{"id":7324,"plugin_id":"plugin_asdk_app_699db5f04b788191a4f9ee070d3e5d67","kind":"skill","collection_source":null,"comparison_source":null,"observed_at":"2026-09-30T22:50:20.982Z","digest":"98e32181bb864a82e59bc663cdbb726f77e9f7f797e17c49830d603d68ebd86a","against":null,"payload":{"name":"empirical-memory","description":"Cross-project personal memory through Empirical CLI and MCP. Use for research, debugging, specs, status, handoffs, personal context, lead/CRM work, assistant operations, or whenever prior decisions and preferences may matter; also use when asked to remember, recall, update, or forget information.","included_files":[],"skill_md_contents":"---\nname: empirical-memory\ndescription: Cross-project personal memory through Empirical CLI and MCP. Use for research, debugging, specs, status, handoffs, personal context, lead/CRM work, assistant operations, or whenever prior decisions and preferences may matter; also use when asked to remember, recall, update, or forget information.\n---\n\n# Empirical Memory\n\nUse Empirical to carry durable context across projects and clients.\n\n## Before doing work\n\n1. Query relevant memories before any substantive response or tool call when the task may benefit from prior context. This includes research, debugging, PRDs/specs, status, handoffs, personal health, leads, CRM, and assistant operations.\n2. Prefer the `empirical` CLI when it is available because it avoids MCP tool discovery:\n\n   ```text\n   empirical memory query --match \"<relevant context>\" --top-k 10\n   ```\n\n3. If the CLI is unavailable, use the connected MCP `query_memories` tool. Use filters such as `category`, `tags`, `nodeType`, and `monthKey` when they improve recall. For exhaustive topic retrieval, use the topic as a tag and follow pagination.\n\n## Persist durable context\n\n- Record durable decisions, project conventions, preferences, plans, and meaningful reflections with `record_graph_memory` or:\n\n  ```text\n  empirical memory record --category <category> --summary \"<concise fact>\" --tags <tag1,tag2>\n  ```\n\n- Append a correction or follow-up to an existing memory with `add_note_by_query` / `empirical memory note`.\n- Patch an existing memory with `update_memory_by_query` / `empirical memory update`.\n- Delete only when the user explicitly asks; use the delete tool with confirmation.\n- Keep writes concise, factual, and easy to search. Never store passwords, API keys, OAuth tokens, or other secrets.\n\n## MCP tools\n\nUse these when connected: `query_memories`, `record_graph_memory`, `add_note_by_query`, `update_memory_by_query`, `delete_memory_by_query`, `get_user`, `get_current_workspace`, `list_workspaces`, and `set_current_workspace`. For graph work, use `get_memory_neighbors` and `update_memory_relationships` when available instead of reconstructing relationships through many unrelated calls.\n\n## Authentication and failures\n\n- If a memory call fails, retry the same call once.\n- For auth/session errors such as `Auth required`, `invalid_token`, `Authentication required`, or `Transport send error`, refresh the active client’s Empirical MCP login, then retry once. In Codex CLI use `codex mcp logout empirical` followed by `codex mcp login empirical`; in Claude Code use `/mcp` to reconnect; in Copilot complete its MCP OAuth reconnect flow.\n- If the retry still fails, report the connectivity/auth problem before making memory-dependent changes.\n- If stored memory conflicts with the current user or repository instruction, follow the current instruction.\n\n## Exact CLI syntax\n\nRun `empirical doc memory` before guessing CLI flags. Run `empirical doctor` to check connectivity and token status. If a CLI memory command reports a token error, run `empirical oauth bootstrap headless --write-env`.\n"},"changes":[],"summary":"First saved snapshot. No earlier version is available for comparison.","summary_kind":"deterministic","summary_metadata":{}}