-ci-flake`, never the raw vendor name. Use `purpose: "search"` only
   when the task is primarily external/document search. Prefer `pi` when a
   third lens or a non-Claude/GPT model is wanted. Any worker takes an optional
   `args.model` (`sys_list_models` shows what each worker can run; an invalid
   model/worker combination fails loud at dispatch, and `model` only applies on
   the dispatch that CREATES the session — a send that continues an existing
   title rejects it).
   Tell the worker to edit nothing and return file,
   command, URL, or line evidence. Emit these `sys_session_send` calls in the
   SAME turn — do not end a turn having only said you will dispatch.
3. End your turn AFTER the dispatch tool calls are in flight (never before).
   Do not inspect files, logs, terminals, docs, or connector output yourself
   while the workers run.
4. When workers finish, collect their completion results with
   `sys_read_inbox`. Synthesize only from those inbox-delivered reports. Use
   `sys_session_get_history` only to debug an empty or unclear worker result; if
   reports conflict or are incomplete, dispatch a follow-up `explore` task
   rather than resolving the conflict from your own direct inspection.
5. If the investigation uncovers required code changes, switch to `fanout` /
   `cross-review`: dispatch an `implement` worker, then verify with the
   opposite-vendor `review` worker.

## Notes
- The orchestrator may use its own tools only to create task packets, maintain
  the registry, or check deterministic external status. It must not answer the
  user's substantive question from its own direct file reads, shell output,
  connector fetches, or terminal scrollback.
- Keep task scopes narrow enough that each worker can return a concise report
  with evidence. Broad investigations should be split into parallel subtasks.
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.

build-omnigentSkill

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

detect-frameworkSkill

Detect Python agent frameworks from code imports and map them to Omnigent executor types. Load when the user has existing agent code to integrate.