{"id":"ce9ab5ba-fcff-4dd8-981b-46c5b9de255a","entityType":"agent","slug":"clawhub-hansenz42-miremo","name":"Miremo Research Skill","canonicalUrl":"https://www.xpersona.co/agent/clawhub-hansenz42-miremo","canonicalPath":"/agent/clawhub-hansenz42-miremo","generatedAt":"2026-10-12T14:52:58.140Z","source":"CLAWHUB","claimStatus":"UNCLAIMED","verificationTier":"NONE","summary":{"evidence":{"source":"CLAWHUB","verified":false,"confidence":"medium","updatedAt":"2026-10-11T21:11:33.667Z","emptyReason":null},"description":"Access the user's personal Miremo knowledge base and reusable method skills — search notes, look up what they know about a topic, browse documents and tags, explore their knowledge graph, save new information, or retrieve the user's Miremo Skill materials.","descriptionLabel":"Source description","evidenceSummary":"Capability contract not published. No trust telemetry is available yet. 992 downloads reported by the source. Last updated 10/11/2026.","installCommand":"clawhub skill install s172d5av5c18p7qtb6s3y1fqqx8434nw:miremo","sourceUrl":"https://clawhub.ai/hansenz42/miremo","homepage":"https://clawhub.ai/hansenz42/skills/miremo","primaryLinks":[{"label":"View on ClawHub","url":"https://clawhub.ai/hansenz42/miremo","kind":"source"},{"label":"Homepage","url":"https://clawhub.ai/hansenz42/skills/miremo","kind":"homepage"}],"safetyScore":84,"overallRank":62,"popularityScore":60,"trustScore":null,"claimedByName":null,"isOwner":false,"seoDescription":"Miremo Research Skill technical dossier on Xpersona with agent coverage, OPENCLEW support, and live trust metadata."},"coverage":{"evidence":{"source":"public-profile","verified":false,"confidence":"medium","updatedAt":"2026-10-11T21:11:33.667Z","emptyReason":null},"protocols":[{"protocol":"OPENCLEW","label":"OpenClaw","status":"self-declared","notes":"Declared in the public agent profile."}],"capabilities":[],"verifiedCount":0,"selfDeclaredCount":1,"capabilityMatrix":{"rows":[{"key":"OPENCLEW","type":"protocol","support":"unknown","confidenceSource":"profile","notes":"Listed on profile"}],"flattenedTokens":"protocol:OPENCLEW|unknown|profile"}},"adoption":{"evidence":{"source":"CLAWHUB","verified":false,"confidence":"medium","updatedAt":"2026-10-11T21:11:33.667Z","emptyReason":null},"stars":null,"forks":null,"downloads":992,"likes":null,"task":null,"library":null,"packageName":null,"latestVersion":"1.0.2","tractionLabel":"992 downloads"},"release":{"evidence":{"source":"CLAWHUB","verified":false,"confidence":"medium","updatedAt":"2026-10-11T21:11:33.599Z","emptyReason":null},"lastUpdatedAt":"2026-10-11T21:11:33.667Z","lastCrawledAt":"2026-10-11T21:11:33.599Z","lastIndexedAt":null,"nextCrawlAt":"2026-10-12T21:11:33.599Z","lastVerifiedAt":null,"highlights":[{"version":"1.0.2","createdAt":"2026-07-08T03:06:26.604Z","changelog":"miremo v1.0.2 - Expanded description and research strategies to support retrieval and use of user-authored method skills, workflows, and output templates. - Added \"Method Skill\" tools: list, search, and retrieve reusable Miremo skills by ID or slug. - Updated skill usage guidance: new Mode D for applying method skill materials, including triggers and workflow. - Replaced document list/read tools with new collection and document-section outline tools. - Removed obsolete or redundant documentation files (e.g., skill-card.md).","fileCount":4,"zipByteSize":7591},{"version":"1.0.1","createdAt":"2026-04-30T07:28:34.932Z","changelog":"- Added support for multiple workspaces with new tools: `list_workspaces` and `get_current_workspace` - All main tools (`search_memos`, `global_search`, `list_memos`, `list_supertags`, `list_documents`, `create_memo`) now accept an optional `workspace_id` to target specific workspaces - Updated research strategies and workflows to handle workspace context and cross-workspace research - Improved documentation on workspace-aware behavior and clarified default vs explicit workspace usage - Minor: Homepage URL updated to https://www.miremoapp.com","fileCount":4,"zipByteSize":5961},{"version":"1.0.0","createdAt":"2026-04-28T07:01:01.553Z","changelog":"Initial release of the Miremo skill for OpenClaw. - Search and browse your personal Miremo knowledge base, including memos, documents, topic tags (supertags), and knowledge graph. - Save new notes directly from chat using “create memo.” - Use structured workflows for topic research, overviews, and exact lookups of your own content. - Explore your AI-extracted entities and their relationships via the built-in knowledge graph tools. - Skill responds only to queries about your stored notes, not general internet searches.","fileCount":3,"zipByteSize":4196}]},"execution":{"evidence":{"source":"CLAWHUB","verified":false,"confidence":"low","updatedAt":null,"emptyReason":"No published capability contract is available yet."},"installCommand":"clawhub skill install s172d5av5c18p7qtb6s3y1fqqx8434nw:miremo","setupComplexity":"low","setupSteps":["Install using `clawhub skill install s172d5av5c18p7qtb6s3y1fqqx8434nw:miremo` in an isolated environment before connecting it to live workloads.","No published capability contract is available yet, so validate auth and request/response behavior manually.","Review the upstream CLAWHUB listing at https://clawhub.ai/hansenz42/miremo before using production credentials."],"contract":{"contractStatus":"missing","authModes":[],"requires":[],"forbidden":[],"supportsMcp":false,"supportsA2a":false,"supportsStreaming":false,"inputSchemaRef":null,"outputSchemaRef":null,"dataRegion":null,"contractUpdatedAt":null,"sourceUpdatedAt":null,"freshnessSeconds":null},"invocationGuide":{"preferredApi":{"snapshotUrl":"https://www.xpersona.co/api/v1/agents/clawhub-hansenz42-miremo/snapshot","contractUrl":"https://www.xpersona.co/api/v1/agents/clawhub-hansenz42-miremo/contract","trustUrl":"https://www.xpersona.co/api/v1/agents/clawhub-hansenz42-miremo/trust"},"curlExamples":["curl -s \"https://www.xpersona.co/api/v1/agents/clawhub-hansenz42-miremo/snapshot\"","curl -s \"https://www.xpersona.co/api/v1/agents/clawhub-hansenz42-miremo/contract\"","curl -s \"https://www.xpersona.co/api/v1/agents/clawhub-hansenz42-miremo/trust\""],"jsonRequestTemplate":{"query":"summarize this repo","constraints":{"maxLatencyMs":2000,"protocolPreference":["OPENCLEW"]}},"jsonResponseTemplate":{"ok":true,"result":{"summary":"...","confidence":0.9},"meta":{"source":"CLAWHUB","generatedAt":"2026-10-12T14:52:58.138Z"}},"retryPolicy":{"maxAttempts":3,"backoffMs":[500,1500,3500],"retryableConditions":["HTTP_429","HTTP_503","NETWORK_TIMEOUT"]}},"endpoints":{"dossierUrl":"https://www.xpersona.co/api/v1/agents/clawhub-hansenz42-miremo/dossier","snapshotUrl":"https://www.xpersona.co/api/v1/agents/clawhub-hansenz42-miremo/snapshot","contractUrl":"https://www.xpersona.co/api/v1/agents/clawhub-hansenz42-miremo/contract","trustUrl":"https://www.xpersona.co/api/v1/agents/clawhub-hansenz42-miremo/trust"}},"reliability":{"evidence":{"source":"runtime-metrics","verified":false,"confidence":"low","updatedAt":null,"emptyReason":"No trust, reliability, or runtime telemetry is available."},"trust":{"status":"unavailable","handshakeStatus":"UNKNOWN","verificationFreshnessHours":null,"reputationScore":null,"p95LatencyMs":null,"successRate30d":null,"fallbackRate":null,"attempts30d":null,"trustUpdatedAt":null,"trustConfidence":"unknown","sourceUpdatedAt":null,"freshnessSeconds":null},"decisionGuardrails":{"doNotUseIf":["Contract metadata is missing or unavailable for deterministic execution."],"safeUseWhen":[],"riskFlags":["missing_or_unavailable_contract","trust_data_unavailable","schema_references_missing"],"operationalConfidence":"low"},"executionMetrics":{"observedLatencyMsP50":null,"observedLatencyMsP95":null,"estimatedCostUsd":null,"uptime30d":null,"rateLimitRpm":null,"rateLimitBurst":null,"lastVerifiedAt":null,"verificationSource":null},"runtimeMetrics":{"successRate":null,"avgLatencyMs":null,"avgCostUsd":null,"hallucinationRate":null,"retryRate":null,"disputeRate":null,"p50Latency":null,"p95Latency":null,"lastUpdated":null}},"benchmarks":{"evidence":{"source":"no-benchmark-data","verified":false,"confidence":"low","updatedAt":null,"emptyReason":"No benchmark suites or observed failure patterns are available."