{ "schemaVersion": "1.0", "item": { "slug": "cord-trees", "name": "Cord Trees", "source": "tencent", "type": "skill", "category": "AI 智能", "sourceUrl": "https://clawhub.ai/MoltonBot000/cord-trees", "canonicalUrl": "https://clawhub.ai/MoltonBot000/cord-trees", "targetPlatform": "OpenClaw" }, "install": { "downloadMode": "redirect", "downloadUrl": "/downloads/cord-trees", "sourceDownloadUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=cord-trees", "sourcePlatform": "tencent", "targetPlatform": "OpenClaw", "installMethod": "Manual import", "extraction": "Extract archive", "prerequisites": [ "OpenClaw" ], "packageFormat": "ZIP package", "includedAssets": [ "SKILL.md", "references/state-helpers.md" ], "primaryDoc": "SKILL.md", "quickSetup": [ "Download the package from Yavira.", "Extract the archive and review SKILL.md first.", "Import or place the package into your OpenClaw setup." ], "agentAssist": { "summary": "Hand the extracted package to your coding agent with a concrete install brief instead of figuring it out manually.", "steps": [ "Download the package from Yavira.", "Extract it into a folder your agent can access.", "Paste one of the prompts below and point your agent at the extracted folder." ], "prompts": [ { "label": "New install", "body": "I downloaded a skill package from Yavira. Read SKILL.md from the extracted folder and install it by following the included instructions. Tell me what you changed and call out any manual steps you could not complete." }, { "label": "Upgrade existing", "body": "I downloaded an updated skill package from Yavira. Read SKILL.md from the extracted folder, compare it with my current installation, and upgrade it while preserving any custom configuration unless the package docs explicitly say otherwise. Summarize what changed and any follow-up checks I should run." } ] }, "sourceHealth": { "source": "tencent", "status": "healthy", "reason": "direct_download_ok", "recommendedAction": "download", "checkedAt": "2026-04-30T16:55:25.780Z", "expiresAt": "2026-05-07T16:55:25.780Z", "httpStatus": 200, "finalUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=network", "contentType": "application/zip", "probeMethod": "head", "details": { "probeUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=network", "contentDisposition": "attachment; filename=\"network-1.0.0.zip\"", "redirectLocation": null, "bodySnippet": null }, "scope": "source", "summary": "Source download looks usable.", "detail": "Yavira can redirect you to the upstream package for this source.", "primaryActionLabel": "Download for OpenClaw", "primaryActionHref": "/downloads/cord-trees" }, "validation": { "installChecklist": [ "Use the Yavira download entry.", "Review SKILL.md after the package is downloaded.", "Confirm the extracted package contains the expected setup assets." ], "postInstallChecks": [ "Confirm the extracted package includes the expected docs or setup files.", "Validate the skill or prompts are available in your target agent workspace.", "Capture any manual follow-up steps the agent could not complete." ] }, "downloadPageUrl": "https://openagent3.xyz/downloads/cord-trees", "agentPageUrl": "https://openagent3.xyz/skills/cord-trees/agent", "manifestUrl": "https://openagent3.xyz/skills/cord-trees/agent.json", "briefUrl": "https://openagent3.xyz/skills/cord-trees/agent.md" }, "agentAssist": { "summary": "Hand the extracted package to your coding agent with a concrete install brief instead of figuring it out manually.", "steps": [ "Download the package from Yavira.", "Extract it into a folder your agent can access.", "Paste one of the prompts below and point your agent at the extracted folder." ], "prompts": [ { "label": "New install", "body": "I downloaded a skill package from Yavira. Read SKILL.md from the extracted folder and install it by following the included instructions. Tell me what you changed and call out any manual steps you could not complete." }, { "label": "Upgrade existing", "body": "I downloaded an updated skill package from Yavira. Read SKILL.md from the extracted folder, compare it with my current installation, and upgrade it while preserving any custom configuration unless the package docs explicitly say otherwise. Summarize what changed and any follow-up checks I should run." } ] }, "documentation": { "source": "clawhub", "primaryDoc": "SKILL.md", "sections": [ { "title": "Cord Trees — Dynamic Task Tree Orchestration", "body": "Build coordination trees at runtime. You decide the decomposition, not the developer.\n\nInspired by Cord by June Kim." }, { "title": "Core Concept", "body": "Instead of following a pre-defined workflow, you analyze the goal and build your own task tree:\n\nGoal: \"Evaluate whether to migrate from REST to GraphQL\"\n\nYou decide:\n├── #1 spawn: Audit current REST API surface\n├── #2 spawn: Research GraphQL trade-offs \n├── #3 ask: How many concurrent users? (blocked-by: #1)\n├── #4 fork: Comparative analysis (blocked-by: #2, #3)\n└── #5 fork: Write recommendation (blocked-by: #4)\n\nThe tree emerges from your analysis, not from hardcoded logic." }, { "title": "1. SPAWN — Isolated Context", "body": "Child gets only its task prompt. Clean slate.\n\nspawn(\n goal=\"Research GraphQL adoption patterns\",\n prompt=\"Search for case studies of REST→GraphQL migrations...\",\n blocked_by=[] # Can start immediately\n)\n\nUse when: Task is self-contained, doesn't need sibling context." }, { "title": "2. FORK — Inherited Context", "body": "Child receives all completed sibling results injected into prompt.\n\nfork(\n goal=\"Synthesize findings into recommendation\",\n prompt=\"Based on the research, write a recommendation...\",\n blocked_by=[\"research-rest\", \"research-graphql\", \"user-scale\"]\n)\n\nUse when: Synthesis, analysis, or integration requiring prior work." }, { "title": "3. ASK — Human Elicitation", "body": "Pause for human input. Creates a checkpoint.\n\nask(\n question=\"How many concurrent users do you serve?\",\n options=[\"<1K\", \"1K-10K\", \"10K-100K\", \">100K\"],\n blocked_by=[\"audit-api\"] # Ask after audit provides context\n)\n\nUse when: Decision requires human knowledge or approval." }, { "title": "4. SERIAL — Ordered Sequence", "body": "Children execute in order. Implicit dependencies.\n\nserial([\n {\"goal\": \"Draft report\", \"type\": \"spawn\"},\n {\"goal\": \"Review draft\", \"type\": \"ask\"},\n {\"goal\": \"Finalize report\", \"type\": \"fork\"}\n])\n\nUse when: Strict ordering required." }, { "title": "5. GOAL — Root Node", "body": "The top-level objective. You decompose it into children." }, { "title": "Implementation with OpenClaw", "body": "Map Cord primitives to OpenClaw tools:\n\nCord PrimitiveOpenClaw Implementationspawnsessions_spawn(task=prompt, label=id)forksessions_spawn with sibling results in taskaskMessage human, wait for responseserialSpawn sequentially, wait between eachread_treeRead state file + subagents listcompleteWrite result to state file" }, { "title": "State File", "body": "Track the tree in cord-state.json:\n\n{\n \"goal\": \"Evaluate REST to GraphQL migration\",\n \"nodes\": {\n \"#1\": {\n \"type\": \"spawn\",\n \"goal\": \"Audit REST API\",\n \"status\": \"complete\",\n \"result\": \"47 endpoints, 12 nested...