Update to Basic Memory Cloud

{
  "name": "memory-continue",
  "description": "Resume prior work by rebuilding context from the Basic Memory knowledge graph — pick up where you left off using memory:// URLs, recent activity, and search. Use when starting a session or when the user says 'continue with...', 'back to...', or 'where were we?'",
  "included_files": [
    {
      "relative_path": "agents/openai.yaml",
      "size_in_bytes": 396
    }
  ],
  "skill_md_contents": "---\nname: memory-continue\ndescription: \"Resume prior work by rebuilding context from the Basic Memory knowledge graph — pick up where you left off using memory:// URLs, recent activity, and search. Use when starting a session or when the user says 'continue with...', 'back to...', or 'where were we?'\"\n---\n\n# Memory Continue\n\nResume previous work by reconstructing context from the Basic Memory knowledge graph, so the assistant can pick up across sessions instead of starting cold.\n\n## When to Use\n\n- Starting a new session and you need to pick up where you left off\n- The user references earlier work: \"continue with...\", \"back to...\", \"where were we on...?\"\n- You need context about an ongoing project or spec\n- The user asks about something discussed in a previous conversation\n- You're working on a task that spans multiple sessions\n\n## Building Context\n\n### 1. Identify What to Continue\n\nIf it's unclear, ask:\n- What topic or project should you resume?\n- What timeframe matters?\n- Any specific aspect to focus on?\n\n### 2. Gather Context with MCP Tools\n\n**Known topic — use `build_context`.** Navigate the graph from a starting point, following relations outward:\n\n```python\nbuild_context(\n    url=\"memory://topic-or-note-name\",\n    depth=2,           # how many relation hops to follow\n    timeframe=\"7d\",    # bias toward recent changes\n)\n```\n\n**No clear starting point — use `recent_activity`.** See what's changed and let it surface the thread:\n\n```python\nrecent_activity(timeframe=\"3d\", depth=1)\n```\n\n**Looking for something specific — use `search_notes`.** Find candidate notes by keyword:\n\n```python\nsearch_notes(query=\"async client refactor\", page_size=10)\n```\n\n### 3. Read the Key Notes\n\nOnce you've identified the relevant notes, read them in full:\n\n```python\nread_note(identifier=\"note-title-or-permalink\")\n```\n\n### 4. Present Context to the User\n\nSummarize what you found, incrementally:\n- Current state of the work\n- Recent changes or progress\n- Open items and next steps\n- Related context that might help\n\n## Memory URL Reference\n\n`build_context` and `read_note` both accept `memory://` URLs, which address notes by permalink and support wildcards for gathering groups of notes.\n\n```\nmemory://note-title            # a single note by permalink\nmemory://folder/*              # all notes in a folder\nmemory://specs/SPEC-24*        # pattern / prefix match\nmemory://project/*/requirements # path wildcards\n```\n\nUse a specific note URL to anchor on one starting point; use a wildcard to pull in a whole folder or family of related notes at once.\n\n## Timeframe Reference\n\n`build_context` and `recent_activity` accept natural-language timeframes:\n\n| Timeframe | Meaning |\n|-----------|---------|\n| `\"today\"` | Current day |\n| `\"yesterday\"` | Previous day |\n| `\"3d\"` or `\"3 days\"` | Last 3 days |\n| `\"1 week\"` or `\"7d\"` | Last week |\n| `\"2 weeks\"` | Last 2 weeks |\n| `\"1 month\"` | Last month |\n\n## Scenario Playbooks\n\n### Resuming a Spec or Project\n\n```python\n# 1. Read the spec / project note\nread_note(identifier=\"SPEC-24: Postgres Database Migration\")\n\n# 2. Pull in related context and recent changes via the graph\nbuild_context(url=\"memory://SPEC-24*\", timeframe=\"7d\")\n```\n\nThen summarize: the goals, what's completed, what's pending, and any blockers or open decisions.\n\n### Continuing General Work\n\n```python\n# 1. Check recent activity\nrecent_activity(timeframe=\"3d\")\n\n# 2. Read notes from the recent sessions it surfaces\nread_note(identifier=\"relevant-note\")\n```\n\nThen list the modified notes with brief descriptions and ask which thread to dive into.\n\n### Following Up on a Topic\n\n```python\n# 1. Find the topic\nsearch_notes(query=\"topic keywords\")\n\n# 2. Build context from the best match, following its relations\nbuild_context(url=\"memory://found-note-permalink\", depth=2)\n```\n\nThen present the full picture — the note plus its connected context.\n\n## Project Discovery\n\nProject names are user-specific. To discover what's available before scoping a search or `memory://` URL:\n\n```python\nlist_memory_projects()\n```\n\nIn multi-project setups, prefix a `memory://` URL with the project name (e.g. `memory://research/papers/crdt`) to scope it.\n\n## Guidelines\n\n1. **Start broad, then narrow.** Get an overview with `recent_activity` or a wildcard `build_context`, then drill into specific notes.\n2. **Present incrementally.** Share what you find as you go rather than holding everything until the end.\n3. **Follow relations.** The graph's connections are the point — `build_context` with `depth` surfaces context you wouldn't find by reading one note.\n4. **Check multiple projects.** Specs may live separately from implementation notes; discover projects with `list_memory_projects`.\n5. **Confirm understanding.** Verify the reconstructed context is what the user actually needs before acting on it.\n6. **Capture new progress.** As the resumed work advances, write it back to the graph (see the **memory-notes** skill) so the next session can continue too.\n"
}