},"suites":[],"failurePatterns":[]},"artifacts":{"evidence":{"source":"CLAWHUB","verified":false,"confidence":"medium","updatedAt":"2026-10-11T21:11:33.667Z","emptyReason":null},"readme":"Skill: Miremo Research Skill\n\nOwner: hansenz42\n\nSummary: Access the user's personal Miremo knowledge base and reusable method skills — search notes, look up what they know about a topic, browse documents and tags, explore their knowledge graph, save new information, or retrieve the user's Miremo Skill materials.\n\nTags: latest:1.0.2\n\nVersion history:\n\nv1.0.2 | 2026-07-08T03:06:26.604Z | user\n\nmiremo v1.0.2\n\n- Expanded description and research strategies to support retrieval and use of user-authored method skills, workflows, and output templates.\n- Added \"Method Skill\" tools: list, search, and retrieve reusable Miremo skills by ID or slug.\n- Updated skill usage guidance: new Mode D for applying method skill materials, including triggers and workflow.\n- Replaced document list/read tools with new collection and document-section outline tools.\n- Removed obsolete or redundant documentation files (e.g., skill-card.md).\n\nv1.0.1 | 2026-04-30T07:28:34.932Z | user\n\n- Added support for multiple workspaces with new tools: `list_workspaces` and `get_current_workspace`\n- All main tools (`search_memos`, `global_search`, `list_memos`, `list_supertags`, `list_documents`, `create_memo`) now accept an optional `workspace_id` to target specific workspaces\n- Updated research strategies and workflows to handle workspace context and cross-workspace research\n- Improved documentation on workspace-aware behavior and clarified default vs explicit workspace usage\n- Minor: Homepage URL updated to https://www.miremoapp.com\n\nv1.0.0 | 2026-04-28T07:01:01.553Z | user\n\nInitial release of the Miremo skill for OpenClaw.\n\n- Search and browse your personal Miremo knowledge base, including memos, documents, topic tags (supertags), and knowledge graph.\n- Save new notes directly from chat using “create memo.”\n- Use structured workflows for topic research, overviews, and exact lookups of your own content.\n- Explore your AI-extracted entities and their relationships via the built-in knowledge graph tools.\n- Skill responds only to queries about your stored notes, not general internet searches.\n\nArchive index:\n\nArchive v1.0.2: 4 files, 7591 bytes\n\nFiles: README.md (2676b), skill-card.md (2357b), SKILL.md (13247b), _meta.json (125b)\n\nFile v1.0.2:SKILL.md\n\n---\nname: miremo\ndescription: Access the user's personal Miremo knowledge base and reusable method skills — search notes, look up what they know about a topic, browse documents and tags, explore their knowledge graph, save new information, or retrieve the user's Miremo Skill materials. Use when the user says \"find my notes\", \"what do I know about\", \"search my knowledge base\", \"look it up in Miremo\", \"save/record/remember this\", \"what topics have I written about\", \"show my notes on X\", \"use my Miremo skill\", \"use my method/template/workflow\", or \"look up my skill instructions\". NOT for general web searches or queries about topics not stored in the user's own Miremo data.\nhomepage: https://www.miremoapp.com\nmetadata:\n  { \"openclaw\": { \"emoji\": \"📓\", \"requires\": { \"config\": [\"mcp.servers\"] } } }\n---\n\n# Miremo Skill\n\n**Prerequisite:** The Miremo MCP server must be connected in OpenClaw before this skill's tools are available. See the README for setup instructions.\n\nMiremo is an AI note-taking tool. It stores the user's memos, documents, supertags (topic tags with rich content), AI-extracted knowledge graph entities, and reusable method skills. All tools only access the currently authenticated user's own data.\n\nWorkspace behavior:\n\n- If `workspace_id` is provided, tools operate in that workspace (with permission checks).\n- If `workspace_id` is omitted, tools operate only in the user's default workspace.\n- Use `list_workspaces` and `get_current_workspace` to inspect available workspaces and the active workspace resolution.\n\n---\n\n## Research Strategy\n\nWhen the user asks about their knowledge or methods, choose one of four modes and follow it through completely before giving a final answer. **Never give up after one failed search.**\n\n### Mode A — Browse (user wants an overview)\n\nTriggers: \"what notes do I have\", \"show me my recent notes\", \"what have I been writing about\", \"give me an overview\"\n\nSteps:\n\n1. `list_workspaces()` to understand all accessible workspaces\n2. `get_current_workspace()` to confirm default workspace before browsing\n3. `list_memos(page_size=30)` to sample recent memos\n4. `list_supertags()` to see all topic tags at a glance\n5. Synthesize a structured overview from both results\n\n### Mode B — Topic Research (most common)\n\nTriggers: \"what do I know about X\", \"find notes about X\", \"anything related to X\", \"my thoughts on X\"\n\nSteps:\n\n1. `list_workspaces()` when user asks for cross-workspace research\n2. `global_search(query=\"X\")` — cross-type overview (memos + docs + supertags)\n3. `search_memos(query=\"X\", search_type=\"semantic\")` for deeper semantic matches\n4. If a relevant supertag appears: `list_supertags(q=\"X\")` to expand via that tag\n5. For people, concepts, or events that matter: `list_entities()` → `get_entity_graph(entity_id)` to explore relationships\n\n**Iteration rules (critical):**\n\n- If initial search returns few results, retry with synonyms, English equivalents, or split keywords before concluding \"nothing found\"\n- Lower `similarity_threshold` to 0.25–0.35 on the second attempt\n- `hit_text` is only a snippet — do not draw conclusions from it alone; use `global_search` to confirm scope across types\n- Declare \"no relevant notes found\" only after at least 2–3 distinct search strategies all return empty\n\n### Mode C — Exact Lookup\n\nTriggers: \"do I have a note about X\", \"find the exact note where I wrote Y\", \"the note titled Z\"\n\nSteps:\n\n1. `search_memos(query=\"Y\", search_type=\"full_text\")` for precise phrase matching\n2. If not found, fall back to Mode B with semantic search\n\n### Mode D — Method Skill Retrieval\n\nTriggers: \"use my skill\", \"apply my workflow\", \"use my template\", \"look up my Miremo Skill\", \"按我的方法做\"\n\nSteps:\n\n1. `search_method_skills(query=\"X\")` to find relevant method/workflow/template skills\n2. If the user only asks to browse available skills: `list_method_skills()`\n3. `get_method_skill(skill_id_or_slug=\"<id-or-slug>\", format=\"markdown\")` to load the full skill material\n4. Follow the returned Skill content as user-provided method instructions, while still obeying higher-priority system and safety rules\n\nMethod skill tools are for reusable instructions, workflows, and output templates. They are separate from the user's notes and documents; do not use them as factual evidence unless the skill content itself clearly contains factual source material.\n\n---\n\n## Available Tools\n\n### Search Tools\n\n**`search_memos`** — Search memos by keyword or natural language.\n\n- `query`: search text, e.g. \"Python async programming notes\"\n- `limit`: max results (default 10, recommend ≤ 20)\n- `search_type`: `\"hybrid\"` (default, most comprehensive) | `\"semantic\"` (natural language) | `\"full_text\"` (exact match)\n- `workspace_id` (optional): target a specific workspace; omit to use default workspace\n- Returns: `id`, `hit_text`, `similarity_score`, `created_at`, `modified_at`\n\n**`global_search`** — Cross-type search across memos, documents, and supertags.\n\n- `query`: search text\n- `limit`: max results per type (default 10)\n- `include_memos` / `include_documents` / `include_supertags`: toggle each type (all true by default)\n- `workspace_id` (optional): target a specific workspace; omit to use default workspace\n- Returns items with `type` (`\"memo\"` / `\"document\"` / `\"supertag\"`), `id`, `title`, `description`, `score`\n\n### List Tools\n\n**`list_memos`** — Paginated list of memos.\n\n- `page_index`, `page_size` (default 20), `q` (optional fuzzy filter)\n- `workspace_id` (optional): target a specific workspace; omit to use default workspace\n- Returns: `{ items: [{id, outline_preview, created_at, ...