{"id":81703,"plugin_id":"plugin_asdk_app_6abebbc07294819182ee61dfb4b9f56f","kind":"skill","collection_source":"plugin_package","comparison_source":null,"observed_at":"2026-11-05T01:16:26.891Z","digest":"de4f8abb6a42bb2262da1f182011dc523b18498cd143f450ecfac79d68b21274","against":null,"payload":{"description":"Route a question to the right Clawnify knowledge source before answering or building. Covers how-to-use-Clawnify product docs, your org's company knowledge (brand, pricing, policy, SOPs), a specific client or project's reference, and durable memory. Use whenever a task needs a company fact, a platform how-to, or client-specific context from a connected Clawnify organization.","included_files":[],"name":"clawnify-knowledge","skill_md_contents":"---\nname: clawnify-knowledge\ndescription: Route a question to the right Clawnify knowledge source before answering or building. Covers how-to-use-Clawnify product docs, your org's company knowledge (brand, pricing, policy, SOPs), a specific client or project's reference, and durable memory. Use whenever a task needs a company fact, a platform how-to, or client-specific context from a connected Clawnify organization.\n---\n\n# Clawnify knowledge router\n\nYou are connected to a Clawnify organization through the Clawnify connector.\nSeveral knowledge sources sit behind it, and each answers a different kind of\nquestion. Pick the right one and retrieve from it: these sources are current\nand scoped to this organization, and your training data is neither.\n\n## Route by question type\n\n| The question is about | Use | Notes |\n|---|---|---|\n| How to use Clawnify itself: deploy an app, set up an agent, connections, platform features | docs.clawnify.com | Product docs; `https://docs.clawnify.com/llms.txt` indexes them. Check them before building against the platform. |\n| Which of the org's apps handles something | `clawnify_docs_search` | Searches the org's apps by name and description. |\n| The company's own facts: brand, pricing, policy, SOP, legal, FAQ | `company_knowledge_search`, then `company_knowledge_get` | The org's source of truth, a versioned wiki linked with `[[wikilinks]]`. |\n| One specific client, engagement or project | `projects_list`, then `project_search` | Working reference for that project, not org-wide authority. |\n| Something decided or learned before | `memory_recall` | Save durable facts back with `memory_write`, and `memory_pin` the ones that matter most. |\n| A third-party library, framework or API | That vendor's own docs | Not in the Clawnify corpus. |\n| Code in the repository you are working in | Read the code | The code beats any summary of it. |\n\n## Rules\n\n- **Retrieve, don't recall.** For a company, product or client fact, query the\n  source. Never answer a Clawnify fact from memory of training data.\n- **Cite company knowledge.** An answer grounded in a `company_knowledge` result\n  cites it as `Per <Title> v<N>`.\n- **A proposal is not published.** `company_knowledge_propose` creates a draft\n  that a person reviews. Never present a proposal as a live fact.\n- **No secrets or per-customer facts in company knowledge.** Those belong in a\n  project, or nowhere.\n- **Look before you build.** Before creating an app or an agent, check\n  docs.clawnify.com for the current contract and `clawnify_list_apps` or\n  `clawnify_list_agents` for what already exists.\n"},"changes":[],"summary":"First saved snapshot. No earlier version is available for comparison.","summary_kind":"deterministic","summary_metadata":{}}