\",\n \"blockedBy\": [],\n \"sessionKey\": \"abc123\"\n },\n \"#2\": {\n \"type\": \"spawn\",\n \"goal\": \"Research GraphQL\",\n \"status\": \"running\",\n \"blockedBy\": [],\n \"sessionKey\": \"def456\"\n },\n \"#3\": {\n \"type\": \"ask\",\n \"goal\": \"Get user scale\",\n \"status\": \"waiting\",\n \"question\": \"How many concurrent users?\",\n \"options\": [\"<1K\", \"1K-10K\", \"10K-100K\", \">100K\"],\n \"blockedBy\": [\"#1\"]\n },\n \"#4\": {\n \"type\": \"fork\",\n \"goal\": \"Comparative analysis\",\n \"status\": \"blocked\",\n \"blockedBy\": [\"#2\", \"#3\"]\n }\n },\n \"nextId\": 5\n}" }, { "title": "Phase 1: Analyze Goal", "body": "Read the goal. Think about:\n\nWhat are the major components?\nWhat can run in parallel?\nWhat has dependencies?\nWhere do I need human input?\nWhat needs synthesis (fork) vs isolation (spawn)?" }, { "title": "Phase 2: Build Initial Tree", "body": "Create nodes for the first level of decomposition:\n\n# Initialize state\nstate = {\n \"goal\": user_goal,\n \"nodes\": {},\n \"nextId\": 1\n}\n\n# Add initial nodes\nadd_node(state, type=\"spawn\", goal=\"Research A\", blockedBy=[])\nadd_node(state, type=\"spawn\", goal=\"Research B\", blockedBy=[])\nadd_node(state, type=\"fork\", goal=\"Synthesize\", blockedBy=[\"#1\", \"#2\"])\n\nwrite(\"cord-state.json\", state)" }, { "title": "Phase 3: Execute Ready Nodes", "body": "Find nodes that are ready (all blockedBy complete):\n\ndef get_ready_nodes(state):\n ready = []\n for id, node in state[\"nodes\"].items():\n if node[\"status\"] != \"blocked\":\n continue\n deps = node[\"blockedBy\"]\n if all(state[\"nodes\"][d][\"status\"] == \"complete\" for d in deps):\n ready.append(id)\n return ready\n\nFor each ready node:\n\nIf spawn:\n\nsessions_spawn(\n task=node[\"prompt\"],\n label=node_id,\n runTimeoutSeconds=600\n)\nnode[\"status\"] = \"running\"\n\nIf fork:\n\n# Inject sibling results\nsibling_context = collect_sibling_results(state, node)\nfull_prompt = f\"{node['prompt']}\\n\\nContext from prior work:\\n{sibling_context}\"\n\nsessions_spawn(task=full_prompt, label=node_id)\nnode[\"status\"] = \"running\"\n\nIf ask:\n\n# Message human\nmessage(action=\"send\", message=f\"Question: {node['question']}\\nOptions: {node['options']}\")\nnode[\"status\"] = \"waiting\"\n# Wait for response, then mark complete with answer" }, { "title": "Phase 4: Monitor & Update", "body": "Poll running agents, update state on completion:\n\nwhile has_running_or_blocked(state):\n # Check agent status\n agents = subagents(action=\"list\")\n \n for agent in agents:\n node = find_node_by_session(state, agent[\"sessionKey\"])\n if agent[\"status\"] == \"complete\":\n # Get result from session history\n result = get_agent_result(agent)\n node[\"status\"] = \"complete\"\n node[\"result\"] = result\n \n # Dispatch newly ready nodes\n for node_id in get_ready_nodes(state):\n dispatch_node(state, node_id)\n \n save_state(state)\n wait(30) # Don't poll too aggressively" }, { "title": "Phase 5: Synthesize", "body": "When all nodes complete, the final fork node produces the result." }, { "title": "Dynamic Restructuring", "body": "Agents can modify their own subtree at runtime:\n\n# Child agent realizes it needs more research\nadd_child_node(\n parent=\"#2\",\n type=\"spawn\",\n goal=\"Deep dive on performance implications\",\n blockedBy=[]\n)\n\nThis is what makes Cord-style orchestration powerful — the tree evolves based on what agents discover." }, { "title": "Spawn vs Fork Decision Guide", "body": "SituationUseIndependent research taskspawnTask that doesn't need sibling contextspawnCheap to restart if it failsspawnSynthesis or analysis across prior workforkFinal integration stepforkTask that builds on discoveriesfork\n\nDefault to spawn. Use fork only when context inheritance is required." }, { "title": "Approval Gate", "body": "#1 spawn: Draft proposal\n#2 ask: \"Approve this proposal?