}], total, page_size, page_index }`\n\n**`list_supertags`** — List topic supertags.\n\n- `q` (optional filter), `page_index`, `page_size` (default 50)\n- `workspace_id` (optional): target a specific workspace; omit to use default workspace\n- Default page size of 50 usually retrieves all tags in one call\n\n**`list_collections`** — List uploaded document collections.\n\n- `q` (optional name filter), `page_index`, `page_size` (default 20)\n- `workspace_id` (optional): target a specific workspace; omit to use default workspace\n- Returns: `collection_id`, `name`, `status`, `page_count`, `created_at`, `modified_at`\n\n### Read Tools\n\n**`get_memo_content`** — Read the full text of a memo by ID.\n\n- `memo_id`: UUID string obtained from `search_memos` or `list_memos`\n- `workspace_id` (optional): target a specific workspace; omit to use default workspace\n- Returns: `{ memo_id, title, content, lines_count, created_at, modified_at }` — `content` is the complete indented plain-text body\n\n**`get_collection_outline`** — Get a collection's structured section outline.\n\n- `collection_id`: UUID string obtained from `list_collections` or `global_search`\n- `workspace_id` (optional): target a specific workspace; omit to use default workspace\n- Returns: `{ collection_id, name, pages: [{document_id, page_order, sections: [{section_id, heading, heading_level, summary, section_order}]}], total_sections }`\n- Use this first to understand document structure, then call `get_document_section` for sections of interest\n\n**`get_document_section`** — Read the full text of a specific document section.\n\n- `document_id`: UUID string of the parent document\n- `section_id`: UUID string from `get_collection_outline`'s `sections` list\n- `workspace_id` (optional): target a specific workspace; omit to use default workspace\n- Returns: `{ section_id, document_id, heading, heading_level, summary, section_text }`\n\n### Method Skill Tools\n\n**`list_method_skills`** — List reusable Miremo method skills available to external agents.\n\n- `q` (optional): keyword filter across skill name, summary, content, and file paths\n- `capability_type` (optional): `AGENT_CAPABILITY` | `OUTPUT_TEMPLATE` | `WORKFLOW`\n- `limit` (default 20, max 50)\n- `workspace_id` (optional): target a specific workspace; omit to use default workspace\n- Returns: `{ items: [{skill_id, name, slug, description, capability_type, files}], total, limit }`\n\n**`search_method_skills`** — Search reusable method/workflow/template skills.\n\n- `query`: natural language task or keyword\n- `limit` (default 10, max 50)\n- `workspace_id` (optional): target a specific workspace; omit to use default workspace\n- Returns the same item structure as `list_method_skills`\n\n**`get_method_skill`** — Read one method skill's full material.\n\n- `skill_id_or_slug`: value returned by `list_method_skills` or `search_method_skills`\n- `format`: `\"markdown\"` (default) | `\"json\"`\n- `workspace_id` (optional): target a specific workspace; omit to use default workspace\n- Markdown returns a SKILL.md-like document containing the skill summary, execution method, and attached files\n- JSON returns structured metadata and all skill package file contents\n\n### Create Tools\n\n**`create_memo`** — Create a new memo.\n\n- `content`: memo body, multi-line supported. First line becomes the top-level title; subsequent lines become sub-content.\n- `workspace_id` (optional): target a specific workspace for writing; omit to write into default workspace\n- Returns: `{ memo_id: \"<new UUID>\" }`\n- After creation, vectorization and knowledge graph updates run automatically in the background.\n\n### Workspace Tools\n\n**`list_workspaces`** — List all workspaces accessible to the current user.\n\n- Returns workspace metadata including `workspace_id`, `name`, `role`, `is_default`\n\n**`get_current_workspace`** — Get the effective workspace for current tool call context.\n\n- `workspace_id` (optional): if provided, validates and resolves explicit workspace\n- Without parameter, resolves to default workspace\n- Returns `source` (`explicit` or `default`) and current workspace metadata\n\n### Knowledge Graph Tools\n\n**`list_entities`** — List AI-extracted knowledge graph entities.\n\n- `entity_type` (optional): `person`, `concept`, `place`, `organization`, `event`, etc.\n- `page_index`, `page_size` (default 20)\n- Omit `entity_type` to get all types mixed\n\n**`get_entity_graph`** — Get an entity's 1-hop relationship graph.\n\n- `entity_id`: obtain via `list_entities` first\n- Returns: `{ entity: {entity_id, name, entity_type, summary}, related_entities: [...], relationships: [{source_entity_id, target_entity_id, description}] }`\n\n---\n\n## When to Use Which Tool\n\n| User intent                         | Recommended tool                                      |\n| ----------------------------------- | ----------------------------------------------------- |\n| \"Find notes about X\"                | `global_search` first, then `search_memos` for detail |\n| \"Find notes with exact phrase\"      | `search_memos` with `search_type=\"full_text\"`         |\n| \"What do I know about X\" (semantic) | `search_memos` with `search_type=\"semantic\"`          |\n| \"Read full content of a memo\"       | `get_memo_content` with `memo_id`                     |\n| \"Show me recent memos\"              | `list_memos`                                          |\n| \"What topics do I write about\"      | `list_supertags`                                      |\n| \"Find a document / PDF\"             | `list_collections` with `q` filter                    |\n| \"Read a document\"                   | `get_collection_outline` → `get_document_section`     |\n| \"Save / record / note down X\"       | `create_memo`                                         |\n| \"Explore my knowledge graph\"        | `list_entities` → `get_entity_graph`                  |\n| \"Which workspace should I use\"      | `list_workspaces` → `get_current_workspace`           |\n| \"Use my Miremo skill / workflow\"    | `search_method_skills` → `get_method_skill`           |\n\n---\n\n## Recommended Workflows\n\n### Answer \"What do I know about X\":\n\n1. `get_current_workspace()` to confirm workspace scope\n2. `global_search(query=\"X\")` for a cross-type overview\n3. If more detail needed: `search_memos(query=\"X\", search_type=\"semantic\")`\n4. If a relevant supertag exists: `list_supertags(q=\"X\")` to expand further\n5. To read a specific memo's full content: `get_memo_content(memo_id=\"<id>\")`\n\n### Read a document:\n\n1. `list_collections(q=\"keyword\")` to find the document collection and get its `collection_id`\n2. `get_collection_outline(collection_id=\"<id>\")` to see the section structure and summaries\n3. `get_document_section(section_id=\"<id>\")` for each section of interest\n\n### Apply a Miremo method skill:\n\n1. `search_method_skills(query=\"user task or method name\")` to find candidate skills\n2. `get_method_skill(skill_id_or_slug=\"<id-or-slug>\", format=\"markdown\")` to load the full skill material\n3. Use the returned Skill content as the user's reusable method, workflow, or output template\n4. If the skill references attached files by path, use the attached file sections or JSON file list from `get_method_skill`\n\n### Help user record new information:\n\n1. Confirm intent, then call `create_memo(content=\"...\")`\n2. Tell the user the note was created and show the `memo_id`\n3. Structure content well: first line = core topic, subsequent lines = details\n\n### Explore user's knowledge structure:\n\n1. `list_supertags()` for a thematic overview\n2. `list_entities()` to understand main knowledge graph nodes\n3. `get_entity_graph(entity_id)` for entities of interest\n\nFile v1.0.2:README.md\n\n# Miremo Skill for OpenClaw\n\nAccess your [Miremo](https://miremoapp.com) notes, documents, supertags, knowledge graph, and reusable method skills directly from OpenClaw via MCP.\n\n## Prerequisites\n\nThis skill requires the Miremo MCP server to be connected in OpenClaw. Complete the following setup first.