Skill Claude Code
Improve a canonical common-owned judge from reviewed rollout evidence, human labels, and leakage-safe calibration without bypassing the frozen router workflow.
Skill Claude Code
Mandatory pre-merge gate for every PR. Runs /code-review --fix at an effort level scaled to the PR's breadth, resolves every review comment (Cursor, Codex, humans), and verifies the diff complies with AGENTS.md. Use whenever the user says a PR is ready to merge, asks to merge, or invokes /ready-for-merge.
Skill Claude Code
Run the live Experiential build-to-serve path as an unattended automation. Fits the pinned terminal-tasks trace export through the CLI, calibrates the judge non-interactively, fits a router, verifies exact replay, and serves the frozen policy on loopback. Use when asked to test the build path, verify cloud setup, or…
Skill Claude Code
End-to-end happy-path test of the Experiential local gateway, covering interactive first-run setup via the exp run TUI, the served OpenAI-compatible routes, usage accounting, restart persistence, and integration with an external OpenAI-compatible client such as opencode. Use when asked to test, validate, or demo the…
Skill Claude Code
Make a pro-level video (launch film, manifesto/brand film, product demo, feature announcement, explainer, social cut, a frame-locked remake of a reference, or a style-matched edit like a reference (sigma, hype or founder edit) with the user's own footage) entirely with code plus optional TTS, AI b-roll and archival…
At most 3 mods per repository are shown here, and a mod shipped inside a plugin is left to that plugin's page — the rest are on their repository pages: