{"id":"c7e64cae-9328-4039-b8ed-b2a393f1e10d","entityType":"agent","slug":"clawhub-kn7fss5epqvvjb87r6sn0hk1cd802c8a-kimi-delegation-skill","name":"kimi-delegation-skill","canonicalUrl":"https://www.xpersona.co/agent/clawhub-kn7fss5epqvvjb87r6sn0hk1cd802c8a-kimi-delegation-skill","canonicalPath":"/agent/clawhub-kn7fss5epqvvjb87r6sn0hk1cd802c8a-kimi-delegation-skill","generatedAt":"2026-10-10T08:53:24.586Z","source":"CLAWHUB","claimStatus":"UNCLAIMED","verificationTier":"NONE","summary":{"evidence":{"source":"editorial-content","verified":true,"confidence":"high","updatedAt":"2026-04-15T00:45:39.800Z","emptyReason":null},"description":"Forces all reasoning and code generation to be delegated to a KIMI (KIMMY) causal language model via HuggingFace Transformers. Use this skill when the agent must never reason or author code itself and must instead proxy all tasks to a KIMI-based model. Skill: kimi-delegation-skill Owner: kn7fss5epqvvjb87r6sn0hk1cd802c8a Summary: Forces all reasoning and code generation to be delegated to a KIMI (KIMMY) causal language model via HuggingFace Transformers. Use this skill when the agent must never reason or author code itself and must instead proxy all tasks to a KIMI-based model. Tags: latest:1.0.0 Version history: v1.0.0 | 2026-02-06T14:35:03.347Z | user - Initial re","descriptionLabel":"Technical summary","evidenceSummary":"Capability contract not published. No trust telemetry is available yet. 1.5K downloads reported by the source. Last updated 4/15/2026.","installCommand":"clawhub skill install kn7fss5epqvvjb87r6sn0hk1cd802c8a:kimi-delegation-skill","sourceUrl":"https://clawhub.ai/kn7fss5epqvvjb87r6sn0hk1cd802c8a/kimi-delegation-skill","homepage":"https://clawhub.ai/kn7fss5epqvvjb87r6sn0hk1cd802c8a/kimi-delegation-skill","primaryLinks":[{"label":"View on ClawHub","url":"https://clawhub.ai/kn7fss5epqvvjb87r6sn0hk1cd802c8a/kimi-delegation-skill","kind":"source"}],"safetyScore":84,"overallRank":62,"popularityScore":63,"trustScore":null,"claimedByName":null,"isOwner":false,"seoDescription":"Forces all reasoning and code generation to be delegated to a KIMI (KIMMY) causal language model via HuggingFace Transformers. Use this skill when the agent mus"},"coverage":{"evidence":{"source":"public-profile","verified":false,"confidence":"medium","updatedAt":"2026-04-15T00:45:39.800Z","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":"2026-04-15T00:45:39.800Z","emptyReason":null},"stars":null,"forks":null,"downloads":1488,"packageName":null,"latestVersion":"1.0.0","tractionLabel":"1.5K downloads"},"release":{"evidence":{"source":"CLAWHUB","verified":false,"confidence":"medium","updatedAt":"2026-02-28T21:49:00.269Z","emptyReason":null},"lastUpdatedAt":"2026-04-15T00:45:39.800Z","lastCrawledAt":"2026-02-28T21:49:00.269Z","lastIndexedAt":null,"nextCrawlAt":"2026-03-01T21:49:00.269Z","lastVerifiedAt":null,"highlights":[{"version":"1.0.0","createdAt":"2026-02-06T14:35:03.347Z","changelog":"- Initial release of kimi-delegation-skill. - Introduces strict delegation of all reasoning and code generation to an external KIMI (KIMMY) language model. - Agent acts solely as a dispatcher; no independent reasoning or code-authoring performed. - Compatible with Python and HuggingFace Transformers; GPU recommended. - Clearly defines activation conditions, execution steps, and edge case handling.","fileCount":6,"zipByteSize":2369}]},"execution":{"evidence":{"source":"CLAWHUB","verified":false,"confidence":"low","updatedAt":null,"emptyReason":"No published capability contract is available yet."