\n\n---\n\n## Step 1: Generate a Miremo API Key\n\n1. Open the Miremo app → **Settings → Preferences**\n2. Find the **API Key** section and click **New API Key**\n3. Enter a name (e.g. `OpenClaw`) and confirm\n4. **Copy the key immediately** (format: `sk-miremo-xxxx`) — it won't be shown again\n\n---\n\n## Step 2: Add the MCP Server to OpenClaw\n\nEdit `~/.openclaw/openclaw.json` and add under `mcp.servers`:\n\n```json\n{\n  \"mcp\": {\n    \"servers\": {\n      \"miremo\": {\n        \"type\": \"http\",\n        \"url\": \"https://api.miremoapp.com/mcp/v1/mcp\",\n        \"headers\": {\n          \"Authorization\": \"Bearer sk-miremo-YOUR_KEY_HERE\"\n        }\n      }\n    }\n  }\n}\n```\n\n> For local development, use `http://localhost:8000/mcp/v1/mcp` as the URL.\n\n---\n\n## Step 3: Install This Skill\n\n```bash\nopenclaw skills install miremo\n```\n\nStart a new OpenClaw session and the Miremo tools will be available.\n\n---\n\n## Available Tools\n\n| Tool | Description |\n|---|---|\n| `search_memos` | Semantic / full-text / hybrid search across memos |\n| `list_memos` | Paginated list of memos |\n| `create_memo` | Create a new memo |\n| `list_supertags` | List / search topic supertags |\n| `list_collections` | List uploaded document collections |\n| `get_collection_outline` | Get a collection's structured section outline |\n| `get_document_section` | Read a specific document section |\n| `global_search` | Cross-type search (memos + docs + supertags) |\n| `get_entity_graph` | Get 1-hop knowledge graph for an entity |\n| `list_entities` | List AI-extracted knowledge graph entities |\n| `list_workspaces` | List all workspaces accessible to the current user |\n| `get_current_workspace` | Get effective workspace resolution (`explicit` / `default`) |\n| `list_method_skills` | List reusable Miremo method/workflow/template skills |\n| `search_method_skills` | Search method skills by task or keyword |\n| `get_method_skill` | Read a method skill as SKILL.md-like markdown or structured JSON |\n\nWorkspace resolution rules:\n- If `workspace_id` is provided in tool arguments, the operation runs in that workspace.\n- If `workspace_id` is omitted, the operation runs only in the user's default workspace.\n\n---\n\n## Security Notes\n\n- Treat your API Key like a password — never commit it to version control\n- Revoke unused keys anytime in Miremo settings\n- Create separate keys for different clients for independent management\n\nFile v1.0.2:_meta.json\n\n{\n  \"ownerId\": \"kn7exb2zewsk68a4cm9sb7r3nx8425fc\",\n  \"slug\": \"miremo\",\n  \"version\": \"1.0.2\",\n  \"publishedAt\": 1783479986604\n}\n\nFile v1.0.2:skill-card.md\n\n## Description:\n\nAccess the user's personal Miremo knowledge base and reusable method skills to search notes, browse documents and tags, explore the knowledge graph, save new information, and retrieve method materials.\n\nThis skill is ready for commercial/non-commercial use.\n\n## Publisher:\n\n[hansenz42](https://clawhub.ai/user/hansenz42)\n\n### License/Terms of Use:\n\nMIT-0\n\n## Use Case:\n\nExternal users and developers use this skill to connect OpenClaw to their own Miremo account, research personal notes and documents, retrieve reusable method skills, and create new memos.\n\n### Deployment Geography for Use:\n\nGlobal\n\n## Known Risks and Mitigations:\n\nRisk: The connected agent can search and read notes, documents, tags, method skills, and knowledge graph data in the authenticated Miremo account.\n\nMitigation: Install only when the user trusts Miremo and the agent session with that account's content; use a dedicated API key for this integration.\n\nRisk: The skill can create new memos in the connected Miremo workspace.\n\nMitigation: Confirm user intent before recording information and review created memo IDs or content when write actions matter.\n\nRisk: The Miremo API key grants access through the configured MCP server if exposed.\n\nMitigation: Keep the API key out of version control, use separate keys for different clients, and revoke unused keys in Miremo settings.\n\n## Reference(s):\n\n- [Miremo homepage](https://www.miremoapp.com)\n- [ClawHub skill page](https://clawhub.ai/hansenz42/skills/miremo)\n- [ClawHub publisher profile](https://clawhub.ai/user/hansenz42)\n- [README.md](artifact/README.md)\n\n## Skill Output:\n\n**Output Type(s):** [Text, Markdown, Configuration, Guidance]\n\n**Output Format:** [Markdown or plain text with retrieved Miremo content, method-skill material, and concise tool-result summaries]\n\n**Output Parameters:** [1D]\n\n**Other Properties Related to Output:** [May include memo IDs, workspace context, document section summaries, knowledge graph relationships, and setup configuration snippets.]\n\n## Skill Version(s):\n\n1.0.2 (source: server release evidence)\n\n## Ethical Considerations:\n\nUsers should evaluate whether this skill is appropriate for their environment, review any generated or modified files before relying on them, and apply their organization's safety, security, and compliance requirements before deployment.\n\nArchive v1.0.1: 4 files, 5961 bytes\n\nFiles: README.md (2261b), skill-card.md (2153b), SKILL.md (8563b), _meta.json (125b)\n\nFile v1.0.1:SKILL.md\n\n---\nname: miremo\ndescription: Access the user's personal Miremo knowledge base — search notes, look up what they know about a topic, browse their documents and tags, explore their knowledge graph, or save new information. Use when the user says \"find my notes\", \"what do I know about\", \"search my knowledge base\", \"look it up in Miremo\", \"save/record/remember this\", \"what topics have I written about\", or \"show my notes on X\". NOT for general web searches or queries about topics not stored in the user's own notes.\nhomepage: https://www.miremoapp.com\nmetadata:\n  { \"openclaw\": { \"emoji\": \"📓\", \"requires\": { \"config\": [\"mcp.servers\"] } } }\n---\n\n# Miremo Skill\n\n**Prerequisite:** The Miremo MCP server must be connected in OpenClaw before this skill's tools are available. See the README for setup instructions.\n\nMiremo is an AI note-taking tool. It stores the user's memos, documents, supertags (topic tags with rich content), and AI-extracted knowledge graph entities. All tools only access the currently authenticated user's own data.\n\nWorkspace behavior:\n\n- If `workspace_id` is provided, tools operate in that workspace (with permission checks).\n- If `workspace_id` is omitted, tools operate only in the user's default workspace.\n- Use `list_workspaces` and `get_current_workspace` to inspect available workspaces and the active workspace resolution.\n\n---\n\n## Research Strategy\n\nWhen the user asks about their knowledge, choose one of three research modes and follow it through completely before giving a final answer. **Never give up after one failed search.**\n\n### Mode A — Browse (user wants an overview)\n\nTriggers: \"what notes do I have\", \"show me my recent notes\", \"what have I been writing about\", \"give me an overview\"\n\nSteps:\n\n1. `list_workspaces()` to understand all accessible workspaces\n2. `get_current_workspace()` to confirm default workspace before browsing\n3. `list_memos(page_size=30)` to sample recent memos\n4. `list_supertags()` to see all topic tags at a glance\n5. Synthesize a structured overview from both results\n\n### Mode B — Topic Research (most common)\n\nTriggers: \"what do I know about X\", \"find notes about X\", \"anything related to X\", \"my thoughts on X\"\n\nSteps:\n\n1. `list_workspaces()` when user asks for cross-workspace research\n2. `global_search(query=\"X\")` — cross-type overview (memos + docs + supertags)\n3. `search_memos(query=\"X\", search_type=\"semantic\")` for deeper semantic matches\n4. If a relevant supertag appears: `list_supertags(q=\"X\")` to expand via that tag\n5. For people, concepts, or events that matter: `list_entities()` → `get_entity_graph(entity_id)` to explore relationships\n\n**Iteration rules (critical):**\n\n- If initial search returns few results, retry with synonyms, English equivalents, or split keywords before concluding \"nothing found\"\n- Lower `similarity_threshold` to 0.25–0.35 on the second attempt\n- `hit_text` is only a snippet — do not draw conclusions from it alone; use `global_search` to confirm scope across types\n- Declare \"no relevant notes found\" only after at least 2–3 distinct search strategies all return empty\n\n### Mode C — Exact Lookup\n\nTriggers: \"do I have a note about X\", \"find the exact note where I wrote Y\", \"the note titled Z\"\n\nSteps:\n\n1. `search_memos(query=\"Y\", search_type=\"full_text\")` for precise phrase matching\n2. If not found, fall back to Mode B with semantic search\n\n---\n\n## Available Tools\n\n### Search Tools\n\n**`search_memos`** — Search memos by keyword or natural language.