{"id":"hivemind-goals-5a19e1","name":"hivemind-goals","summary":"OpenclawのHivemindを使ってチーム目標+KPIを作成・追跡・閲覧できます。ユーザーが目標、目標、KPI、目標、マイルストーン、または測定可能な進捗を追跡したいと尋ねるたびに使います。","body":"# Hivemind Goals (openclaw)\n\nOpenClaw exposes purpose-built tools for goals + KPIs. Use them directly — do NOT try to write files via the host filesystem.\n\n## Tools\n\n- `hivemind_goal_add({ text })` — create a new goal. Returns `goal_id` (UUID). Status starts at `opened`.\n- `hivemind_kpi_add({ goal_id, kpi_id, target, unit, name? })` — add a KPI to an existing goal. Only call when the user explicitly asks for KPIs; do NOT auto-generate.\n- `hivemind_search({ query })` — search Hivemind shared memory (summaries + sessions). Use this when the user asks \"what's already there\" before creating a duplicate.\n- `hivemind_read({ path })` — read the full content of a specific Hivemind path.\n- `hivemind_index({})` — list everything in memory.\n\n## Workflow when the user expresses a goal\n\n1. (Optional) `hivemind_search` first to surface any existing related goal.\n2. `hivemind_goal_add({ text: \"<short description>\" })` — capture the returned `goal_id`.\n3. ONLY if the user asks for KPIs: `hivemind_kpi_add` once per KPI with `goal_id` + `kpi_id` (short slug like `k-prs`) + `target` (positive int) + `unit`.\n4. Confirm to the user with the goal_id and that the goal is team-visible.\n\n## Capture a task for later (with resumable context)\n\nWhen the user **parks a tangential task** mid-session — \"save this for later\", \"remind me to …\", \"don't let me forget …\", \"let's do X later\" — store enough **context to resume cold** later, not just a one-liner. Put the full package in the `text` of `hivemind_goal_add`:\n\n```\nhivemind_goal_add({ text:\n  \"Add rate-limiting to the webhook handler\\n\\n\" +\n  \"Start here: add a per-IP token bucket on the handler entry path\\n\" +\n  \"Files: src/webhook/handler.ts:120-160, src/webhook/limits.ts\\n\" +\n  \"Branch: feat/webhook-hardening\\n\" +\n  \"Run: pnpm test webhook\\n\" +\n  \"Why: bursty clients hammer the endpoint; defer until retry-backoff lands\" })\n```\n\nLine 1 is the label. Fill `Start here / Files / Branch / Run / Why` from the conversation; `Start here:` (the concrete first action) matters most. (OpenClaw's `hivemind_goal_add` has no provenance flag, so the row is tagged `manual` — that's fine; the context is what matters.)\n\n## Resume a parked task (automatic context transfer)\n\nWhen the user says \"let's work on that task / goal\" or \"pick up the `<X>` task\":\n\n1. `hivemind_search({ query: \"<topic>\" })` or `hivemind_index({})` to locate the parked goal, then `hivemind_read({ path: \"memory/goal/<owner>/opened/<goal_id>.md\" })` to pull the **full** context package back.\n2. Read it as your working context and begin from `Start here:` using the `Files` / `Branch` / `Run` lines — continue as if the context was never lost.\n\n(Status-move tools aren't exposed on OpenClaw, so leave the goal where it is and just resume the work.)\n\n## What NOT to do\n\n- Do NOT write files anywhere under `~/.deeplake/memory/`. OpenClaw's runtime does not route filesystem writes to the Deeplake tables — only the `hivemind_*` tools above do.\n- Do NOT call `hivemind_kpi_add` unsolicited. Wait for the user to ask.\n- Do NOT use `hivemind_search` to *create* anything — it's read-only.","author":"@activeloopai","ownerProfile":null,"authorContacts":null,"sourceUrl":"https://github.com/activeloopai/hivemind/tree/main/harnesses/openclaw/skills/hivemind-goals","license":"Apache-2.0","category":"writing","lang":"en","tokens":876,"stars":0,"calls30d":1,"claimed":false,"visibility":"public","origin":"crawler","version":"0.1.0","createdAt":"2026-08-22","updatedAt":"2026-08-22","files":[],"requires":{"mcp":[],"tools":["hivemind_search","hivemind_read","hivemind_index","hivemind_goal_add","hivemind_kpi_add"]},"safety":{"flags":[],"scannedAt":"2026-08-22","hasScripts":false,"networkEndpoints":[]}}