Loading...
Loading...
Found 7 Skills
Use when acting as Grunk - reads specs from beads, plans, implements, commits, tags pr-ready. Merged TL+Engineer. Works in loop mode or interactive mode.
Defines command mode policy. Non-interactive is default; interactive is opt-in.
Set up a new autoresearch experiment interactively. Collects domain, target file, eval command, metric, direction, and evaluator.
Story brainstorming capture — minimal notes that preserve creative freedom. Use when exploring narrative ideas, discussing characters, planning chapters, or thinking through story possibilities. Supports interactive conversation and autonomous report mode for fan-out exploration.
Audit a rules document (SKILL.md, CLAUDE.md, AGENTS.md, or convention doc) and propose updates that leverage what the current Claude version knows natively. Classifies each rule as Keep / Sharpen / Add-rationale / Redundant / Stale, proposes Missing rules from the shared quality baseline, and applies all proposed changes only on one explicit confirmation. A guided --interactive mode replaces the batch confirmation with per-rule decisions.
Edit existing MTHDS bundles (.mthds files). Use when user says "change this pipe", "update the prompt", "rename this concept", "add a step", "remove this pipe", "modify the workflow", "modify the method", "refactor this pipeline", or wants any modification to an existing .mthds file. Supports automatic mode for clear changes and interactive mode for complex modifications.
Use when the user wants a short animated explainer video. Trigger phrases include "animated explainer", "make an explainer", "explainer video about X", "30-second video about Y", "90-second video explaining Z", "how X works as a video", "explain X in a short video".