Loading...
Loading...
Found 9 Skills
Install and update manually hosted skills in this repository, keeping canonical skill sources under `skills/`, installed output under `.agents/skills`, and `skills-lock.json` in sync. Use when asked to add, refresh, verify, or dogfood repo-local skills for this shared agent setup.
With 'Dao' as the overall controller, consolidate capabilities such as planning, game design, game visual design, general design, review, implementation, summary, and repository maintenance into a unified entry, and call internal modules as needed.
Create and manage AI-powered GitHub workflows that autonomously maintain repositories, review code, update docs, and handle developer tasks.
For answering, using, and debugging @wot-ui/cli. Keywords: wot, @wot-ui/cli, CLI, MCP, doctor, usage, lint, list, info, doc, demo, token, changelog, extract, wot mcp. Applicable for command queries, parameter explanations, MCP integration, local debugging, data extraction, and open-wot repository maintenance.
Maintain the local OpenCode mirror for self-reference
Create an annotated Git tag to mark a project milestone, documenting achievements and next-phase plans. Use when completing a phase, releasing a version, or marking a research checkpoint with a structured summary.
Inspect or run the manual maintenance workflow. Uses explicitly configured repository checks, applies safe auto-fixes, and archives successful maintenance changes.
Normalizes GitHub issue and PR titles by removing any bracketed [NemoClaw] tag case-insensitively, even when the tag appears later in the title. Use when cleaning issue tags, bulk-renaming titles, or normalizing repo title hygiene.
Log genuine, recurring repository friction to .agents/PAPERCUTS.md — confusing setup, a flaky repo command or script, a misleading in-repo error, stale generated files, or a non-obvious gotcha that will cost the next contributor time. Also use to review, deduplicate, and resolve existing entries. Gate hard before logging: only friction the repository itself can fix counts. Never log the agent's own sandbox/permission errors, shell-scripting mistakes, transient flakiness, or third-party tool quirks the repo can't change.