\n\n- `query`: search text, e.g. \"Python async programming notes\"\n- `limit`: max results (default 10, recommend ≤ 20)\n- `search_type`: `\"hybrid\"` (default, most comprehensive) | `\"semantic\"` (natural language) | `\"full_text\"` (exact match)\n- `workspace_id` (optional): target a specific workspace; omit to use default workspace\n- Returns: `id`, `hit_text`, `similarity_score`, `created_at`, `modified_at`\n\n**`global_search`** — Cross-type search across memos, documents, and supertags.\n\n- `query`: search text\n- `limit`: max results per type (default 10)\n- `include_memos` / `include_documents` / `include_supertags`: toggle each type (all true by default)\n- `workspace_id` (optional): target a specific workspace; omit to use default workspace\n- Returns items with `type` (`\"memo\"` / `\"document\"` / `\"supertag\"`), `id`, `title`, `description`, `score`\n\n### List Tools\n\n**`list_memos`** — Paginated list of memos.\n\n- `page_index`, `page_size` (default 20), `q` (optional fuzzy filter)\n- `workspace_id` (optional): target a specific workspace; omit to use default workspace\n- Returns: `{ items: [{id, outline_preview, created_at, ...}], total, page_size, page_index }`\n\n**`list_supertags`** — List topic supertags.\n\n- `q` (optional filter), `page_index`, `page_size` (default 50)\n- `workspace_id` (optional): target a specific workspace; omit to use default workspace\n- Default page size of 50 usually retrieves all tags in one call\n\n**`list_documents`** — List uploaded documents (PDFs, files).\n\n- `q` (optional name filter), `page_index`, `page_size` (default 20)\n- `workspace_id` (optional): target a specific workspace; omit to use default workspace\n- Returns: `document_id`, `name`, `created_at`, `modified_at`, `status`\n\n### Create Tools\n\n**`create_memo`** — Create a new memo.\n\n- `content`: memo body, multi-line supported. First line becomes the top-level title; subsequent lines become sub-content.\n- `workspace_id` (optional): target a specific workspace for writing; omit to write into default workspace\n- Returns: `{ memo_id: \"<new UUID>\" }`\n- After creation, vectorization and knowledge graph updates run automatically in the background.\n\n### Workspace Tools\n\n**`list_workspaces`** — List all workspaces accessible to the current user.\n\n- Returns workspace metadata including `workspace_id`, `name`, `role`, `is_default`\n\n**`get_current_workspace`** — Get the effective workspace for current tool call context.\n\n- `workspace_id` (optional): if provided, validates and resolves explicit workspace\n- Without parameter, resolves to default workspace\n- Returns `source` (`explicit` or `default`) and current workspace metadata\n\n### Knowledge Graph Tools\n\n**`list_entities`** — List AI-extracted knowledge graph entities.\n\n- `entity_type` (optional): `person`, `concept`, `place`, `organization`, `event`, etc.\n- `page_index`, `page_size` (default 20)\n- Omit `entity_type` to get all types mixed\n\n**`get_entity_graph`** — Get an entity's 1-hop relationship graph.\n\n- `entity_id`: obtain via `list_entities` first\n- Returns: `{ entity: {entity_id, name, entity_type, summary}, related_entities: [...], relationships: [{source_entity_id, target_entity_id, description}] }`\n\n---\n\n## When to Use Which Tool\n\n| User intent                         | Recommended tool                                      |\n| ----------------------------------- | ----------------------------------------------------- |\n| \"Find notes about X\"                | `global_search` first, then `search_memos` for detail |\n| \"Find notes with exact phrase\"      | `search_memos` with `search_type=\"full_text\"`         |\n| \"What do I know about X\" (semantic) | `search_memos` with `search_type=\"semantic\"`          |\n| \"Show me recent memos\"              | `list_memos`                                          |\n| \"What topics do I write about\"      | `list_supertags`                                      |\n| \"Find a document / PDF\"             | `list_documents` with `q` filter                      |\n| \"Save / record / note down X\"       | `create_memo`                                         |\n| \"Explore my knowledge graph\"        | `list_entities` → `get_entity_graph`                  |\n| \"Which workspace should I use\"      | `list_workspaces` → `get_current_workspace`           |\n\n---\n\n## Recommended Workflows\n\n### Answer \"What do I know about X\":\n\n1. `get_current_workspace()` to confirm workspace scope\n2. `global_search(query=\"X\")` for a cross-type overview\n3. If more detail needed: `search_memos(query=\"X\", search_type=\"semantic\")`\n4. If a relevant supertag exists: `list_supertags(q=\"X\")` to expand further\n\n### Help user record new information:\n\n1. Confirm intent, then call `create_memo(content=\"...\")`\n2. Tell the user the note was created and show the `memo_id`\n3. Structure content well: first line = core topic, subsequent lines = details\n\n### Explore user's knowledge structure:\n\n1. `list_supertags()` for a thematic overview\n2. `list_entities()` to understand main knowledge graph nodes\n3. `get_entity_graph(entity_id)` for entities of interest\n\nFile v1.0.1:README.md\n\n# Miremo Skill for OpenClaw\n\nAccess your [Miremo](https://miremoapp.com) notes, documents, supertags, and knowledge graph directly from OpenClaw via MCP.\n\n## Prerequisites\n\nThis skill requires the Miremo MCP server to be connected in OpenClaw. Complete the following setup first.\n\n---\n\n## Step 1: Generate a Miremo API Key\n\n1. Open the Miremo app → **Settings → Preferences**\n2. Find the **API Key** section and click **New API Key**\n3. Enter a name (e.g. `OpenClaw`) and confirm\n4. **Copy the key immediately** (format: `sk-miremo-xxxx`) — it won't be shown again\n\n---\n\n## Step 2: Add the MCP Server to OpenClaw\n\nEdit `~/.openclaw/openclaw.json` and add under `mcp.servers`:\n\n```json\n{\n  \"mcp\": {\n    \"servers\": {\n      \"miremo\": {\n        \"type\": \"http\",\n        \"url\": \"https://api.miremoapp.com/mcp/v1/mcp\",\n        \"headers\": {\n          \"Authorization\": \"Bearer sk-miremo-YOUR_KEY_HERE\"\n        }\n      }\n    }\n  }\n}\n```\n\n> For local development, use `http://localhost:8000/mcp/v1/mcp` as the URL.\n\n---\n\n## Step 3: Install This Skill\n\n```bash\nopenclaw skills install miremo\n```\n\nStart a new OpenClaw session and the Miremo tools will be available.\n\n---\n\n## Available Tools\n\n| Tool | Description |\n|---|---|\n| `search_memos` | Semantic / full-text / hybrid search across memos |\n| `list_memos` | Paginated list of memos |\n| `create_memo` | Create a new memo |\n| `list_supertags` | List / search topic supertags |\n| `list_documents` | List uploaded documents |\n| `global_search` | Cross-type search (memos + docs + supertags) |\n| `get_entity_graph` | Get 1-hop knowledge graph for an entity |\n| `list_entities` | List AI-extracted knowledge graph entities |\n| `list_workspaces` | List all workspaces accessible to the current user |\n| `get_current_workspace` | Get effective workspace resolution (`explicit` / `default`) |\n\nWorkspace resolution rules:\n- If `workspace_id` is provided in tool arguments, the operation runs in that workspace.\n- If `workspace_id` is omitted, the operation runs only in the user's default workspace.