[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M6JVQGSZBS23CZ4J1PEAB6WZ":3,"skill-same:01M6JVQGSZBS23CZ4J1PEAB6WZ":65},{"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":30,"linkOnly":31,"markdownContent":32,"markdownBody":33,"frontMatter":34,"refName":35,"commitSha":36,"skillDirectory":37,"forksCount":38,"repositoryHtmlUrl":39,"repositoryHomepageUrl":40,"ownerHtmlUrl":41,"ownerBlogUrl":42,"ownerDescription":43,"updatedAt":44,"install":45,"resources":58},"01M6JVQGSZBS23CZ4J1PEAB6WZ","long-task-continuation",null,"Use when a task is multi-step, may span context resets or sessions, uses subagents, or risks losing state before completion.","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\u002FGanyuanRan\u002FAegis\u002Fskills\u002Flong-task-continuation\u002FSKILL.md",[],[19,20,21,22,23,24,25,26,27,28,29],"task","long","long task continuation","continuation","sessions","state","context","subagents","use","multi","when","2026-11-10 10:12:30",false,"---\nname: long-task-continuation\ndescription: \"Use when a task is multi-step, may span context resets or sessions, uses subagents, or risks losing state before completion.\"\n---\n\n# Long Task Continuation\n\n## Overview\n\nKeep long work checkpointed, resumable, drift-aware, and evidence-gated. This\nprotocol does not execute plans, dispatch subagents, run tests, or grant\ncompletion authority.\n\n## Authority Boundary\n\nThe Method Pack owns continuation discipline only. It does not own the parent\nplan, host retry\u002Fwatchdog behavior, authoritative `GateDecision`, evidence\nsufficiency, requirement acceptance, or completion.\n\n## When To Use\n\nUse this skill when the work has meaningful phases, may be compacted\u002Fresumed or\nhanded off, uses subagents, or explicitly needs continuity and drift control.\nArchitecture, contract, shared-workflow, and verification-gate changes also\nbenefit from it. Do not force it onto a short answer or one-command check.\n\nChoose exactly one state carrier:\n\n- within this continuation workflow, use a durable `work\u002F` record for\n  medium\u002Fhigh work, or for work of any complexity that actually crosses\n  sessions, needs handoff, or requires resumable state;\n- otherwise keep one inline checkpoint.\n\nMulti-step, todo-driven, possible-compaction, and subagent use do not force\ndurable records for low-complexity work by themselves. Do not create both carriers or a record per\nslice.\n\n## Required Artifacts\n\nA durable task has one process trail under\n`docs\u002Faegis\u002Fwork\u002FYYYY-MM-DD-\u003Cslug>\u002F`. It keeps logical intent\u002Fbaseline state,\nthe latest todo\u002Fcheckpoint\u002Fresume state, terminal evidence\u002Fdrift state, and a\ncompletion reflection when warranted. These are\n`TaskIntentDraft`, `BaselineReadSetHint`, `BaselineUsageDraft`,\n`ImpactStatementDraft`, `TodoCheckpointDraft`, `ResumeStateHint`,\n`DriftCheckDraft`, and `EvidenceBundleDraft` views—not authoritative runtime\nrecords or separate plan owners.\n\nRead only the lifecycle-matched section of `durable-work-guidance.md`:\n\n- `## Required Artifact Layout` and `## Create A Durable Work Record` for a new durable work record;\n- `## Update A Slice` when an existing helper-backed record needs sidecar updates;\n- `## Retry Convergence Detail` for retry\u002Fattempt bookkeeping;\n- `## Pause, Handoff, And Completion Bundle` when preparing a pause, handoff, or completion bundle; and\n- `## Expanded State Fields` only when natural checkpoint prose is ambiguous.\n\nThe reference owns artifact layout and `\u003Caegis-workspace-helper>` command\ndetail; this file owns carrier selection, resume order, drift decisions, and\nstop conditions.\n\nAn `Execution Readiness View` may be kept in the intent or active checkpoint\nfor medium\u002Fhigh, handoff-prone, long-running, subagent-driven, architecture,\ncontract, compatibility, or retirement-sensitive work. It renders existing\nintent, scope, baseline, owner, test, review, and drift constraints; it is not a\nnew JSON artifact or completion authority.\n\nPlanless Slice Lane:\n\n- When an existing parent plan\u002Fspec owns a bounded task, reuse it and the\n  current checkpoint. For a no-parent direct bounded request with no new\n  durable or unclear verification boundary, use an inline checkpoint.\n- State one compact `Slice Card`: Goal, `Parent plan\u002Fspec` (or\n  `none — direct bounded request`), Files, Boundary, Verification, and Stop.\n- The slice goal closes only that slice. Final completion returns to the parent\n  or direct bounded request through `verification-before-completion`.\n- Do not create a plan\u002Fspec merely to give a micro-slice a parent, and do not\n  create per-slice plans\u002Fspecs or work records.\n- Escalate when a new owner, contract, schema, public API, architecture,\n  migration, persistence, security\u002Fpermission, distribution\u002Frelease surface,\n  unclear verification boundary, or mismatch with parent scope or acceptance\n  appears.\n\nWhen durable architecture decisions are in scope, these work records are the\npreferred ADR Auto Backfill source. Preserve decision signals, source refs,\nalternatives, compatibility, retirement, drift, and baseline-sync questions.