[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M6ME9TNT8E5NESMCQYTTWJ80":3,"skill-same:01M6ME9TNT8E5NESMCQYTTWJ80":77},{"skillNo":4,"name":5,"nameZh":6,"description":7,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":16,"categories":17,"keywords":18,"publishedAt":38,"linkOnly":39,"markdownContent":40,"markdownBody":41,"frontMatter":42,"refName":47,"commitSha":48,"skillDirectory":49,"forksCount":50,"repositoryHtmlUrl":51,"repositoryHomepageUrl":52,"ownerHtmlUrl":53,"ownerBlogUrl":54,"ownerDescription":55,"updatedAt":56,"install":57,"resources":70},"01M6ME9TNT8E5NESMCQYTTWJ80","orchestration",null,"Multi-agent orchestration: lane contracts, worker-model doctrine, fault tolerance. Triggers: orchestrate, coordinate, agents, parallel, spawn, contract, tier 2, tier 3.","hashgraph-online\u002Fawesome-codex-plugins","hashgraph-online","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F160371962?v=4","01M6CNB6NRJVNNGN14TR01Q6D3","HOL (Hashgraph Online)","01M6JT1HSKKG9V68KQAQGBA7XP",1575,"Apache-2.0","https:\u002F\u002Fgithub.com\u002Fhashgraph-online\u002Fawesome-codex-plugins\u002Fblob\u002Fmain\u002Fplugins\u002Fariaxhan\u002Fkernel-claude\u002Fskills\u002Forchestration\u002FSKILL.md",[],[5,19,20,21,22,23,24,25,26,27,28,29,30,31,32,33,34,35,36,37],"agent orchestration","tolerance","multi","triggers","contract","fault tolerance","worker","task","coordinate","doctrine","spawn","read","parallel","multi-agent","model","Bash","methodology","lane","orchestrate","2026-11-10 10:12:30",false,"---\nname: orchestration\ndescription: \"Multi-agent orchestration: lane contracts, worker-model doctrine, fault tolerance. Triggers: orchestrate, coordinate, agents, parallel, spawn, contract, tier 2, tier 3.\"\nallowed-tools: Task, Bash, Read\nkernel:\n  kind: methodology\n  version: 1\n  side_effects: none\n  confirmation: none\n---\n\n\u003Cskill id=\"orchestration\">\n\n\u003Cpurpose>\nOrchestration is coordination, not implementation. You define contracts, agents\nexecute, AgentDB is the bus. Never assume completion without reading the file.\nReference on demand: skills\u002Forchestration\u002Freference\u002Forchestration-research.md.\n\u003C\u002Fpurpose>\n\n\u003Clane_contract>\nEvery spawned lane gets ALL of these fields; a missing field is where the lane fails:\n1. **Deliverable**: the observable artifact, named exactly (file path, PR, report).\n2. **Read-first list**: the files\u002Fdocs the lane must read before acting.\n3. **Files table**: exhaustive list of files it may touch (`constraints.files`).\n   No two concurrent lanes may overlap. Contract JSON:\n   `{\"goal\":\"X\",\"constraints\":{\"files\":[\"a.sh\",\"b.md\"]},\"tier\":2}`\n4. **Known traps, restated**: gotchas relevant to this lane, inlined, not linked.\n5. **Verification loop with exact commands**: the literal commands the lane runs to\n   prove its own work (test invocation, grep, curl), plus expected output.\n6. **Forbidden list**: what the lane must NOT do (push, touch _meta\u002F, add deps, ...).\n7. **Raw-data return format**: counts, file lists, command output. Never narrative\n   alone; a lane that returns only prose has returned nothing checkable.\n8. **Capabilities needed from outside the runtime**: none | browser | isolated-chromium |\n   gui | keychain | ssh | api:vendor | interactive. A lane that needs a capability the\n   sandbox denies fails deep into the work, having already spent the budget.\n\nThe prompt must stand alone in a fresh session with no conversation history: no \"as\ndiscussed\", no reference to a target that exists only in your context, no compressed\nshorthand only this session can expand. Read it as if you had just booted.\nPass it by FILE PATH once it is large; an inline prompt over a few hundred KB dies on the\nsubprocess argv limit (E2BIG), and the failure looks like a crash, not a size error.\n\u003C\u002Flane_contract>\n\n\u003Coutput_integrity>\nStructured long-report lanes degrade silently to placeholders under load. Validate\nevery lane return mechanically before using it: minimum-length check on required\nsections, placeholder detection (\"TBD\", \"...