ephes

Run a bounded, fail-closed Claude Code review gate over the current git worktree with a configurable Claude model and strict read-only isolation. Use for fresh-context different-family reviews before commit, including requests for Opus, Fable, Sonnet, or an explicitly selected Claude model; drive fix and re-review rounds until the configured reviewer returns CLEAN.

Use before committing an implementation slice when a configurable different-family reviewer should inspect the slice, or when coordinating up to three fix/re-review cycles with Claude, Codex, or Pi. Claude reviews delegate to the supervised claude-review-loop harness.

Use when you want a fresh-context code-review gate before committing — runs Pi only with the approved OpenAI Codex GPT-5.6 Sol model at high reasoning over the current git diff in a bounded, observable loop, and only proceeds when Pi returns CLEAN. Never falls back to Claude/Anthropic, local models, OpenRouter, or another provider. Drives review → fix → re-review up to a round cap. Triggers: "have pi review this", "pi review before commit", "run the pi review loop".

Use before committing an implementation slice when a configurable different-family reviewer should inspect the slice, or when coordinating up to three fix/re-review cycles with Claude, Codex, or Pi. Claude reviews delegate to the supervised claude-review-loop harness.

Use when the user asks for a compact goal prompt, goal condition, create_goal objective, continuation objective, or second-agent goal statement, especially when the destination has a strict character limit such as 4000 characters. Generate a concise, context-specific goal condition from the current worktree, session context, and relevant planning docs without producing a full implementation or review handoff.

Legacy compatibility alias for claude-review-loop. Use only when an existing workflow explicitly invokes opus-review-loop; delegate the review to the canonical configurable Claude gate with the Opus model.

Consume captured pipy parity-loop lessons and materialize each into a gated edit to the skills/docs/tests/harness. Applies only when the working directory is the pipy repo (~/projects/pipy).

Drive one pi-mono parity gap end to end in the pipy repo (select gap, plan, different-family review, implement, docs, review until CLEAN, commit). Applies only when the working directory is the pipy repo (~/projects/pipy).

Use this skill when a user wants to add an Electron shell around an existing Django project, especially from a different repository. It provides the workflow, guardrails, and key integration points for adapting a server-rendered Django app into a local desktop app with a bundled Python runtime.

Use this experimental workflow when the one-shot wrap prompt is too broad for a smaller local model. It splits the work into a deterministic scaffold step, a focused Electron adaptation step, a focused Django integration step, and a final fix-from-failures step.

Use to consume captured parity-loop lessons and materialize them into gated edits to the skills/docs/tests/harness in this repo. Trigger phrases — "parity improve", "drain lessons", "apply parity lessons".

Use when driving one pi-mono parity gap in this repo end to end (select gap → plan → different-family plan review → impl plan → implement → docs → code-review loop until CLEAN → commit). Triggers: "parity loop", "next parity gap", "close a pi-mono gap".

Use Playwright for browser automation and end-to-end testing. Invoke when writing e2e tests, browser automation, or testing web UI interactions.