\n\n---\n\n## Security Notes\n\n- Treat your API Key like a password — never commit it to version control\n- Revoke unused keys anytime in Miremo settings\n- Create separate keys for different clients for independent management\n\nFile v1.0.1:_meta.json\n\n{\n  \"ownerId\": \"kn7exb2zewsk68a4cm9sb7r3nx8425fc\",\n  \"slug\": \"miremo\",\n  \"version\": \"1.0.1\",\n  \"publishedAt\": 1777534114932\n}\n\nFile v1.0.1:skill-card.md\n\n## Description: <br>\nAccess the user's personal Miremo knowledge base to search notes, inspect documents and tags, explore knowledge graph entities, and save new information. <br>\n\nThis skill is ready for commercial/non-commercial use. <br>\n\n## Publisher: <br>\n[hansenz42](https://clawhub.ai/user/hansenz42) <br>\n\n### License/Terms of Use: <br>\nMIT-0 <br>\n\n\n## Use Case: <br>\nOpenClaw users use this skill to work with their own Miremo notes, documents, supertags, workspaces, and knowledge graph through a connected Miremo MCP server. It supports personal knowledge research, exact lookups, workspace-aware browsing, and creating new memos. <br>\n\n### Deployment Geography for Use: <br>\nGlobal <br>\n\n## Known Risks and Mitigations: <br>\nRisk: The skill requires a user-provided Miremo API key and can access the user's Miremo knowledge base. <br>\nMitigation: Use a dedicated Miremo API key, keep OpenClaw configuration out of untrusted version control and backups, and revoke the key when the skill is no longer needed. <br>\nRisk: A misconfigured MCP server URL could send requests or credentials to an unintended endpoint. <br>\nMitigation: Verify that the MCP URL is the official Miremo endpoint or a local server you control before installing the skill. <br>\n\n\n## Reference(s): <br>\n- [ClawHub skill page](https://clawhub.ai/hansenz42/miremo) <br>\n- [Publisher profile](https://clawhub.ai/user/hansenz42) <br>\n- [Miremo homepage](https://www.miremoapp.com) <br>\n\n\n## Skill Output: <br>\n**Output Type(s):** [Text, Markdown, Guidance, Configuration] <br>\n**Output Format:** [Markdown responses with MCP tool guidance and configuration snippets] <br>\n**Output Parameters:** [1D] <br>\n**Other Properties Related to Output:** [Requires a connected Miremo MCP server and user-provided API key.] <br>\n\n## Skill Version(s): <br>\n1.0.1 (source: server-resolved release metadata) <br>\n\n## Ethical Considerations: <br>\nUsers should evaluate whether this skill is appropriate for their environment, review any generated or modified files before relying on them, and apply their organization's safety, security, and compliance requirements before deployment. <br>\n\nArchive v1.0.0: 3 files, 4196 bytes\n\nFiles: README.md (1890b), SKILL.md (6438b), _meta.json (125b)\n\nFile v1.0.0:SKILL.md\n\n---\nname: miremo\ndescription: Access the user's personal Miremo knowledge base — search notes, look up what they know about a topic, browse their documents and tags, explore their knowledge graph, or save new information. Use when the user says \"find my notes\", \"what do I know about\", \"search my knowledge base\", \"look it up in Miremo\", \"save/record/remember this\", \"what topics have I written about\", or \"show my notes on X\". NOT for general web searches or queries about topics not stored in the user's own notes.\nhomepage: https://miremoapp.com\nmetadata: {\"openclaw\": {\"emoji\": \"📓\", \"requires\": {\"config\": [\"mcp.servers\"]}}}\n---\n\n# Miremo Skill\n\n**Prerequisite:** The Miremo MCP server must be connected in OpenClaw before this skill's tools are available. See the README for setup instructions.\n\nMiremo is an AI note-taking tool. It stores the user's memos, documents, supertags (topic tags with rich content), and AI-extracted knowledge graph entities. All tools only access the currently authenticated user's own data.\n\n---\n\n## Research Strategy\n\nWhen the user asks about their knowledge, choose one of three research modes and follow it through completely before giving a final answer. **Never give up after one failed search.**\n\n### Mode A — Browse (user wants an overview)\nTriggers: \"what notes do I have\", \"show me my recent notes\", \"what have I been writing about\", \"give me an overview\"\n\nSteps:\n1. `list_memos(page_size=30)` to sample recent memos\n2. `list_supertags()` to see all topic tags at a glance\n3. Synthesize a structured overview from both results\n\n### Mode B — Topic Research (most common)\nTriggers: \"what do I know about X\", \"find notes about X\", \"anything related to X\", \"my thoughts on X\"\n\nSteps:\n1. `global_search(query=\"X\")` — cross-type overview (memos + docs + supertags)\n2. `search_memos(query=\"X\", search_type=\"semantic\")` for deeper semantic matches\n3. If a relevant supertag appears: `list_supertags(q=\"X\")` to expand via that tag\n4. For people, concepts, or events that matter: `list_entities()` → `get_entity_graph(entity_id)` to explore relationships\n\n**Iteration rules (critical):**\n- If initial search returns few results, retry with synonyms, English equivalents, or split keywords before concluding \"nothing found\"\n- Lower `similarity_threshold` to 0.25–0.35 on the second attempt\n- `hit_text` is only a snippet — do not draw conclusions from it alone; use `global_search` to confirm scope across types\n- Declare \"no relevant notes found\" only after at least 2–3 distinct search strategies all return empty\n\n### Mode C — Exact Lookup\nTriggers: \"do I have a note about X\", \"find the exact note where I wrote Y\", \"the note titled Z\"\n\nSteps:\n1. `search_memos(query=\"Y\", search_type=\"full_text\")` for precise phrase matching\n2. If not found, fall back to Mode B with semantic search\n\n---\n\n## Available Tools\n\n### Search Tools\n\n**`search_memos`** — Search memos by keyword or natural language.\n- `query`: search text, e.g. \"Python async programming notes\"\n- `limit`: max results (default 10, recommend ≤ 20)\n- `search_type`: `\"hybrid\"` (default, most comprehensive) | `\"semantic\"` (natural language) | `\"full_text\"` (exact match)\n- Returns: `id`, `hit_text`, `similarity_score`, `created_at`, `modified_at`\n\n**`global_search`** — Cross-type search across memos, documents, and supertags.\n- `query`: search text\n- `limit`: max results per type (default 10)\n- `include_memos` / `include_documents` / `include_supertags`: toggle each type (all true by default)\n- Returns items with `type` (`\"memo\"` / `\"document\"` / `\"supertag\"`), `id`, `title`, `description`, `score`\n\n### List Tools\n\n**`list_memos`** — Paginated list of memos.\n- `page_index`, `page_size` (default 20), `q` (optional fuzzy filter)\n- Returns: `{ items: [{id, outline_preview, created_at, ...}], total, page_size, page_index }`\n\n**`list_supertags`** — List topic supertags.\n- `q` (optional filter), `page_index`, `page_size` (default 50)\n- Default page size of 50 usually retrieves all tags in one call\n\n**`list_documents`** — List uploaded documents (PDFs, files).\n- `q` (optional name filter), `page_index`, `page_size` (default 20)\n- Returns: `document_id`, `name`, `created_at`, `modified_at`, `status`\n\n### Create Tools\n\n**`create_memo`** — Create a new memo.\n- `content`: memo body, multi-line supported. First line becomes the top-level title; subsequent lines become sub-content.\n- Returns: `{ memo_id: \"<new UUID>\" }`\n- After creation, vectorization and knowledge graph updates run automatically in the background.\n\n### Knowledge Graph Tools\n\n**`list_entities`** — List AI-extracted knowledge graph entities.\n- `entity_type` (optional): `person`, `concept`, `place`, `organization`, `event`, etc.\n- `page_index`, `page_size` (default 20)\n- Omit `entity_type` to get all types mixed\n\n**`get_entity_graph`** — Get an entity's 1-hop relationship graph.\n- `entity_id`: obtain via `list_entities` first\n- Returns: `{ entity: {entity_id, name, entity_type, summary}, related_entities: [...], relationships: [{source_entity_id, target_entity_id, description}] }`\n\n---\n\n## When to Use Which Tool\n\n| User intent | Recommended tool |\n|---|---|\n| \"Find notes about X\" | `global_search` first, then `search_memos` for detail |\n| \"Find notes with exact phrase\" | `search_memos` with `search_type=\"full_text\"` |\n| \"What do I know about X\" (semantic) | `search_memos` with `search_type=\"semantic\"` |\n| \"Show me recent memos\" | `list_memos` |\n| \"What topics do I write about\" | `list_supertags` |\n| \"Find a document / PDF\" | `list_documents` with `q` filter |\n| \"Save / record / note down X\" | `create_memo` |\n| \"Explore my knowledge graph\" | `list_entities` → `get_entity_graph` |\n\n---\n\n## Recommended Workflows\n\n### Answer \"What do I know about X\":\n1. `global_search(query=\"X\")` for a cross-type overview\n2. If more detail needed: `search_memos(query=\"X\", search_type=\"semantic\")`\n3. If a relevant supertag exists: `list_supertags(q=\"X\")` to expand further\n\n### Help user record new information:\n1. Confirm intent, then call `create_memo(content=\"...