\", repeated boilerplate), counts match\nthe claimed work. Reject-and-retry a degraded return; never synthesize over it.\nPass large input pools to lanes by FILE PATH, never as an inline slice (silent\ntruncation reads as full coverage). Each lane keeps a per-lane journal\u002Fcheckpoint\nso a degraded final message is not the only record of what it did.\n\u003C\u002Foutput_integrity>\n\n\u003Cfrozen_inputs>\nFreeze the exact bytes a review lane judges before dispatching it. A concurrent lane\ncorrecting the same artifact mid-review destroys the review: it now reports on a version\nthat no longer exists, and the finding cannot be reproduced or dismissed. Snapshot the\ninput to a path the reviewer reads, record its hash in the contract, and re-check the hash\nwhen the verdict lands. If the source moved, the verdict is void, not stale.\n\u003C\u002Ffrozen_inputs>\n\n\u003Cshared_resources>\nAny id, lock, slot, or row a runner allocates for lanes is contended the moment two lanes\nstart. Allocate atomically (a real transaction, O_EXCL that is checked, a database\nconstraint), then READ BACK what you got and fail loudly if it is empty. Exit 0 with a\nblank id is the signature of a lost race, and it produces a malformed record that outlives\nthe run. An O_EXCL lock created during initialization admits a second owner unless the\ninitialization itself is inside the lock.\n\u003C\u002Fshared_resources>\n\n\u003Csingle_coordinator>\nOne coordinator per repo at a time. Before coordinating, check for a live second\nsession on the same working directory (stale sessions can survive as background\ndaemons and produce split-brain: two coordinators mutating one repo in parallel).\nWhen killing a stuck session, kill its whole process pool, not just the visible pid.\n\u003C\u002Fsingle_coordinator>\n\n\u003Cworker_model_doctrine>\nSelect model and effort from the lane's task shape and measured evidence, never from\nrole prestige. Mechanical total-spec execution with deterministic checks can use the\nlowest setting proven adequate. Ambiguous judgment or a measured miss justifies more\neffort; protected work requires a fresh independent verifier. The lane contract records\nthe requested model and effort, whether inheritance is intentional, and the escalation\ncondition. A prompt that says \"use your judgment\" is evidence of ambiguity, not a license\nto choose a prestige model by role. Receipts keep `requested_model` and `requested_effort`\nseparate from `observed_model` and `observed_effort`. Unsupported or unexposed values are\n`unavailable`, never inferred. Protected receipts require distinct `builder_identity` and\n`verifier_identity`; the builder never grades its own protected work. The coordinator\nreproduces acceptance evidence.\n\u003C\u002Fworker_model_doctrine>\n\n\u003Cfault_tolerance>\n1. RETRY transient failures with backoff, max 3. 2. CLASSIFY the failure before choosing\nrecovery. 3. Never silently substitute model, effort, or provider. Use an alternative only\nwhen the contract names a pre-authorized fallback; record the original request, the failure,\nand the observed fallback identity separately. Otherwise stop and re-contract. 4. CHECKPOINT\nstate to AgentDB at every boundary so a respawn resumes instead of restarting.\n\u003C\u002Ffault_tolerance>\n\n\u003Clane_safety>\nNEVER use git worktrees (`isolation: \"worktree\"`, `git worktree add`): the operator forbids them\nand they have never produced merged work here. Parallel lanes (tier 2+) share the live checkout\nand are made safe by file-disjointness: each lane's `constraints.files` is disjoint from all active\nlanes, and a lane stages only its own paths by name. Post-agent validation: read the lane's\ncheckpoint, then `git diff --name-only` over the lane's commits; every changed file MUST appear in\n`constraints.files`, and an out-of-scope file means reject, revert that path, re-contract.\nWork that cannot be made file-disjoint runs sequentially.