Use when manage multiple local CLI agents via tmux sessions (start/stop/monitor/assign) with cron-friendly scheduling.
中文简介正在准备中。当前显示原文说明。
Quality-assure integrated tdmcp features: run the four PR gates + recipe/bridge tests, cross-boundary coherence checks (tool schema↔CLI↔docs↔registry, operator↔createable, bridge↔client), and live TouchDesigner validation (preview + post-cook error check) when the bridge is reachable. Use when validating/QA-ing/testing tdmcp tools, checking a feature actually cooks in TD, verifying CLI matches a tool, or gating a release.
中文简介正在准备中。当前显示原文说明。
查看安装方法安装前可以查看交给 AI 代理的指令内容。
Most defects here live at boundaries, and a tool that returns success can still cook to errors or a black frame. So: read both sides of every boundary together, and check errors after the network cooks, not just the create_* return flag. Run incrementally — validate each feature as it lands so an early boundary bug doesn't propagate.
npm run typecheck · npm run build · npm test./node_modules/.bin/biome check . (NOT npm run lint — RTK proxy gives a false ESLint parse error)npm run validate:recipes · npm run test:bridge (python3 -m unittest discover -s td/tests)| Boundary | Left (producer) | Right (consumer) | Compare |
|---|---|---|---|
| Tool ↔ CLI | tool's Zod inputSchema | command in src/cli/agent.ts | every param reachable from CLI; types/defaults align; name maps to the right handler |
| Tool ↔ registry | register… export | layer*/index.ts + tools/index.ts | actually registered + aggregated, not just written |
| Tool ↔ docs | live registry | generated docs/reference/tools.md | regenerates and includes the new tool |
…Impl ↔ test | real return / isError shape | msw test assertions | test exercises the actual shape, not a cast-away generic |
| Code ↔ TD | operator types created | what this build can create | optype exists + is createable (dir(td) suffix-match over-counts; ~22 names not createable; KB lags ~14 ops) |
| Bridge ↔ client | td/ endpoint/payload | touchDesignerClient.ts + validators.ts envelope | response shape matches the Zod validator |
Policy: offline gates always; live when available. Call get_td_info first.
get_preview, and check get_td_node_errors after it cooks.Live gotchas to rule out before declaring a bug:
gain (it's brightness1); no cross-container wires (Select TOP).op('/').time.play is false — check it before concluding a reactive chain is dead.mcp__tdmcp__* runs the old build until restarted; editing td/ doesn't reload the running bridge (reload_bridge / restart) — suspect stale modules before "fixing" correct code.out vec4 fragColor + a self-supplied time uniform.A report at _workspace/04_qa_<feature|batch>.md with three explicit buckets — PASS, FAIL (file:line + concrete fix + owning agent), UNVERIFIED (what wasn't checked + why, e.g. bridge offline). Never silently skip a check; list it as UNVERIFIED.
td-builder for handler/schema/test, td-integrator for wiring/CLI/docs); boundary bugs go to both. Re-validate after each fix.vitest run <yourfile>).还没有评价。欢迎分享你的使用感受。
无需登录即可发表。欢迎分享使用感受、提问,或说明在哪些环境下无法运行。
还没有评论。来写第一条吧。
Use when manage multiple local CLI agents via tmux sessions (start/stop/monitor/assign) with cron-friendly scheduling.
中文简介正在准备中。当前显示原文说明。
Use when a hybrid memory system that provides persistent, searchable knowledge management for AI agents (Architecture, Patterns, Decisions).
中文简介正在准备中。当前显示原文说明。
Reference for how BDB structures autonomous software engineering work — the seven-node dispatcher graph (Architect, TechLead, UI/UX, Engineering, Media/EventTech, Reviewer, Shipping) that /startcycle-graph actually runs. Use when you need the high-level lifecycle framing without inventing your own process.
中文简介正在准备中。当前显示原文说明。
Tools are how AI agents interact with the world. A well-designed tool is the difference between an agent that works and one that hallucinates, fails silently, or costs 10x more tokens than necessary. This skill covers tool design from schema to error handling.
中文简介正在准备中。当前显示原文说明。
Harness patterns for coding agents — memory, permissions, context engineering, delegation, skills, hooks, bootstrap.
中文简介正在准备中。当前显示原文说明。
agenttrail: live map of a multi-agent build in the browser: which plan component is being worked on, by which agent or harness, what is done and what is stuck. Use when a multi-agent pipeline starts (/startcycle, /startcycle-graph, /teamwork-preview) or after a plan-canvas approve, when the user asks to see what the agents are doing ("live map", "build board", "who is running now"), or by yourself whenever a multi-agent run is under way — no user prompt needed.
中文简介正在准备中。当前显示原文说明。