\")`\n2. Tell the user the note was created and show the `memo_id`\n3. Structure content well: first line = core topic, subsequent lines = details\n\n### Explore user's knowledge structure:\n1. `list_supertags()` for a thematic overview\n2. `list_entities()` to understand main knowledge graph nodes\n3. `get_entity_graph(entity_id)` for entities of interest\n\nFile v1.0.0:README.md\n\n# Miremo Skill for OpenClaw\n\nAccess your [Miremo](https://miremoapp.com) notes, documents, supertags, and knowledge graph directly from OpenClaw via MCP.\n\n## Prerequisites\n\nThis skill requires the Miremo MCP server to be connected in OpenClaw. Complete the following setup first.\n\n---\n\n## Step 1: Generate a Miremo API Key\n\n1. Open the Miremo app → **Settings → Preferences**\n2. Find the **API Key** section and click **New API Key**\n3. Enter a name (e.g. `OpenClaw`) and confirm\n4. **Copy the key immediately** (format: `sk-miremo-xxxx`) — it won't be shown again\n\n---\n\n## Step 2: Add the MCP Server to OpenClaw\n\nEdit `~/.openclaw/openclaw.json` and add under `mcp.servers`:\n\n```json\n{\n  \"mcp\": {\n    \"servers\": {\n      \"miremo\": {\n        \"type\": \"sse\",\n        \"url\": \"https://v.miremoapp.com/api/mcp/v1/sse\",\n        \"headers\": {\n          \"Authorization\": \"Bearer sk-miremo-YOUR_KEY_HERE\"\n        }\n      }\n    }\n  }\n}\n```\n\n> For local development, use `http://localhost:8000/mcp/v1/sse` as the URL.\n\n---\n\n## Step 3: Install This Skill\n\n```bash\nopenclaw skills install miremo\n```\n\nStart a new OpenClaw session and the Miremo tools will be available.\n\n---\n\n## Available Tools\n\n| Tool | Description |\n|---|---|\n| `search_memos` | Semantic / full-text / hybrid search across memos |\n| `list_memos` | Paginated list of memos |\n| `create_memo` | Create a new memo |\n| `list_supertags` | List / search topic supertags |\n| `list_documents` | List uploaded documents |\n| `global_search` | Cross-type search (memos + docs + supertags) |\n| `get_entity_graph` | Get 1-hop knowledge graph for an entity |\n| `list_entities` | List AI-extracted knowledge graph entities |\n\n---\n\n## Security Notes\n\n- Treat your API Key like a password — never commit it to version control\n- Revoke unused keys anytime in Miremo settings\n- Create separate keys for different clients for independent management\n\nFile v1.0.0:_meta.json\n\n{\n  \"ownerId\": \"kn7exb2zewsk68a4cm9sb7r3nx8425fc\",\n  \"slug\": \"miremo\",\n  \"version\": \"1.0.0\",\n  \"publishedAt\": 1777359661553\n}","readmeExcerpt":"Skill: Miremo Research Skill Owner: hansenz42 Summary: Access the user's personal Miremo knowledge base and reusable method skills — search notes, look up what they know about a topic, browse documents and tags, explore their knowledge graph, save new information, or retrieve the user's Miremo Skill materials. Tags: latest:1.0.2 Version history: v1.0.2 | 2026-07-08T03:06:26.604Z | user miremo v1.0.2 - Expanded descri","codeSnippets":[],"executableExamples":[{"language":"json","snippet":"{\n  \"mcp\": {\n    \"servers\": {\n      \"miremo\": {\n        \"type\": \"http\",\n        \"url\": \"https://api.miremoapp.com/mcp/v1/mcp\",\n        \"headers\": {\n          \"Authorization\": \"Bearer sk-miremo-YOUR_KEY_HERE\"\n        }\n      }\n    }\n  }\n}"},{"language":"bash","snippet":"openclaw skills install miremo"},{"language":"json","snippet":"{\n  \"mcp\": {\n    \"servers\": {\n      \"miremo\": {\n        \"type\": \"http\",\n        \"url\": \"https://api.miremoapp.com/mcp/v1/mcp\",\n        \"headers\": {\n          \"Authorization\": \"Bearer sk-miremo-YOUR_KEY_HERE\"\n        }\n      }\n    }\n  }\n}"},{"language":"bash","snippet":"openclaw skills install miremo"},{"language":"json","snippet":"{\n  \"mcp\": {\n    \"servers\": {\n      \"miremo\": {\n        \"type\": \"sse\",\n        \"url\": \"https://v.miremoapp.com/api/mcp/v1/sse\",\n        \"headers\": {\n          \"Authorization\": \"Bearer sk-miremo-YOUR_KEY_HERE\"\n        }\n      }\n    }\n  }\n}"},{"language":"bash","snippet":"openclaw skills install miremo"}],"parameters":null,"dependencies":[],"permissions":[],"extractedFiles":[{"path":"SKILL.md","content":"---\nname: miremo\ndescription: Access the user's personal Miremo knowledge base and reusable method skills — search notes, look up what they know about a topic, browse documents and tags, explore their knowledge graph, save new information, or retrieve the user's Miremo Skill materials. Use when the user says \"find my notes\", \"what do I know about\", \"search my knowledge base\", \"look it up in Miremo\", \"save/record/remember this\", \"what topics have I written about\", \"show my notes on X\", \"use my Miremo skill\", \"use my method/template/workflow\", or \"look up my skill instructions\". NOT for general web searches or queries about topics not stored in the user's own Miremo data.\nhomepage: https://www.miremoapp.com\nmetadata:\n  { \"openclaw\": { \"emoji\": \"📓\", \"requires\": { \"config\": [\"mcp.servers\"] } } }\n---\n\n# Miremo Skill\n\n**Prerequisite:** The Miremo MCP server must be connected in OpenClaw before this skill's tools are available. See the README for setup instructions.\n\nMiremo is an AI note-taking tool. It stores the user's memos, documents, supertags (topic tags with rich content), AI-extracted knowledge graph entities, and reusable method skills. All tools only access the currently authenticated user's own data.\n\nWorkspace behavior:\n\n- If `workspace_id` is provided, tools operate in that workspace (with permission checks).\n- If `workspace_id` is omitted, tools operate only in the user's default workspace.\n- Use `list_workspaces` and `get_current_workspace` to inspect available workspaces and the active workspace resolution.\n\n---\n\n## Research Strategy\n\nWhen the user asks about their knowledge or methods, choose one of four modes and follow it through completely before giving a final answer. **Never give up after one failed search.**\n\n### Mode A — Browse (user wants an overview)\n\nTriggers: \"what notes do I have\", \"show me my recent notes\", \"what have I been writing about\", \"give me an overview\"\n\nSteps:\n\n1. `list_workspaces()` to understand all accessible workspaces\n2. `get_current_workspace()` to confirm default workspace before browsing\n3. `list_memos(page_size=30)` to sample recent memos\n4. `list_supertags()` to see all topic tags at a glance\n5. Synthesize a structured overview from both results\n\n### Mode B — Topic Research (most common)\n\nTriggers: \"what do I know about X\", \"find notes about X\", \"anything related to X\", \"my thoughts on X\"\n\nSteps:\n\n1. `list_workspaces()` when user asks for cross-workspace research\n2. `global_search(query=\"X\")` — cross-type overview (memos + docs + supertags)\n3. `search_memos(query=\"X\", search_type=\"semantic\")` for deeper semantic matches\n4. If a relevant supertag appears: `list_supertags(q=\"X\")` to expand via that tag\n5. For people, concepts, or events that matter: `list_entities()` → `get_entity_graph(entity_id)` to explore relationships\n\n**Iteration rules (critical):**\n\n- If initial search returns few results, retry with synonyms, English equivalents, or split keywords before concluding \"nothing found\"\n- Lower `similar"},{"path":"README.md","content":"# Miremo Skill for OpenClaw\n\nAccess your [Miremo](https://miremoapp.com) notes, documents, supertags, knowledge graph, and reusable method skills directly from OpenClaw via MCP.\n\n## Prerequisites\n\nThis skill requires the Miremo MCP server to be connected in OpenClaw. Complete the following setup first.