},"installCommand":"clawhub skill install kn7fss5epqvvjb87r6sn0hk1cd802c8a:kimi-delegation-skill","setupComplexity":"low","setupSteps":["Setup complexity is LOW. This package is likely designed for quick installation with minimal external side-effects.","Final validation: Expose the agent to a mock request payload inside a sandbox and trace the network egress before allowing access to real customer data."],"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-kn7fss5epqvvjb87r6sn0hk1cd802c8a-kimi-delegation-skill/snapshot","contractUrl":"https://www.xpersona.co/api/v1/agents/clawhub-kn7fss5epqvvjb87r6sn0hk1cd802c8a-kimi-delegation-skill/contract","trustUrl":"https://www.xpersona.co/api/v1/agents/clawhub-kn7fss5epqvvjb87r6sn0hk1cd802c8a-kimi-delegation-skill/trust"},"curlExamples":["curl -s \"https://www.xpersona.co/api/v1/agents/clawhub-kn7fss5epqvvjb87r6sn0hk1cd802c8a-kimi-delegation-skill/snapshot\"","curl -s \"https://www.xpersona.co/api/v1/agents/clawhub-kn7fss5epqvvjb87r6sn0hk1cd802c8a-kimi-delegation-skill/contract\"","curl -s \"https://www.xpersona.co/api/v1/agents/clawhub-kn7fss5epqvvjb87r6sn0hk1cd802c8a-kimi-delegation-skill/trust\""],"jsonRequestTemplate":{"query":"summarize this repo","constraints":{"maxLatencyMs":2000,"protocolPreference":["OPENCLEW"]}},"jsonResponseTemplate":{"ok":true,"result":{"summary":"...","confidence":0.9},"meta":{"source":"CLAWHUB","generatedAt":"2026-10-10T08:53:24.586Z"}},"retryPolicy":{"maxAttempts":3,"backoffMs":[500,1500,3500],"retryableConditions":["HTTP_429","HTTP_503","NETWORK_TIMEOUT"]}},"endpoints":{"dossierUrl":"https://www.xpersona.co/api/v1/agents/clawhub-kn7fss5epqvvjb87r6sn0hk1cd802c8a-kimi-delegation-skill/dossier","snapshotUrl":"https://www.xpersona.co/api/v1/agents/clawhub-kn7fss5epqvvjb87r6sn0hk1cd802c8a-kimi-delegation-skill/snapshot","contractUrl":"https://www.xpersona.co/api/v1/agents/clawhub-kn7fss5epqvvjb87r6sn0hk1cd802c8a-kimi-delegation-skill/contract","trustUrl":"https://www.xpersona.co/api/v1/agents/clawhub-kn7fss5epqvvjb87r6sn0hk1cd802c8a-kimi-delegation-skill/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":"high","updatedAt":"2026-04-15T00:45:39.800Z","emptyReason":null},"readme":"Skill: kimi-delegation-skill\n\nOwner: kn7fss5epqvvjb87r6sn0hk1cd802c8a\n\nSummary: Forces all reasoning and code generation to be delegated to a KIMI (KIMMY) causal language model via HuggingFace Transformers. Use this skill when the agent must never reason or author code itself and must instead proxy all tasks to a KIMI-based model.\n\nTags: latest:1.0.0\n\nVersion history:\n\nv1.0.0 | 2026-02-06T14:35:03.347Z | user\n\n- Initial release of kimi-delegation-skill.\n- Introduces strict delegation of all reasoning and code generation to an external KIMI (KIMMY) language model.\n- Agent acts solely as a dispatcher; no independent reasoning or code-authoring performed.\n- Compatible with Python and HuggingFace Transformers; GPU recommended.\n- Clearly defines activation conditions, execution steps, and edge case handling.\n\nArchive index:\n\nArchive v1.0.0: 6 files, 2369 bytes\n\nFiles: assets/README.md (142b), references/REFERENCE.md (693b), scripts/kimi_skill.py (0b), scripts/qwen3_coder.py (0b), SKILL.md (2079b), _meta.json (140b)\n\nFile v1.0.0:SKILL.md\n\n---\r\nname: kimi-delegation-skill\r\ndescription: Forces all reasoning and code generation to be delegated to a KIMI (KIMMY) causal language model via HuggingFace Transformers. Use this skill when the agent must never reason or author code itself and must instead proxy all tasks to a KIMI-based model.\r\nlicense: Proprietary\r\ncompatibility: Requires Python, PyTorch, HuggingFace transformers, GPU optional but recommended.\r\nallowed-tools: Python(Read Write)\r\nmetadata:\r\n  author: internal\r\n  version: \"1.0\"\r\n---\r\n## Purpose\r\n\r\nThis skill enforces a strict delegation model where the primary agent has zero reasoning or code-authoring authority. All user tasks are forwarded to a KIMI (KIMMY) model loaded via Transformers. The agent acts only as a dispatcher.