\n\u003C\u002Flane_safety>\n\n\u003Cknowledge_injection>\nInject context BEFORE spawn, never let lanes discover it at runtime: build the slice\nwith `agentdb inject-context \u003Cagent_type>` and inline it in the prompt (surgeon gets\ngotchas + patterns + contract; adversary\u002Freviewer get past failures + recent errors;\nresearcher gets domain learnings). The orchestrator owns injection. Every agent\nboundary is lossy compression: structured briefing in, structured checkpoint out;\nnever rely on conversation history across agents.\n\u003C\u002Fknowledge_injection>\n\n\u003Canti_patterns>\nHolding context in memory instead of AgentDB · assuming a lane finished without\nreading the deliverable file (receipts describe intent; files describe reality) ·\nparallel lanes touching shared files (N-way merge conflicts) · serial execution when\nparallel is genuinely safe · retrying without new information from the failure ·\nautonomous loops without a budget cap (`max_budget_usd` on the contract) ·\naccepting a lane return without the output-integrity check (placeholder degradation\nis silent) · two coordinators on one repo · dispatching a review over bytes another lane\nis still editing · a prompt that only makes sense inside the dispatching session.\n\u003C\u002Fanti_patterns>\n\n\u003C\u002Fskill>\n","\u003Cskill id=\"orchestration\">\n\n\u003Cpurpose>\nOrchestration is coordination, not implementation. You define contracts, agents\nexecute, AgentDB is the bus. Never assume completion without reading the file.\nReference on demand: skills\u002Forchestration\u002Freference\u002Forchestration-research.md.\n\u003C\u002Fpurpose>\n\n\u003Clane_contract>\nEvery spawned lane gets ALL of these fields; a missing field is where the lane fails:\n1. **Deliverable**: the observable artifact, named exactly (file path, PR, report).\n2. **Read-first list**: the files\u002Fdocs the lane must read before acting.\n3. **Files table**: exhaustive list of files it may touch (`constraints.files`).\n   No two concurrent lanes may overlap. Contract JSON:\n   `{\"goal\":\"X\",\"constraints\":{\"files\":[\"a.sh\",\"b.md\"]},\"tier\":2}`\n4. **Known traps, restated**: gotchas relevant to this lane, inlined, not linked.\n5. **Verification loop with exact commands**: the literal commands the lane runs to\n   prove its own work (test invocation, grep, curl), plus expected output.\n6. **Forbidden list**: what the lane must NOT do (push, touch _meta\u002F, add deps, ...).\n7. **Raw-data return format**: counts, file lists, command output. Never narrative\n   alone; a lane that returns only prose has returned nothing checkable.\n8. **Capabilities needed from outside the runtime**: none | browser | isolated-chromium |\n   gui | keychain | ssh | api:vendor | interactive. A lane that needs a capability the\n   sandbox denies fails deep into the work, having already spent the budget.\n\nThe prompt must stand alone in a fresh session with no conversation history: no \"as\ndiscussed\", no reference to a target that exists only in your context, no compressed\nshorthand only this session can expand. Read it as if you had just booted.\nPass it by FILE PATH once it is large; an inline prompt over a few hundred KB dies on the\nsubprocess argv limit (E2BIG), and the failure looks like a crash, not a size error.\n\u003C\u002Flane_contract>\n\n\u003Coutput_integrity>\nStructured long-report lanes degrade silently to placeholders under load. Validate\nevery lane return mechanically before using it: minimum-length check on required\nsections, placeholder detection (\"TBD\", \"...\", repeated boilerplate), counts match\nthe claimed work. Reject-and-retry a degraded return; never synthesize over it.\nPass large input pools to lanes by FILE PATH, never as an inline slice (silent\ntruncation reads as full coverage). Each lane keeps a per-lane journal\u002Fcheckpoint\nso a degraded final message is not the only record of what it did.