菜单
Scaffold a new Tlamatini visual agent end-to-end across the 8 places the agent contract requires (script + config.yaml, view + url, migration, CSS gradient, 4 JS files, agentic_skill.md, README.md, lint).
用 Codex 或 Claude 帮你安装 复制这段 Prompt，粘贴到 Codex、Claude 或其他助手里，让它检查 Skill 页面并帮你完成安装。
基于 SOC 职业分类
| name | tlamatini-new-acp-agent |
| description | Scaffold a new Tlamatini visual agent end-to-end across the 8 places the agent contract requires (script + config.yaml, view + url, migration, CSS gradient, 4 JS files, agentic_skill.md, README.md, lint). |
| metadata | {"openclaw":{"emoji":"🧱"},"tlamatini":{"runtime":"in-process","requires_tools":["chat_agent_file_creator","chat_agent_executer","chat_agent_pythonxer"],"requires_mcps":["Files-Search"],"budget":{"max_iterations":30,"max_seconds":600,"max_tokens":80000},"permissions":{"filesystem":{"read":["Tlamatini/agent/**/*"],"write":["Tlamatini/agent/agents/${input.agent_name}/**/*","Tlamatini/agent/views.py","Tlamatini/agent/urls.py","Tlamatini/agent/static/agent/css/agentic_control_panel.css","Tlamatini/agent/static/agent/js/acp-*.js","Tlamatini/agent/migrations/*.py","Tlamatini/agent/agents/flowcreator/agentic_skill.md","README.md"]},"shell":["python -m ruff check Tlamatini/agent","npm run lint"],"network":"deny","db":["read","write-via-migrations-only"]},"inputs":[{"name":"agent_name","type":"string","required":true,"description":"snake_case folder name; display name derived as title-case"},{"name":"category","type":"enum","values":["control","routing","gates","action","crypto","utility","terminal"],"required":true},{"name":"gradient","type":"string","required":false,"description":"4 hex colors comma-separated (#aabbcc,...)"}],"outputs":[{"name":"files_changed","type":"array","required":true},{"name":"migration_id","type":"string","required":true},{"name":"lint_summary","type":"string","required":true}],"triggers":{"keywords":["new agent","add agent","scaffold agent","create acp agent"],"file_globs":["Tlamatini/agent/agents/**/*"]}}} |
Read Tlamatini/.agents/workflows/create_new_agent.md first. It is the
ground truth for the 8-step contract. This skill drives that procedure
end-to-end.
agent_name is snake_case ASCII; reject collisions with
existing agents in Tlamatini/agent/agents/.shoter.py boilerplate into the new directory; rename references.
Temp/Templates policy (2026-06-02): if the agent creates temp files, add
the module-top if (os.environ.get('TLAMATINI_TEMP') or '').strip(): … tempfile.tempdir = … guard (verbatim from executer.py — an if-block, not
a def, so ruff E402 stays clean); if it scaffolds a project/template dir
(firmware/engine style), default the parent to <app>/Templates
(TLAMATINI_TEMPLATES). See prompt.pmt Rules 15/16 + agent/path_guard.py.Agent row with the display name.agentic_control_panel.css and the
hover variant.agentic_skill.md and README.md (agent count, table,
classification, glossary, changelog, API table).python -m ruff check and npm run lint. Stop on any error and
report.Return:
{
"files_changed": ["..."],
"migration_id": "00NN_add_<agent_name>",
"lint_summary": "ruff: 0 errors; eslint: 0 errors"
}
Run the daily automated Tlamatini chat regression — drive a visible Chrome via Playwright, log into agent_page.html, ask up to 1000 curated safe questions one-by-one (Multi-Turn ON, ACPX/Ask-Execs/Exec-Report/Internet OFF), wait for and qualify each answer (heuristic + LLM judge on failures), then write a dated report + summary. Invoke when the user says "run the daily chat test", "test Tlamatini with the 1000 questions", "daily Tlamatini regression", or schedules this test.
Turn a natural-language objective into a downloadable .flw workflow by driving the FlowCreator engine (full 83-agent catalog), then emit a canvas-loadable .flw.
The authoritative, exhaustive end-to-end runbook for creating a BRAND-NEW Tlamatini workflow agent — every surface, in order, with 530+ numbered steps across 26 phases. Invoke whenever Angela says "create a new agent", "add an agent", "make a <X>er agent", "I want a new canvas agent", or asks to wire any new pool agent across backend + frontend + Multi-Turn + Parametrizer + FlowCreator + FlowHypervisor + watchdog + config dialog + demo prompts + Python tests + Playwright harness tests + docs + packaging. Covers naming, coloring, the inputs/outputs connector contract in agentic_control_panel.html, the Multi-Turn (wrapped chat-agent) tool, Exec Report, the configuration dialog, automated unit tests AND Playwright tests in Claude's harness. Pairs with tlamatini-agent-naming (casing) and the @-imported create_new_agent.md / create_new_mcp.md.
Build and edit in Roblox Studio via the Roblox Studio MCP the RIGHT way - preflight the Studio connection, do the whole build in a few big execute_luau scripts (not dozens of tiny calls), make REALISTIC terrain with the Terrain VOXEL api driven by Perlin noise (NEVER stacked Parts or concentric layers - those give ugly blocky stepped pyramids), poll generative jobs, check the console, and fail honestly. Invoke for ANY "in Roblox / Roblox Studio" request - terrain, mountains, parts, scripts, models, materials, assets.
The authoritative 8-step contract for scaffolding a NEW Tlamatini workflow agent end-to-end (backend script + config.yaml, connection-update view + URL, migration seeding the Agent row, CSS gradient, four JS files, agentic_skill.md, README.md, lint). READ THIS BEFORE adding or renaming any of the 83 visual agents, before touching `agent/agents/<name>/`, before writing a `00NN_add_<name>.py` migration, before adding a `.canvas-item.<x>-agent` rule, or before extending the `acp-*.js` classMap / connectors. Companion to the `tlamatini-new-acp-agent` skill (which drives the procedure) and to `tlamatini-agent-naming` (the naming-convention guard).
Turn a one-sentence objective into a downloadable .flw workflow that wires the right Tlamatini visual agents and connections.