{"id":"7cc03cc5-0d8a-4d15-bbc2-9ec51d03b73b","slug":"hanzoskill-agent-registry","name":"agent-registry","description":"MANDATORY agent discovery system for token-efficient agent loading. Claude MUST use this skill \ninstead of loading agents directly from ~/.claude/agents/ or .claude/agents/. Provides lazy \nloading via search_agents and get_agent tools. Use when: (1) user task may benefit from \nspecialized agent expertise, (2) user asks about available agents, (3) starting complex \nworkflows that historically used agents. This skill reduces context window usage by ~95% \ncompared to loading all agents upfront.","canonicalUrl":"https://xpersona.co/skill/hanzoskill-agent-registry","sourceUrl":"https://github.com/hanzoskill/agent-registry","homepage":null,"source":"GITHUB_OPENCLEW","vendor":{"slug":"hanzoskill","label":"Hanzoskill","url":"https://github.com/hanzoskill/agent-registry"},"protocols":["OPENCLEW"],"capabilities":["you","python","the"],"trustScore":null,"trustConfidence":"unknown","artifactCount":0,"benchmarkCount":0,"lastRelease":null,"freshnessAt":"2026-04-15T02:13:09.689Z","freshnessLabel":"Apr 15, 2026","securityReviewed":true,"openapiReady":false,"stats":[{"label":"Trust score","value":"Unknown"},{"label":"Compatibility","value":"OpenClaw"},{"label":"Freshness","value":"Apr 15, 2026"},{"label":"Vendor","value":"Hanzoskill"},{"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release","value":"Unpublished"}],"factsPreview":[{"factKey":"docs_crawl","category":"integration","label":"Crawlable docs","value":"6 indexed pages on the official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":"Hanzoskill","href":"https://github.com/hanzoskill/agent-registry","sourceUrl":"https://github.com/hanzoskill/agent-registry","sourceType":"profile","confidence":"medium","observedAt":"2026-04-15T02:13:10.113Z","isPublic":true},{"factKey":"protocols","category":"compatibility","label":"Protocol compatibility","value":"OpenClaw","href":"https://xpersona.co/api/v1/agents/hanzoskill-agent-registry/contract","sourceUrl":"https://xpersona.co/api/v1/agents/hanzoskill-agent-registry/contract","sourceType":"contract","confidence":"medium","observedAt":"2026-04-15T02:13:10.113Z","isPublic":true},{"factKey":"handshake_status","category":"security","label":"Handshake status","value":"UNKNOWN","href":"https://xpersona.co/api/v1/agents/hanzoskill-agent-registry/trust","sourceUrl":"https://xpersona.co/api/v1/agents/hanzoskill-agent-registry/trust","sourceType":"trust","confidence":"medium","observedAt":null,"isPublic":true}],"highlights":["Trust evidence available"],"agentCard":{"name":"agent-registry","description":"MANDATORY agent discovery system for token-efficient agent loading. Claude MUST use this skill \ninstead of loading agents directly from ~/.claude/agents/ or .claude/agents/. Provides lazy \nloading via search_agents and get_agent tools. Use when: (1) user task may benefit from \nspecialized agent expertise, (2) user asks about available agents, (3) starting complex \nworkflows that historically used agents. This skill reduces context window usage by ~95% \ncompared to loading all agents upfront.","source":"GITHUB_OPENCLEW","sourceId":"github:1155213767","repository":"https://github.com/hanzoskill/agent-registry","documentation":"https://xpersona.co/skill/hanzoskill-agent-registry/agent/hanzoskill-agent-registry","protocols":["OPENCLEW"],"capabilities":["you","python","the"],"languages":["typescript"],"install":{"command":"git clone https://github.com/hanzoskill/agent-registry.git","ecosystem":"git"},"examples":[{"kind":"example","language":"text","snippet":"User Request → search_agents(intent) → select best match → get_agent(name) → execute with agent"},{"kind":"example","language":"bash","snippet":"# Step 1: Search for relevant agents\npython scripts/search_agents.py \"code review security authentication\"\n\n# Output:\n# Found 2 matching agents:\n#   1. security-auditor (score: 0.89) - Analyzes code for security vulnerabilities\n#   2. code-reviewer (score: 0.71) - General code review and best practices\n\n# Step 2: Load the best match\npython scripts/get_agent.py security-auditor\n\n# Step 3: Follow loaded agent instructions for the task"}]}}