{"id":"acbf5219-38b6-4b23-8845-b032e3982f1a","slug":"javicasper-memory-forge","name":"memory-forge","description":"Continuous learning system that forges knowledge from work sessions into permanent memory.\nUse when: (1) after completing non-trivial debugging or investigation, (2) discovering\npatterns not obvious from documentation, (3) finding workarounds worth preserving,\n(4) \"what did we learn?\", (5) \"save this pattern\", (6) \"extract a skill\".\nSupports monorepos with distributed context files. CLI-agnostic (works with Claude Code,\nOpenCode, Codex, Cursor, and any tool supporting the Agent Skills standard).","canonicalUrl":"https://xpersona.co/skill/javicasper-memory-forge","sourceUrl":"https://github.com/javicasper/memory-forge","homepage":null,"source":"GITHUB_OPENCLEW","vendor":{"slug":"javicasper","label":"Javicasper","url":"https://github.com/javicasper/memory-forge"},"protocols":["MCP"],"capabilities":["be"],"trustScore":null,"trustConfidence":"unknown","artifactCount":0,"benchmarkCount":0,"lastRelease":null,"freshnessAt":"2026-04-14T22:27:06.745Z","freshnessLabel":"Apr 14, 2026","securityReviewed":true,"openapiReady":true,"stats":[{"label":"Trust score","value":"Unknown"},{"label":"Compatibility","value":"MCP"},{"label":"Freshness","value":"Apr 14, 2026"},{"label":"Vendor","value":"Javicasper"},{"label":"Artifacts","value":"0"},{"label":"Benchmarks","value":"0"},{"label":"Last release","value":"Unpublished"}],"factsPreview":[{"factKey":"docs_crawl","category":"integration","label":"Crawlable docs","value":"6 indexed pages on the official domain","href":"https://github.com/login?return_to=https%3A%2F%2Fgithub.com%2Fopenclaw%2Fskills%2Ftree%2Fmain%2Fskills%2Fasleep123%2Fcaldav-calendar","sourceUrl":"https://github.com/login?return_to=https%3A%2F%2Fgithub.com%2Fopenclaw%2Fskills%2Ftree%2Fmain%2Fskills%2Fasleep123%2Fcaldav-calendar","sourceType":"search_document","confidence":"medium","observedAt":"2026-04-15T05:03:46.393Z","isPublic":true},{"factKey":"vendor","category":"vendor","label":"Vendor","value":"Javicasper","href":"https://github.com/javicasper/memory-forge","sourceUrl":"https://github.com/javicasper/memory-forge","sourceType":"profile","confidence":"medium","observedAt":"2026-04-14T22:27:06.746Z","isPublic":true},{"factKey":"protocols","category":"compatibility","label":"Protocol compatibility","value":"MCP","href":"https://xpersona.co/api/v1/agents/javicasper-memory-forge/contract","sourceUrl":"https://xpersona.co/api/v1/agents/javicasper-memory-forge/contract","sourceType":"contract","confidence":"high","observedAt":"2026-02-24T19:43:49.619Z","isPublic":true},{"factKey":"auth_modes","category":"compatibility","label":"Auth modes","value":"mcp, api_key","href":"https://xpersona.co/api/v1/agents/javicasper-memory-forge/contract","sourceUrl":"https://xpersona.co/api/v1/agents/javicasper-memory-forge/contract","sourceType":"contract","confidence":"high","observedAt":"2026-02-24T19:43:49.619Z","isPublic":true},{"factKey":"schema_refs","category":"artifact","label":"Machine-readable schemas","value":"OpenAPI or schema references published","href":"https://github.com/javicasper/memory-forge#input","sourceUrl":"https://xpersona.co/api/v1/agents/javicasper-memory-forge/contract","sourceType":"contract","confidence":"high","observedAt":"2026-02-24T19:43:49.619Z","isPublic":true},{"factKey":"handshake_status","category":"security","label":"Handshake status","value":"UNKNOWN","href":"https://xpersona.co/api/v1/agents/javicasper-memory-forge/trust","sourceUrl":"https://xpersona.co/api/v1/agents/javicasper-memory-forge/trust","sourceType":"trust","confidence":"medium","observedAt":null,"isPublic":true}],"highlights":["Schema refs published","Trust evidence available"],"agentCard":{"name":"memory-forge","description":"Continuous learning system that forges knowledge from work sessions into permanent memory.\nUse when: (1) after completing non-trivial debugging or investigation, (2) discovering\npatterns not obvious from documentation, (3) finding workarounds worth preserving,\n(4) \"what did we learn?\", (5) \"save this pattern\", (6) \"extract a skill\".\nSupports monorepos with distributed context files. CLI-agnostic (works with Claude Code,\nOpenCode, Codex, Cursor, and any tool supporting the Agent Skills standard).","source":"GITHUB_OPENCLEW","sourceId":"github:1144142805","repository":"https://github.com/javicasper/memory-forge","documentation":"https://xpersona.co/skill/javicasper-memory-forge/agent/javicasper-memory-forge","protocols":["MCP"],"capabilities":["be"],"languages":["typescript"],"install":{"command":"git clone https://github.com/javicasper/memory-forge.git","ecosystem":"git"},"examples":[{"kind":"example","language":"text","snippet":"┌─────────────────────────────────────────────────────────────┐\n│ STEP 1: Is there extractable knowledge?                     │\n│                                                             │\n│ Ask yourself:                                               │\n│ • Did this require non-trivial investigation?               │\n│ • Did I discover something not obvious from docs?           │\n│ • Would this help someone facing a similar situation?       │\n│                                                             │\n│ If NO to all → STOP (nothing to extract)                    │\n│ If YES to any → Continue to Step 2                          │\n└─────────────────────────────────────────────────────────────┘\n                              │\n                              ▼\n┌─────────────────────────────────────────────────────────────┐\n│ STEP 2: What type of knowledge is it?                       │\n│                                                             │\n│ A) ERROR/WORKAROUND with specific trigger conditions?       │\n│    → Create a SKILL (universal SKILL.md format)             │\n│    Examples:                                                │\n│    - \"MongoDB connection pool exhaustion fix\"               │\n│    - \"TypeScript circular dependency resolution\"            │\n│    - \"AWS Lambda cold start optimization\"                   │\n│                                                             │\n│ B) ARCHITECTURAL PATTERN or CONVENTION?                     │\n│    → Update context file (CLAUDE.md and/or AGENTS.md)       │\n│    Examples:                                                │\n│    - \"All repositories use this interface pattern\"         │\n│    - \"Events must have static EVENT_NAME constant\"         │\n│    - \"Use Libio3 for all HTTP requests\"                    │\n│                                                             │\n│ C) MODULE-SPECIFIC knowledge (in a monorepo)?               │\n│    → Update the MODULE's context file                       │\n│    Examples:     "},{"kind":"example","language":"text","snippet":"1. Check what exists in the project:\n   - Only CLAUDE.md? → Update CLAUDE.md\n   - Only AGENTS.md? → Update AGENTS.md\n   - Both exist? → Update BOTH to keep them in sync\n   - Neither? → Create based on primary tool:\n     * Claude Code users → Create CLAUDE.md\n     * OpenCode/Codex users → Create AGENTS.md\n     * Unknown → Create AGENTS.md (wider compatibility)\n\n2. For monorepos, apply same logic per directory"}]}}