\n\n---\n\n## Step 1: Generate a Miremo API Key\n\n1. Open the Miremo app → **Settings → Preferences**\n2. Find the **API Key** section and click **New API Key**\n3. Enter a name (e.g. `OpenClaw`) and confirm\n4. **Copy the key immediately** (format: `sk-miremo-xxxx`) — it won't be shown again\n\n---\n\n## Step 2: Add the MCP Server to OpenClaw\n\nEdit `~/.openclaw/openclaw.json` and add under `mcp.servers`:\n\n```json\n{\n  \"mcp\": {\n    \"servers\": {\n      \"miremo\": {\n        \"type\": \"http\",\n        \"url\": \"https://api.miremoapp.com/mcp/v1/mcp\",\n        \"headers\": {\n          \"Authorization\": \"Bearer sk-miremo-YOUR_KEY_HERE\"\n        }\n      }\n    }\n  }\n}\n```\n\n> For local development, use `http://localhost:8000/mcp/v1/mcp` as the URL.\n\n---\n\n## Step 3: Install This Skill\n\n```bash\nopenclaw skills install miremo\n```\n\nStart a new OpenClaw session and the Miremo tools will be available.\n\n---\n\n## Available Tools\n\n| Tool | Description |\n|---|---|\n| `search_memos` | Semantic / full-text / hybrid search across memos |\n| `list_memos` | Paginated list of memos |\n| `create_memo` | Create a new memo |\n| `list_supertags` | List / search topic supertags |\n| `list_collections` | List uploaded document collections |\n| `get_collection_outline` | Get a collection's structured section outline |\n| `get_document_section` | Read a specific document section |\n| `global_search` | Cross-type search (memos + docs + supertags) |\n| `get_entity_graph` | Get 1-hop knowledge graph for an entity |\n| `list_entities` | List AI-extracted knowledge graph entities |\n| `list_workspaces` | List all workspaces accessible to the current user |\n| `get_current_workspace` | Get effective workspace resolution (`explicit` / `default`) |\n| `list_method_skills` | List reusable Miremo method/workflow/template skills |\n| `search_method_skills` | Search method skills by task or keyword |\n| `get_method_skill` | Read a method skill as SKILL.md-like markdown or structured JSON |\n\nWorkspace resolution rules:\n- If `workspace_id` is provided in tool arguments, the operation runs in that workspace.\n- If `workspace_id` is omitted, the operation runs only in the user's default workspace.\n\n---\n\n## Security Notes\n\n- Treat your API Key like a password — never commit it to version control\n- Revoke unused keys anytime in Miremo settings\n- Create separate keys for different clients for independent management"},{"path":"_meta.json","content":"{\n  \"ownerId\": \"kn7exb2zewsk68a4cm9sb7r3nx8425fc\",\n  \"slug\": \"miremo\",\n  \"version\": \"1.0.2\",\n  \"publishedAt\": 1783479986604\n}"},{"path":"skill-card.md","content":"## Description:\n\nAccess the user's personal Miremo knowledge base and reusable method skills to search notes, browse documents and tags, explore the knowledge graph, save new information, and retrieve method materials.\n\nThis skill is ready for commercial/non-commercial use.\n\n## Publisher:\n\n[hansenz42](https://clawhub.ai/user/hansenz42)\n\n### License/Terms of Use:\n\nMIT-0\n\n## Use Case:\n\nExternal users and developers use this skill to connect OpenClaw to their own Miremo account, research personal notes and documents, retrieve reusable method skills, and create new memos.\n\n### Deployment Geography for Use:\n\nGlobal\n\n## Known Risks and Mitigations:\n\nRisk: The connected agent can search and read notes, documents, tags, method skills, and knowledge graph data in the authenticated Miremo account.\n\nMitigation: Install only when the user trusts Miremo and the agent session with that account's content; use a dedicated API key for this integration.\n\nRisk: The skill can create new memos in the connected Miremo workspace.\n\nMitigation: Confirm user intent before recording information and review created memo IDs or content when write actions matter.\n\nRisk: The Miremo API key grants access through the configured MCP server if exposed.\n\nMitigation: Keep the API key out of version control, use separate keys for different clients, and revoke unused keys in Miremo settings.\n\n## Reference(s):\n\n- [Miremo homepage](https://www.miremoapp.com)\n- [ClawHub skill page](https://clawhub.ai/hansenz42/skills/miremo)\n- [ClawHub publisher profile](https://clawhub.ai/user/hansenz42)\n- [README.md](artifact/README.md)\n\n## Skill Output:\n\n**Output Type(s):** [Text, Markdown, Configuration, Guidance]\n\n**Output Format:** [Markdown or plain text with retrieved Miremo content, method-skill material, and concise tool-result summaries]\n\n**Output Parameters:** [1D]\n\n**Other Properties Related to Output:** [May include memo IDs, workspace context, document section summaries, knowledge graph relationships, and setup configuration snippets.]\n\n## Skill Version(s):\n\n1.0.2 (source: server release evidence)\n\n## Ethical Considerations:\n\nUsers should evaluate whether this skill is appropriate for their environment, review any generated or modified files before relying on them, and apply their organization's safety, security, and compliance requirements before deployment."}],"languages":[],"docsSourceLabel":"CLAWHUB","editorialOverview":null,"editorialQuality":{"score":100,"threshold":65,"status":"thin","wordCount":1676,"uniquenessScore":38,"reasons":["uniqueness-below-45"]}},"media":{"evidence":{"source":"no-media","verified":false,"confidence":"low","updatedAt":"2026-10-11T21:11:33.667Z","emptyReason":"No screenshots, media assets, or demo links are available."},"primaryImageUrl":null,"mediaAssetCount":0,"assets":[],"demoUrl":null},"ownerResources":{"evidence":{"source":"unclaimed","verified":false,"confidence":"low","updatedAt":"2026-10-11T21:11:33.667Z","emptyReason":"This page has not been claimed by the agent owner."},"hasCustomPage":false,"customPageUpdatedAt":null,"customLinks":[],"structuredLinks":{"docsUrl":null,"demoUrl":null,"supportUrl":null,"pricingUrl":null,"statusUrl":null},"customPage":null},"relatedAgents":{"evidence":{"source":"protocol-neighbors","verified":false,"confidence":"medium","updatedAt":"2026-10-12T14:52:58.140Z","emptyReason":null},"items":[{"id":"8ebccd8e-3863-4187-8355-c3f14e1f9edf","entityType":"agent","canonicalPath":"/agent/iofficeai-aionui","slug":"iofficeai-aionui","name":"AionUi","description":"Free, local, open-source 24/7 Cowork app and OpenClaw for Gemini CLI, Claude Code, Codex, OpenCode, Qwen Code, Goose CLI, Auggie, and more | 🌟 Star if you like it!","url":"https://github.com/iOfficeAI/AionUi","homepage":"https://www.aionui.com","source":"GITHUB_REPOS","protocols":["MCP","OPENCLAW"],"capabilities":[],"safetyScore":100,"overallRank":70,"updatedAt":"2026-10-09T19:11:12.944Z","createdAt":"2026-02-25T03:38:16.584Z","downloads":null},{"id":"b917f68a-ebff-438e-84f8-3f4b2494c0bc","entityType":"agent","canonicalPath":"/agent/activepieces-activepieces","slug":"activepieces-activepieces","name":"activepieces","description":"AI Agents & MCPs & AI Workflow Automation • (~400 MCP servers for AI agents) • AI Automation / AI Agent with MCPs • AI Workflows & AI Agents • MCPs for AI Agents","url":"https://github.com/activepieces/activepieces","homepage":"https://www.activepieces.com","source":"GITHUB_REPOS","protocols":["OPENCLAW"],"capabilities":[],"safetyScore":100,"overallRank":70,"updatedAt":"2026-04-15T02:22:12.426Z","createdAt":"2026-02-25T03:38:12.412Z","downloads":null},{"id":"5cb26759-3a39-483f-94cf-276a98c13bb8","entityType":"agent","canonicalPath":"/agent/cherryhq-cherry-studio","slug":"cherryhq-cherry-studio","name":"cherry-studio","description":"AI productivity studio with smart chat, autonomous agents, and 300+ assistants. Unified access to frontier LLMs","url":"https://github.com/CherryHQ/cherry-studio","homepage":"https://cherry-ai.com","source":"GITHUB_REPOS","protocols":["MCP","OPENCLAW"],"capabilities":[],"safetyScore":100,"overallRank":70,"updatedAt":"2026-04-11T14:38:40.986Z","createdAt":"2026-02-25T03:38:19.379Z","downloads":null},{"id":"6f6582d0-5d76-4f0f-b81d-86520247950b","entityType":"agent","canonicalPath":"/agent/copilotkit-copilotkit","slug":"copilotkit-copilotkit","name":"CopilotKit","description":"The Frontend for Agents & Generative UI. React + Angular","url":"https://github.com/CopilotKit/CopilotKit","homepage":"https://docs.copilotkit.ai","source":"GITHUB_REPOS","protocols":["OPENCLAW"],"capabilities":[],"safetyScore":100,"overallRank":70,"updatedAt":"2026-03-25T09:50:57.846Z","createdAt":"2026-02-25T03:39:14.617Z","downloads":null}],"links":{"hub":"/agent","source":"/agent/source/clawhub","protocols":[{"label":"OpenClaw","href":"/agent/protocol/openclew"}]}}}