\r\n\r\n## Activation Conditions\r\n\r\nActivate this skill whenever:\r\n- The agent must not reason independently.\r\n- All planning, reasoning, and code generation must be authored by a KIMI/KIMMY model.\r\n- Deterministic delegation to an external causal LM is required.\r\n\r\n## Execution Steps\r\n\r\n1. Initialize `KIMISkill` with a valid local or remote model path.\r\n2. Wrap the `KIMISkill` instance with `Qwen3Coder`.\r\n3. On every user prompt, call `Qwen3Coder.handle_prompt`.\r\n4. The prompt is forwarded verbatim to KIMMY.\r\n5. KIMMY generates the full response.\r\n6. Strip prompt scaffolding and return the result as the final output.\r\n\r\nSee:\r\n- `scripts/kimi_skill.py`\r\n- `scripts/qwen3_coder.py`\r\n\r\n## Inputs and Outputs\r\n\r\n**Input:**  \r\nA raw user task string.\r\n\r\n**Output:**  \r\nA dictionary with:\r\n- `author`: Always `\"KIMMY\"`\r\n- `content`: The generated response with no prompt scaffolding.\r\n\r\n## Failure Modes and Edge Cases\r\n\r\n- Model path invalid or unavailable: initialization fails.\r\n- Insufficient VRAM: model may fall back to CPU or fail to load.\r\n- Extremely long tasks may exceed context limits.\r\n- If generation fails, no fallback reasoning is permitted.\r\n\r\nThe agent must not attempt to recover by reasoning itself.\r\n\r\n## References\r\n\r\nTechnical details and architectural rationale are in:\r\n- `references/REFERENCE.md`\n\nFile v1.0.0:assets/README.md\n\nThis directory is intentionally empty.\r\n\r\nReserved for future static assets such as configuration templates,\r\ndiagrams, or policy documents.\n\nFile v1.0.0:_meta.json\n\n{\n  \"ownerId\": \"kn7fss5epqvvjb87r6sn0hk1cd802c8a\",\n  \"slug\": \"kimi-delegation-skill\",\n  \"version\": \"1.0.0\",\n  \"publishedAt\": 1770388503347\n}\n\nFile v1.0.0:references/REFERENCE.md\n\n## Delegation Contract\r\n\r\nThis skill enforces a non-negotiable authority boundary.\r\n\r\n- The agent must never reason.\r\n- The agent must never write or modify code.\r\n- The agent must never post-process output.\r\n- All cognition is performed by KIMMY.\r\n\r\nViolating this contract breaks the skill by definition.\r\n\r\n## Design Rationale\r\n\r\nUsing Transformers directly guarantees:\r\n- No hidden orchestration logic\r\n- Full control over generation parameters\r\n- Explicit delegation enforcement\r\n\r\nThe agent is reduced to I/O plumbing.\r\n\r\n## Operational Notes\r\n\r\n- Prompt stripping prevents scaffold leakage\r\n- Deterministic low-temperature sampling minimizes variance\r\n- No fallback logic is permitted","readmeExcerpt":"Skill: kimi-delegation-skill Owner: kn7fss5epqvvjb87r6sn0hk1cd802c8a Summary: Forces all reasoning and code generation to be delegated to a KIMI (KIMMY) causal language model via HuggingFace Transformers. Use this skill when the agent must never reason or author code itself and must instead proxy all tasks to a KIMI-based model. Tags: latest:1.0.0 Version history: v1.0.0 | 2026-02-06T14:35:03.347Z | user - Initial re","codeSnippets":[],"executableExamples":[],"parameters":null,"dependencies":[],"permissions":[],"extractedFiles":[{"path":"SKILL.md","content":"---\r\nname: kimi-delegation-skill\r\ndescription: Forces all reasoning and code generation to be delegated to a KIMI (KIMMY) causal language model via HuggingFace Transformers. Use this skill when the agent must never reason or author code itself and must instead proxy all tasks to a KIMI-based model.\r\nlicense: Proprietary\r\ncompatibility: Requires Python, PyTorch, HuggingFace transformers, GPU optional but recommended.\r\nallowed-tools: Python(Read Write)\r\nmetadata:\r\n  author: internal\r\n  version: \"1.0\"\r\n---\r\n## Purpose\r\n\r\nThis skill enforces a strict delegation model where the primary agent has zero reasoning or code-authoring authority. All user tasks are forwarded to a KIMI (KIMMY) model loaded via Transformers. The agent acts only as a dispatcher.