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

This is a fixture skill for `tests/e2e/test_codex_skills_filter_e2e.py`. The skill body itself does not matter — the test asserts on whether the SKILL name (`codex_e2e_xyz_count_b8d4e7`) appears in the agent's enumerated-skills response.

This is a fixture skill for `tests/e2e/test_codex_skills_filter_e2e.py`. The skill body itself does not matter — the test asserts on whether the SKILL name (`codex_e2e_xyz_greet_a3f9c2`) appears in the agent's enumerated-skills response.

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

Use ONLY for subtasks that are parallel-safe (no shared files, no ordering dependency).

This skill describes the **feature matrix** every Omnigent harness must consider. Use it when planning, reviewing, or implementing a new harness.

Turn a breaking change (an API rename, removed flag, changed default, or moved module) into concrete upgrade steps with before/after examples. Use when the user asks how to migrate, upgrade, or adapt to a breaking change.

Deep reference on Omnigent config format, executor types, skill/tool structure, and conventions. Load when you need to look up how the platform works.

Check the final diff's consumers, focused tests, evidence, and gaps.

Run Polly and OCR on a PR until all findings settle.

This is a fixture skill for `tests/e2e/test_pi_skills_filter_e2e.py`. The skill body itself does not matter — the test asserts on whether the SKILL name (`pi-e2e-xyz-count-d2f6e1`) appears in the agent's enumerated-skills response.

The `pi-native` harness wraps the **real Pi coding-agent TUI** (`@earendil-works/pi-coding-agent`, the `pi` CLI). Unlike the SDK harnesses (cursor / copilot / antigravity), it does **not** run in-process: `omnigent pi` ensures a host daemon, the daemon spawns a **runner** that launches `pi` inside a

Find the root cause, implement a focused fix, and prove behavior with targeted tests and recordings.

Emit the complete Resolve handoff with exact modes, outcomes, test evidence, and publication state.

Select the Resolve mode, recover its input, check the workspace, and discover existing fixes.

Audit a recovered repro patch, assertions, and behavioral baseline before authoring or reviewing.

Run the Omnigent load test and produce a results file explaining the latencies. Load when the user wants to load-test / stress-test / benchmark Omnigent under concurrency ("load test omnigent", "stress test the server", "how many hosts/sessions/turns can it handle", "load test real agent turns / conversations", "run a load test"). The test makes each simulated user a real omnigent host that creates host-bound sessions and drives real multi-turn conversations with a mocked LLM; it boots its own local stack (dev/loadtest/run.py). Gather inputs, run it, then read the generated summary.md and explain the latency distribution (avg/median/p95/p99, throughput, failures). NOT for single-request latency micro-benchmarks (that is dev/benchmarks/).

Drive Omnigent the way a user does and prove a behavior with recorded evidence, using an isolated server, runner, and mock model plus a feature map of every user entry point. Load before reproducing a user-facing bug, before claiming a fix works, or when reviewing whether a change covered every surface (session vs. new-session composer, terminal strip vs. agent terminal, all twelve native harnesses). Covers the web UI, native harness terminals, and the CLI.