\n\u003C\u002Foutput_integrity>\n\n\u003Cfrozen_inputs>\nFreeze the exact bytes a review lane judges before dispatching it. A concurrent lane\ncorrecting the same artifact mid-review destroys the review: it now reports on a version\nthat no longer exists, and the finding cannot be reproduced or dismissed. Snapshot the\ninput to a path the reviewer reads, record its hash in the contract, and re-check the hash\nwhen the verdict lands. If the source moved, the verdict is void, not stale.\n\u003C\u002Ffrozen_inputs>\n\n\u003Cshared_resources>\nAny id, lock, slot, or row a runner allocates for lanes is contended the moment two lanes\nstart. Allocate atomically (a real transaction, O_EXCL that is checked, a database\nconstraint), then READ BACK what you got and fail loudly if it is empty. Exit 0 with a\nblank id is the signature of a lost race, and it produces a malformed record that outlives\nthe run. An O_EXCL lock created during initialization admits a second owner unless the\ninitialization itself is inside the lock.\n\u003C\u002Fshared_resources>\n\n\u003Csingle_coordinator>\nOne coordinator per repo at a time. Before coordinating, check for a live second\nsession on the same working directory (stale sessions can survive as background\ndaemons and produce split-brain: two coordinators mutating one repo in parallel).\nWhen killing a stuck session, kill its whole process pool, not just the visible pid.\n\u003C\u002Fsingle_coordinator>\n\n\u003Cworker_model_doctrine>\nSelect model and effort from the lane's task shape and measured evidence, never from\nrole prestige. Mechanical total-spec execution with deterministic checks can use the\nlowest setting proven adequate. Ambiguous judgment or a measured miss justifies more\neffort; protected work requires a fresh independent verifier. The lane contract records\nthe requested model and effort, whether inheritance is intentional, and the escalation\ncondition. A prompt that says \"use your judgment\" is evidence of ambiguity, not a license\nto choose a prestige model by role. Receipts keep `requested_model` and `requested_effort`\nseparate from `observed_model` and `observed_effort`. Unsupported or unexposed values are\n`unavailable`, never inferred. Protected receipts require distinct `builder_identity` and\n`verifier_identity`; the builder never grades its own protected work. The coordinator\nreproduces acceptance evidence.\n\u003C\u002Fworker_model_doctrine>\n\n\u003Cfault_tolerance>\n1. RETRY transient failures with backoff, max 3. 2. CLASSIFY the failure before choosing\nrecovery. 3. Never silently substitute model, effort, or provider. Use an alternative only\nwhen the contract names a pre-authorized fallback; record the original request, the failure,\nand the observed fallback identity separately. Otherwise stop and re-contract. 4. CHECKPOINT\nstate to AgentDB at every boundary so a respawn resumes instead of restarting.\n\u003C\u002Ffault_tolerance>\n\n\u003Clane_safety>\nNEVER use git worktrees (`isolation: \"worktree\"`, `git worktree add`): the operator forbids them\nand they have never produced merged work here. Parallel lanes (tier 2+) share the live checkout\nand are made safe by file-disjointness: each lane's `constraints.files` is disjoint from all active\nlanes, and a lane stages only its own paths by name. Post-agent validation: read the lane's\ncheckpoint, then `git diff --name-only` over the lane's commits; every changed file MUST appear in\n`constraints.files`, and an out-of-scope file means reject, revert that path, re-contract.\nWork that cannot be made file-disjoint runs sequentially.\n\u003C\u002Flane_safety>\n\n\u003Cknowledge_injection>\nInject context BEFORE spawn, never let lanes discover it at runtime: build the slice\nwith `agentdb inject-context \u003Cagent_type>` and inline it in the prompt (surgeon gets\ngotchas + patterns + contract; adversary\u002Freviewer get past failures + recent errors;\nresearcher gets domain learnings). The orchestrator owns injection. Every agent\nboundary is lossy compression: structured briefing in, structured checkpoint out;\nnever rely on conversation history across agents.