\" (blocked-by: #1)\n#3 fork: Implement approved proposal (blocked-by: #2)" }, { "title": "Clarification", "body": "#1 spawn: Initial analysis\n#2 ask: \"Which direction should we focus?\" (blocked-by: #1)\n#3 spawn: Deep dive on chosen direction (blocked-by: #2)" }, { "title": "Periodic Checkpoints", "body": "#1 spawn: Phase 1\n#2 ask: \"Continue to phase 2?\" (blocked-by: #1)\n#3 spawn: Phase 2 (blocked-by: #2)\n#4 ask: \"Continue to phase 3?\" (blocked-by: #3)\n..." }, { "title": "Example: Full Decomposition", "body": "Goal: \"Create a comprehensive competitor analysis report\"\n\n#1 [spawn] List top 5 competitors\n └── No dependencies, starts immediately\n\n#2 [spawn] Research Competitor A (blocked-by: #1)\n#3 [spawn] Research Competitor B (blocked-by: #1)\n#4 [spawn] Research Competitor C (blocked-by: #1)\n#5 [spawn] Research Competitor D (blocked-by: #1)\n#6 [spawn] Research Competitor E (blocked-by: #1)\n └── All parallel, isolated research\n\n#7 [fork] Identify patterns across competitors (blocked-by: #2-#6)\n └── Needs all research results\n\n#8 [ask] \"Focus on pricing, features, or positioning?\" (blocked-by: #7)\n └── Human steers direction\n\n#9 [fork] Deep analysis on chosen focus (blocked-by: #8)\n └── Builds on patterns + human input\n\n#10 [fork] Write final report (blocked-by: #9)\n └── Synthesis of everything" }, { "title": "Error Handling", "body": "if node[\"status\"] == \"failed\":\n # Options:\n # 1. Retry (reset to blocked)\n node[\"status\"] = \"blocked\"\n node[\"retries\"] = node.get(\"retries\", 0) + 1\n \n # 2. Skip (mark complete with error)\n node[\"status\"] = \"complete\"\n node[\"result\"] = f\"FAILED: {error}\"\n \n # 3. Escalate (ask human)\n add_node(state, type=\"ask\", \n question=f\"Node {id} failed. Retry, skip, or abort?\",\n blockedBy=[])" }, { "title": "Attribution", "body": "This skill implements patterns from the Cord protocol by June Kim, adapted for OpenClaw's sessions_spawn and subagents primitives." } ], "body": "Cord Trees — Dynamic Task Tree Orchestration\n\nBuild coordination trees at runtime. You decide the decomposition, not the developer.\n\nInspired by Cord by June Kim.\n\nCore Concept\n\nInstead of following a pre-defined workflow, you analyze the goal and build your own task tree:\n\nGoal: \"Evaluate whether to migrate from REST to GraphQL\"\n\nYou decide:\n├── #1 spawn: Audit current REST API surface\n├── #2 spawn: Research GraphQL trade-offs \n├── #3 ask: How many concurrent users? (blocked-by: #1)\n├── #4 fork: Comparative analysis (blocked-by: #2, #3)\n└── #5 fork: Write recommendation (blocked-by: #4)\n\n\nThe tree emerges from your analysis, not from hardcoded logic.\n\nFive Primitives\n1. SPAWN — Isolated Context\n\nChild gets only its task prompt. Clean slate.\n\nspawn(\n goal=\"Research GraphQL adoption patterns\",\n prompt=\"Search for case studies of REST→GraphQL migrations...\",\n blocked_by=[] # Can start immediately\n)\n\n\nUse when: Task is self-contained, doesn't need sibling context.\n\n2. FORK — Inherited Context\n\nChild receives all completed sibling results injected into prompt.\n\nfork(\n goal=\"Synthesize findings into recommendation\",\n prompt=\"Based on the research, write a recommendation...\",\n blocked_by=[\"research-rest\", \"research-graphql\", \"user-scale\"]\n)\n\n\nUse when: Synthesis, analysis, or integration requiring prior work.\n\n3. ASK — Human Elicitation\n\nPause for human input. Creates a checkpoint.\n\nask(\n question=\"How many concurrent users do you serve?\",\n options=[\"<1K\", \"1K-10K\", \"10K-100K\", \">100K\"],\n blocked_by=[\"audit-api\"] # Ask after audit provides context\n)\n\n\nUse when: Decision requires human knowledge or approval.