\r\n\r\n## Activation Conditions\r\n\r\nActivate this skill whenever:\r\n- The agent must not reason independently.\r\n- All planning, reasoning, and code generation must be authored by a KIMI/KIMMY model.\r\n- Deterministic delegation to an external causal LM is required.\r\n\r\n## Execution Steps\r\n\r\n1. Initialize `KIMISkill` with a valid local or remote model path.\r\n2. Wrap the `KIMISkill` instance with `Qwen3Coder`.\r\n3. On every user prompt, call `Qwen3Coder.handle_prompt`.\r\n4. The prompt is forwarded verbatim to KIMMY.\r\n5. KIMMY generates the full response.\r\n6. Strip prompt scaffolding and return the result as the final output.\r\n\r\nSee:\r\n- `scripts/kimi_skill.py`\r\n- `scripts/qwen3_coder.py`\r\n\r\n## Inputs and Outputs\r\n\r\n**Input:**  \r\nA raw user task string.\r\n\r\n**Output:**  \r\nA dictionary with:\r\n- `author`: Always `\"KIMMY\"`\r\n- `content`: The generated response with no prompt scaffolding.\r\n\r\n## Failure Modes and Edge Cases\r\n\r\n- Model path invalid or unavailable: initialization fails.\r\n- Insufficient VRAM: model may fall back to CPU or fail to load.\r\n- Extremely long tasks may exceed context limits.\r\n- If generation fails, no fallback reasoning is permitted.\r\n\r\nThe agent must not attempt to recover by reasoning itself.\r\n\r\n## References\r\n\r\nTechnical details and architectural rationale are in:\r\n- `references/REFERENCE.md`"},{"path":"assets/README.md","content":"This directory is intentionally empty.\r\n\r\nReserved for future static assets such as configuration templates,\r\ndiagrams, or policy documents."},{"path":"_meta.json","content":"{\n  \"ownerId\": \"kn7fss5epqvvjb87r6sn0hk1cd802c8a\",\n  \"slug\": \"kimi-delegation-skill\",\n  \"version\": \"1.0.0\",\n  \"publishedAt\": 1770388503347\n}"},{"path":"references/REFERENCE.md","content":"## Delegation Contract\r\n\r\nThis skill enforces a non-negotiable authority boundary.\r\n\r\n- The agent must never reason.\r\n- The agent must never write or modify code.\r\n- The agent must never post-process output.\r\n- All cognition is performed by KIMMY.\r\n\r\nViolating this contract breaks the skill by definition.\r\n\r\n## Design Rationale\r\n\r\nUsing Transformers directly guarantees:\r\n- No hidden orchestration logic\r\n- Full control over generation parameters\r\n- Explicit delegation enforcement\r\n\r\nThe agent is reduced to I/O plumbing.\r\n\r\n## Operational Notes\r\n\r\n- Prompt stripping prevents scaffold leakage\r\n- Deterministic low-temperature sampling minimizes variance\r\n- No fallback logic is permitted"}],"languages":[],"docsSourceLabel":"CLAWHUB","editorialOverview":"Forces all reasoning and code generation to be delegated to a KIMI (KIMMY) causal language model via HuggingFace Transformers. Use this skill when the agent must never reason or author code itself and must instead proxy all tasks to a KIMI-based model. Skill: kimi-delegation-skill Owner: kn7fss5epqvvjb87r6sn0hk1cd802c8a Summary: Forces all reasoning and code generation to be delegated to a KIMI (KIMMY) causal language model via HuggingFace Transformers. Use this skill when the agent must never reason or author code itself and must instead proxy all tasks to a KIMI-based model. Tags: latest:1.0.0 Version history: v1.0.0 | 2026-02-06T14:35:03.347Z | user - Initial re","editorialQuality":{"score":100,"threshold":65,"status":"ready","wordCount":858,"uniquenessScore":53,"reasons":[]}},"media":{"evidence":{"source":"no-media","verified":false,"confidence":"low","updatedAt":"2026-04-15T00:45:39.800Z","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":"2026-04-15T00:45:39.800Z","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":"2026-10-10T08:53:24.586Z","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"}]}}}