\n\u003C\u002Fknowledge_injection>\n\n\u003Canti_patterns>\nHolding context in memory instead of AgentDB · assuming a lane finished without\nreading the deliverable file (receipts describe intent; files describe reality) ·\nparallel lanes touching shared files (N-way merge conflicts) · serial execution when\nparallel is genuinely safe · retrying without new information from the failure ·\nautonomous loops without a budget cap (`max_budget_usd` on the contract) ·\naccepting a lane return without the output-integrity check (placeholder degradation\nis silent) · two coordinators on one repo · dispatching a review over bytes another lane\nis still editing · a prompt that only makes sense inside the dispatching session.\n\u003C\u002Fanti_patterns>\n\n\u003C\u002Fskill>\n",{"name":5,"kernel":43,"description":7,"allowed-tools":46},{"kind":35,"version":44,"confirmation":45,"side_effects":45},1,"none","Task, Bash, Read","main","2b63f856ce19c2a797929cacabd9e0fc936812fa","plugins\u002Fariaxhan\u002Fkernel-claude\u002Fskills\u002Forchestration",491,"https:\u002F\u002Fgithub.com\u002Fhashgraph-online\u002Fawesome-codex-plugins","https:\u002F\u002Fhol.org\u002Fplugins\u002Fbest-codex-plugins","https:\u002F\u002Fgithub.com\u002Fhashgraph-online","https:\u002F\u002Fhol.org","Open-source standards and developer tools for interoperable AI agents: discovery, identity, communication, payments, privacy and security.","2026-11-14 14:06:13",{"source":8,"skillName":5,"commands":58,"prompt":68,"zipAvailable":69},[59,62,65],{"tool":60,"command":61},"npx","npx skills add hashgraph-online\u002Fawesome-codex-plugins --skill orchestration",{"tool":63,"command":64},"bunx","bunx skills add hashgraph-online\u002Fawesome-codex-plugins --skill orchestration",{"tool":66,"command":67},"pnpm","pnpm dlx skills add hashgraph-online\u002Fawesome-codex-plugins --skill orchestration","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Fhashgraph-online\u002Fawesome-codex-plugins\u002Fblob\u002Fmain\u002Fplugins\u002Fariaxhan\u002Fkernel-claude\u002Fskills\u002Forchestration\u002FSKILL.md",true,[71],{"path":72,"resourceType":73,"resourceTypeDesc":74,"sizeBytes":75,"sourceHtmlUrl":76},"reference\u002Forchestration-research.md","REFERENCE","参考文档",11167,"https:\u002F\u002Fgithub.com\u002Fhashgraph-online\u002Fawesome-codex-plugins\u002Fblob\u002Fmain\u002Fplugins\u002Fariaxhan\u002Fkernel-claude\u002Fskills\u002Forchestration\u002Freference\u002Forchestration-research.md",[78,88,96,104,112,120],{"skillNo":79,"name":80,"nameZh":6,"description":81,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":82,"licenseFileUrl":83,"sourceHtmlUrl":84,"categories":85,"keywords":86,"publishedAt":87},"01M7DV332YQMGD8WTRJ9DZQXTB","worktable-review-with-annotations","Create, inspect, reply to, update, or resolve situated Worktable annotations. Use when feedback belongs to a Doc section, block, text range, or HTML Doc, or when the user asks to address existing review feedback and coordinate a requested artifact edit.","MIT","https:\u002F\u002Fgithub.com\u002Fhashgraph-online\u002Fawesome-codex-plugins\u002Fblob\u002Fmain\u002Fplugins\u002Fworktable\u002Fworktable-plugin\u002Fskills\u002Fworktable-review-with-annotations\u002FLICENSE","https:\u002F\u002Fgithub.com\u002Fhashgraph-online\u002Fawesome-codex-plugins\u002Fblob\u002Fmain\u002Fplugins\u002Fworktable\u002Fworktable-plugin\u002Fskills\u002Fworktable-review-with-annotations\u002FSKILL.md",[],[],"2026-11-15 14:19:17",{"skillNo":89,"name":90,"nameZh":6,"description":91,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":82,"licenseFileUrl":92,"sourceHtmlUrl":93,"categories":94,"keywords":95,"publishedAt":87},"01M7DV2YGHCZVBEB1AHYB6CGHE","worktable-find-and-synthesize-context","Find, assess, and synthesize context from Worktable Docs and Records. Use when the user asks what a workspace contains, wants workspace-backed research, needs current facts reconciled across artifacts, or requests a cited synthesis without changing workspace