\n\n4. SERIAL — Ordered Sequence\n\nChildren execute in order. Implicit dependencies.\n\nserial([\n {\"goal\": \"Draft report\", \"type\": \"spawn\"},\n {\"goal\": \"Review draft\", \"type\": \"ask\"},\n {\"goal\": \"Finalize report\", \"type\": \"fork\"}\n])\n\n\nUse when: Strict ordering required.\n\n5. GOAL — Root Node\n\nThe top-level objective. You decompose it into children.\n\nImplementation with OpenClaw\n\nMap Cord primitives to OpenClaw tools:\n\nCord Primitive\tOpenClaw Implementation\nspawn\tsessions_spawn(task=prompt, label=id)\nfork\tsessions_spawn with sibling results in task\nask\tMessage human, wait for response\nserial\tSpawn sequentially, wait between each\nread_tree\tRead state file + subagents list\ncomplete\tWrite result to state file\nState File\n\nTrack the tree in cord-state.json:\n\n{\n \"goal\": \"Evaluate REST to GraphQL migration\",\n \"nodes\": {\n \"#1\": {\n \"type\": \"spawn\",\n \"goal\": \"Audit REST API\",\n \"status\": \"complete\",\n \"result\": \"47 endpoints, 12 nested...\",\n \"blockedBy\": [],\n \"sessionKey\": \"abc123\"\n },\n \"#2\": {\n \"type\": \"spawn\",\n \"goal\": \"Research GraphQL\",\n \"status\": \"running\",\n \"blockedBy\": [],\n \"sessionKey\": \"def456\"\n },\n \"#3\": {\n \"type\": \"ask\",\n \"goal\": \"Get user scale\",\n \"status\": \"waiting\",\n \"question\": \"How many concurrent users?\",\n \"options\": [\"<1K\", \"1K-10K\", \"10K-100K\", \">100K\"],\n \"blockedBy\": [\"#1\"]\n },\n \"#4\": {\n \"type\": \"fork\",\n \"goal\": \"Comparative analysis\",\n \"status\": \"blocked\",\n \"blockedBy\": [\"#2\", \"#3\"]\n }\n },\n \"nextId\": 5\n}\n\nWorkflow\nPhase 1: Analyze Goal\n\nRead the goal. Think about:\n\nWhat are the major components?\nWhat can run in parallel?\nWhat has dependencies?\nWhere do I need human input?\nWhat needs synthesis (fork) vs isolation (spawn)?\nPhase 2: Build Initial Tree\n\nCreate nodes for the first level of decomposition:\n\n# Initialize state\nstate = {\n \"goal\": user_goal,\n \"nodes\": {},\n \"nextId\": 1\n}\n\n# Add initial nodes\nadd_node(state, type=\"spawn\", goal=\"Research A\", blockedBy=[])\nadd_node(state, type=\"spawn\", goal=\"Research B\", blockedBy=[])\nadd_node(state, type=\"fork\", goal=\"Synthesize\", blockedBy=[\"#1\", \"#2\"])\n\nwrite(\"cord-state.json\", state)\n\nPhase 3: Execute Ready Nodes\n\nFind nodes that are ready (all blockedBy complete):\n\ndef get_ready_nodes(state):\n ready = []\n for id, node in state[\"nodes\"].items():\n if node[\"status\"] != \"blocked\":\n continue\n deps = node[\"blockedBy\"]\n if all(state[\"nodes\"][d][\"status\"] == \"complete\" for d in deps):\n ready.append(id)\n return ready\n\n\nFor each ready node:\n\nIf spawn:\n\nsessions_spawn(\n task=node[\"prompt\"],\n label=node_id,\n runTimeoutSeconds=600\n)\nnode[\"status\"] = \"running\"\n\n\nIf fork:\n\n# Inject sibling results\nsibling_context = collect_sibling_results(state, node)\nfull_prompt = f\"{node['prompt']}\\n\\nContext from prior work:\\n{sibling_context}\"\n\nsessions_spawn(task=full_prompt, label=node_id)\nnode[\"status\"] = \"running\"\n\n\nIf ask:\n\n# Message human\nmessage(action=\"send\", message=f\"Question: {node['question']}\\nOptions: {node['options']}\")\nnode[\"status\"] = \"waiting\"\n# Wait for response, then mark complete with answer\n\nPhase 4: Monitor & Update\n\nPoll running agents, update state on completion:\n\nwhile has_running_or_blocked(state):\n # Check agent status\n agents = subagents(action=\"list\")\n \n for agent in agents:\n node = find_node_by_session(state, agent[\"sessionKey\"])\n if agent[\"status\"] == \"complete\":\n # Get result from session history\n result = get_agent_result(agent)\n node[\"status\"] = \"complete\"\n node[\"result\"] = result\n \n # Dispatch newly ready nodes\n for node_id in get_ready_nodes(state):\n dispatch_node(state, node_id)\n \n save_state(state)\n wait(30) # Don't poll too aggressively\n\nPhase 5: Synthesize\n\nWhen all nodes complete, the final fork node produces the result.