\n\n## Start Protocol\n\nBefore execution:\n\n1. Capture requested outcome, scope, non-goals, risks, parent plan\u002Fgoal, success\n   evidence, and stop states (`done | blocked | needs-verification |\n   scope-exceeded`).\n2. Identify required baseline refs and record acknowledged, cited, and missing\n   refs. Missing authority pauses in `needs-baseline-readback`.\n3. Choose inline or durable state once, then record the todo map, active slice,\n   completed slices\u002Fevidence, blockers, next step, and current branch\u002FHEAD.\n4. When an `Execution Readiness View` exists, retain its intent lock, scope\n   fence, baseline lock, compatibility\u002Fretirement boundary, tests, reviews,\n   evidence, and rewind rules.\n5. For a new helper-backed record, use `durable-work-guidance.md` to create and\n   structurally check it before implementation.\n\n## Retry Convergence Protocol\n\nA failed verification is another attempt in the current slice, not a new\nslice. Keep failed-attempt telemetry out of terminal evidence and normal\ncommits. Only `evidence-finalized`, `blocked`, or `abandoned` is terminal.\nWhen retry state reaches `process-artifact-pressure`, stop auto-retry and route\nto `systematic-debugging` or `verification-before-completion`. Load the durable\nreference only when the attempt\u002Fevidence commands or sidecar rules are needed.\n\n## Per-Slice Protocol\n\nBefore each slice, state the current goal\u002Ftodo, intended edits, explicit\nnon-edits, verification, and readiness alignment. A bounded parent-plan or\nno-parent slice uses the compact Slice Card rather than a new plan\u002Fspec.\n\nAfter each slice, update completed todos, evidence refs, newly used baseline\nrefs, blockers, next step, and drift decision. When an active helper-backed work record exists, read `durable-work-guidance.md` and update that same record;\nnever create another workstream for bookkeeping.\n\nWhen patch-shape\u002Fripple triage, an H-class finding, or a bounded compatibility\nmitigation fired, a locally green result does not clear the direction. Retain\n`PatchShape`, `CanonicalOwner`, `UpwardDrillSignal`, latest outcome, and one\nbounded evidence ref; do not copy raw logs or full diffs. If no fresh evidence\nexists, the state is `needs-verification` or `partial`. For repairs or\noptimization, retain the causal scope, evidence references, unresolved\ninfluences that could change the solution, and verification coverage in the\nsame checkpoint. Compression must not turn one confirmed cause into a complete\nroot claim or erase counterevidence; recheck these unknowns before resuming\nretained changes. Do not add a parallel causal record.\n\n## Resume Protocol\n\nResume in this order:\n\n1. Read original intent, parent plan\u002Fgoal, latest checkpoint and resume hint.\n   Reconcile current user instructions: continuation, amendment, pause, or\n   replacement. Preserve outstanding deliverables; update authorized scope\n   before treating a valid amendment as drift. Internal milestones are not\n   substitutes for the user's delivered result.\n2. Re-read required baseline refs and relevant active `CONTEXT.md` language.\n3. Read the `Execution Readiness View` when present.\n4. Compare checkpoint branch\u002FHEAD, completed commits, evidence refs, and claims\n   with the current worktree.\n   Treat inherited completion claims as unverified until the worktree confirms\n   them. Correct contradictions in the checkpoint, disclose them in the final\n   report, and do not republish stale claims as current.\n   Preserve the claim's subject, scope and resume-time state; distinguish that\n   from later repair and from historical execution you cannot verify. One\n   accurate correction may cover related claims. The record must adopt it,\n   without elsewhere denying it or assigning it to another scope. A reviewer's\n   classification is contestable: if material disagreement remains unresolved\n   after checking evidence, retain `needs-verification` without forcing assent.\n   If evidence resolves it, retain the supported conclusion and verify normally.\n5. Compare the active slice against intent lock, scope fence, baseline lock,\n   compatibility\u002Fretirement boundary, tests, reviews, and non-goals.\n6. Re-run the drift decision, then name the next smallest authorized action.\n\nAny disagreement among plan, checkpoint, baseline, context, readiness view, or\nworktree pauses execution. A semantic conflict routes to\n`establishing-project-context`; an unplanned repair re-reads the retained\ninvariant, owner seam, patch shape, and causal topology, then route comparison to\n`systematic-debugging`. A new carrier name alone does not prove a new direction. Never resume from memory alone.\n\n## Drift Check\n\nCheck original intent and stop condition, parent scope\u002Facceptance, compatibility,\nnew owners\u002Ffallbacks\u002Fadapters\u002Fbranches, retirement, evidence freshness, and any\nreadiness locks. Allowed decisions are `continue`, `pause-for-user`,\n`needs-baseline-readback`, `needs-verification`, and `blocked`.