state.","https:\u002F\u002Fgithub.com\u002Fhashgraph-online\u002Fawesome-codex-plugins\u002Fblob\u002Fmain\u002Fplugins\u002Fworktable\u002Fworktable-plugin\u002Fskills\u002Fworktable-find-and-synthesize-context\u002FLICENSE","https:\u002F\u002Fgithub.com\u002Fhashgraph-online\u002Fawesome-codex-plugins\u002Fblob\u002Fmain\u002Fplugins\u002Fworktable\u002Fworktable-plugin\u002Fskills\u002Fworktable-find-and-synthesize-context\u002FSKILL.md",[],[],{"skillNo":97,"name":98,"nameZh":6,"description":99,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":82,"licenseFileUrl":100,"sourceHtmlUrl":101,"categories":102,"keywords":103,"publishedAt":87},"01M7DV2TQN1H11ME2SAF9MXN7V","worktable-create-or-update-docs","Create, edit, rename, or maintain narrative Worktable Docs. Use for plans, decisions, briefs, notes, research syntheses, and other durable prose when the user requests a new artifact or a safe update to an existing one.","https:\u002F\u002Fgithub.com\u002Fhashgraph-online\u002Fawesome-codex-plugins\u002Fblob\u002Fmain\u002Fplugins\u002Fworktable\u002Fworktable-plugin\u002Fskills\u002Fworktable-create-or-update-docs\u002FLICENSE","https:\u002F\u002Fgithub.com\u002Fhashgraph-online\u002Fawesome-codex-plugins\u002Fblob\u002Fmain\u002Fplugins\u002Fworktable\u002Fworktable-plugin\u002Fskills\u002Fworktable-create-or-update-docs\u002FSKILL.md",[],[],{"skillNo":105,"name":106,"nameZh":6,"description":107,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":82,"licenseFileUrl":108,"sourceHtmlUrl":109,"categories":110,"keywords":111,"publishedAt":87},"01M7DV2NE452NEA8TXATKSNAJH","worktable-create-or-manage-records","Organize repeated structured information as durable Worktable Records. Use for research datasets, inventories, directories, pipelines, trackers, and other collections whose items need identity, fields, filtering, links, validation, or individual updates.","https:\u002F\u002Fgithub.com\u002Fhashgraph-online\u002Fawesome-codex-plugins\u002Fblob\u002Fmain\u002Fplugins\u002Fworktable\u002Fworktable-plugin\u002Fskills\u002Fworktable-create-or-manage-records\u002FLICENSE","https:\u002F\u002Fgithub.com\u002Fhashgraph-online\u002Fawesome-codex-plugins\u002Fblob\u002Fmain\u002Fplugins\u002Fworktable\u002Fworktable-plugin\u002Fskills\u002Fworktable-create-or-manage-records\u002FSKILL.md",[],[],{"skillNo":113,"name":114,"nameZh":6,"description":115,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":82,"licenseFileUrl":116,"sourceHtmlUrl":117,"categories":118,"keywords":119,"publishedAt":87},"01M7DV2HENRBR2KSCVM064WH0Y","worktable-create-or-manage-interactive-html","Create or improve durable visual and interactive artifacts in Worktable. Use for dashboards, trackers, calculators, mini apps, slide presentations, and other requests that benefit from a polished HTML Doc.","https:\u002F\u002Fgithub.com\u002Fhashgraph-online\u002Fawesome-codex-plugins\u002Fblob\u002Fmain\u002Fplugins\u002Fworktable\u002Fworktable-plugin\u002Fskills\u002Fworktable-create-or-manage-interactive-html\u002FLICENSE","https:\u002F\u002Fgithub.com\u002Fhashgraph-online\u002Fawesome-codex-plugins\u002Fblob\u002Fmain\u002Fplugins\u002Fworktable\u002Fworktable-plugin\u002Fskills\u002Fworktable-create-or-manage-interactive-html\u002FSKILL.md",[],[],{"skillNo":121,"name":122,"nameZh":6,"description":123,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":82,"licenseFileUrl":124,"sourceHtmlUrl":125,"categories":126,"keywords":127,"publishedAt":87},"01M7DV2CADR5R7RQFFYPNAGR9Y","worktable-collaborate-threads","Read, answer, and hand off messages through durable Worktable threads with users or other authenticated participants. Use when the user asks to check addressed messages, reply to a participant, continue a thread, request another agent's help, wait briefly for a response, or watch for comments and messages sent to the agent.","https:\u002F\u002Fgithub.com\u002Fhashgraph-online\u002Fawesome-codex-plugins\u002Fblob\u002Fmain\u002Fplugins\u002Fworktable\u002Fworktable-plugin\u002Fskills\u002Fworktable-collaborate-threads\u002FLICENSE","https:\u002F\u002Fgithub.com\u002Fhashgraph-online\u002Fawesome-codex-plugins\u002Fblob\u002Fmain\u002Fplugins\u002Fworktable\u002Fworktable-plugin\u002Fskills\u002Fworktable-collaborate-threads\u002FSKILL.md",[],[]]