菜单
Build sessions_spawn command payloads from JSON profiles. Use when you want reusable subagent profiles (model/thinking/timeout/cleanup/agentId/label) and command-ready JSON without executing spawn.
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
Continuity, durable memory, state tracking, journal writes, identity diffs, and mood/current-state checks for Valentina/OpenClaw. Use for memory writes/search, emotion/state ticks, heartbeat state upkeep, journal synthesis, and preserving self-state across sessions.
Ingest pasted PC parts purchase/config text (Discord message receipts, bullet lists) into Notion DIY_PC tables (PCConfig, ストレージ, エンクロージャー, PCInput). Use when the user pastes raw purchase logs/spec notes and wants the AI to classify, enrich via web search, ask follow-up questions for unknowns, and then upsert rows into the correct Notion data sources using the 2025-09-03 data_sources API.
Read-only Calibre catalog lookup, ID viewing, and one-book analysis comments workflow over a running Content server. Use for list/search/id viewing, including ID requests without edit verbs. Never for title/authors/tags/series/series_index metadata edits.
Primary skill for Calibre metadata edits over a running Content server. Use only when the user explicitly requests changing/editing/fixing title, authors, series, series_index, tags, publisher, pubdate, languages, comments, or analysis metadata. Never for read-only lookups.
Use when Home Assistant OS needs SSH-based maintenance that cannot be completed cleanly through the Home Assistant API alone. Prefer API-first investigation for states, history, logbook, and routine automation checks; use this skill when direct filesystem access, YAML edits, custom_components inspection, HAOS shell troubleshooting, or interactive `ha` CLI work is required. Distinguish one-shot SSH commands from interactive SSH sessions: `ha` commands such as `ha core logs` may work only inside an interactive PTY-backed SSH session.
| name | subagent-spawn-command-builder |
| description | Build sessions_spawn command payloads from JSON profiles. Use when you want reusable subagent profiles (model/thinking/timeout/cleanup/agentId/label) and command-ready JSON without executing spawn. |
Generate sessions_spawn payload JSON from profile config.
This skill does not execute sessions_spawn; it only builds payload/command JSON.
scripts/build_spawn_payload.mjsstate/build-log.jsonltask (required)label (optional)agentId (optional)model (optional)thinking (optional)runTimeoutSeconds (optional)cleanup (keep|delete, optional)cwd (optional) — working directory for the subagentmode (run|session, optional)Read the "Subagent Spawn Profiles" table in TOOLS.md for default values per profile. Pass values as explicit CLI arguments (--model, --thinking, --run-timeout-seconds, --cleanup). The --profile flag is now a logging label, not a lookup key for a config file.
skills/subagent-spawn-command-builder/scripts/build_spawn_payload.mjs \
--profile heartbeat \
--task "Analyze recent context and return a compact summary" \
--label heartbeat-test \
--model claude-sonnet-4-20250514 \
--thinking low \
--run-timeout-seconds 300 \
--cleanup delete
The script prints JSON directly usable for sessions_spawn.
All values come from explicit CLI arguments. --profile is a logging label only (not a config lookup key). Refer to the "Subagent Spawn Profiles" table in TOOLS.md for recommended defaults per profile.
task always comes from CLI --task.
Note: this builder is Node.js (.mjs) based. If generated tasks include Python execution steps, write commands with python3 (not python).
--profile (required)--task (required)--label--agent-id--model--thinking--run-timeout-seconds--cleanup keep|delete--cwd <path>--mode run|session