\n\nDynamic Restructuring\n\nAgents can modify their own subtree at runtime:\n\n# Child agent realizes it needs more research\nadd_child_node(\n parent=\"#2\",\n type=\"spawn\",\n goal=\"Deep dive on performance implications\",\n blockedBy=[]\n)\n\n\nThis is what makes Cord-style orchestration powerful — the tree evolves based on what agents discover.\n\nSpawn vs Fork Decision Guide\nSituation\tUse\nIndependent research task\tspawn\nTask that doesn't need sibling context\tspawn\nCheap to restart if it fails\tspawn\nSynthesis or analysis across prior work\tfork\nFinal integration step\tfork\nTask that builds on discoveries\tfork\n\nDefault to spawn. Use fork only when context inheritance is required.\n\nHuman-in-the-Loop Patterns\nApproval Gate\n#1 spawn: Draft proposal\n#2 ask: \"Approve this proposal?\" (blocked-by: #1)\n#3 fork: Implement approved proposal (blocked-by: #2)\n\nClarification\n#1 spawn: Initial analysis\n#2 ask: \"Which direction should we focus?\" (blocked-by: #1)\n#3 spawn: Deep dive on chosen direction (blocked-by: #2)\n\nPeriodic Checkpoints\n#1 spawn: Phase 1\n#2 ask: \"Continue to phase 2?\" (blocked-by: #1)\n#3 spawn: Phase 2 (blocked-by: #2)\n#4 ask: \"Continue to phase 3?\" (blocked-by: #3)\n...\n\nExample: Full Decomposition\n\nGoal: \"Create a comprehensive competitor analysis report\"\n\n#1 [spawn] List top 5 competitors\n └── No dependencies, starts immediately\n\n#2 [spawn] Research Competitor A (blocked-by: #1)\n#3 [spawn] Research Competitor B (blocked-by: #1)\n#4 [spawn] Research Competitor C (blocked-by: #1)\n#5 [spawn] Research Competitor D (blocked-by: #1)\n#6 [spawn] Research Competitor E (blocked-by: #1)\n └── All parallel, isolated research\n\n#7 [fork] Identify patterns across competitors (blocked-by: #2-#6)\n └── Needs all research results\n\n#8 [ask] \"Focus on pricing, features, or positioning?\" (blocked-by: #7)\n └── Human steers direction\n\n#9 [fork] Deep analysis on chosen focus (blocked-by: #8)\n └── Builds on patterns + human input\n\n#10 [fork] Write final report (blocked-by: #9)\n └── Synthesis of everything\n\nError Handling\nif node[\"status\"] == \"failed\":\n # Options:\n # 1. Retry (reset to blocked)\n node[\"status\"] = \"blocked\"\n node[\"retries\"] = node.get(\"retries\", 0) + 1\n \n # 2. Skip (mark complete with error)\n node[\"status\"] = \"complete\"\n node[\"result\"] = f\"FAILED: {error}\"\n \n # 3. Escalate (ask human)\n add_node(state, type=\"ask\", \n question=f\"Node {id} failed. Retry, skip, or abort?\",\n blockedBy=[])\n\nAttribution\n\nThis skill implements patterns from the Cord protocol by June Kim, adapted for OpenClaw's sessions_spawn and subagents primitives." }, "trust": { "sourceLabel": "tencent", "provenanceUrl": "https://clawhub.ai/MoltonBot000/cord-trees", "publisherUrl": "https://clawhub.ai/MoltonBot000/cord-trees", "owner": "MoltonBot000", "version": "1.0.1", "license": null, "verificationStatus": "Indexed source record" }, "links": { "detailUrl": "https://openagent3.xyz/skills/cord-trees", "downloadUrl": "https://openagent3.xyz/downloads/cord-trees", "agentUrl": "https://openagent3.xyz/skills/cord-trees/agent", "manifestUrl": "https://openagent3.xyz/skills/cord-trees/agent.json", "briefUrl": "https://openagent3.xyz/skills/cord-trees/agent.md" } }