\n\nNever emit `gate-passed`, `completion-granted`, or `authoritatively-safe`.\n\n## Completion Candidate Protocol\n\nBefore a completion claim:\n\n1. Use `aegis:verification-before-completion`.\n2. Confirm every todo has status, blockers are resolved\u002Fexternalized, evidence\n   covers acceptance, and drift has no blocking state.\n3. If a durable record exists, load `durable-work-guidance.md` for the completion\n   bundle and structural workspace check.\n4. For durable architecture work, pass the work record, proof bundle and ADR signals\n   to verification for ADR Backfill Check.\n\nGenerated packs are future-runtime inputs only. Method Pack output remains\nverified evidence and advisory judgment, not authoritative completion.\n\n## Minimal Reporting Shape\n\nReport naturally and omit empty structures. Keep these semantic slots visible:\n`Aegis Visibility`; current todo\u002Factive\u002Fcompleted\u002Fnext; baseline usage decision;\nreadiness state when present; fresh evidence; inherited-claim corrections when\na resumed record overstated its state; retry\u002Fconvergence state when\nrelevant; drift decision; risk\u002Funknown; and the next smallest safe action.\n","# Long Task Continuation\n\n## Overview\n\nKeep long work checkpointed, resumable, drift-aware, and evidence-gated. This\nprotocol does not execute plans, dispatch subagents, run tests, or grant\ncompletion authority.\n\n## Authority Boundary\n\nThe Method Pack owns continuation discipline only. It does not own the parent\nplan, host retry\u002Fwatchdog behavior, authoritative `GateDecision`, evidence\nsufficiency, requirement acceptance, or completion.\n\n## When To Use\n\nUse this skill when the work has meaningful phases, may be compacted\u002Fresumed or\nhanded off, uses subagents, or explicitly needs continuity and drift control.\nArchitecture, contract, shared-workflow, and verification-gate changes also\nbenefit from it. Do not force it onto a short answer or one-command check.\n\nChoose exactly one state carrier:\n\n- within this continuation workflow, use a durable `work\u002F` record for\n  medium\u002Fhigh work, or for work of any complexity that actually crosses\n  sessions, needs handoff, or requires resumable state;\n- otherwise keep one inline checkpoint.\n\nMulti-step, todo-driven, possible-compaction, and subagent use do not force\ndurable records for low-complexity work by themselves. Do not create both carriers or a record per\nslice.\n\n## Required Artifacts\n\nA durable task has one process trail under\n`docs\u002Faegis\u002Fwork\u002FYYYY-MM-DD-\u003Cslug>\u002F`. It keeps logical intent\u002Fbaseline state,\nthe latest todo\u002Fcheckpoint\u002Fresume state, terminal evidence\u002Fdrift state, and a\ncompletion reflection when warranted. These are\n`TaskIntentDraft`, `BaselineReadSetHint`, `BaselineUsageDraft`,\n`ImpactStatementDraft`, `TodoCheckpointDraft`, `ResumeStateHint`,\n`DriftCheckDraft`, and `EvidenceBundleDraft` views—not authoritative runtime\nrecords or separate plan owners.\n\nRead only the lifecycle-matched section of `durable-work-guidance.md`:\n\n- `## Required Artifact Layout` and `## Create A Durable Work Record` for a new durable work record;\n- `## Update A Slice` when an existing helper-backed record needs sidecar updates;\n- `## Retry Convergence Detail` for retry\u002Fattempt bookkeeping;\n- `## Pause, Handoff, And Completion Bundle` when preparing a pause, handoff, or completion bundle; and\n- `## Expanded State Fields` only when natural checkpoint prose is ambiguous.\n\nThe reference owns artifact layout and `\u003Caegis-workspace-helper>` command\ndetail; this file owns carrier selection, resume order, drift decisions, and\nstop conditions.\n\nAn `Execution Readiness View` may be kept in the intent or active checkpoint\nfor medium\u002Fhigh, handoff-prone, long-running, subagent-driven, architecture,\ncontract, compatibility, or retirement-sensitive work. It renders existing\nintent, scope, baseline, owner, test, review, and drift constraints; it is not a\nnew JSON artifact or completion authority.\n\nPlanless Slice Lane:\n\n- When an existing parent plan\u002Fspec owns a bounded task, reuse it and the\n  current checkpoint. For a no-parent direct bounded request with no new\n  durable or unclear verification boundary, use an inline checkpoint.\n- State one compact `Slice Card`: Goal, `Parent plan\u002Fspec` (or\n  `none — direct bounded request`), Files, Boundary, Verification, and Stop.\n- The slice goal closes only that slice. Final completion returns to the parent\n  or direct bounded request through `verification-before-completion`.\n- Do not create a plan\u002Fspec merely to give a micro-slice a parent, and do not\n  create per-slice plans\u002Fspecs or work records.\n- Escalate when a new owner, contract, schema, public API, architecture,\n  migration, persistence, security\u002Fpermission, distribution\u002Frelease surface,\n  unclear verification boundary, or mismatch with parent scope or acceptance\n  appears.\n\nWhen durable architecture decisions are in scope, these work records are the\npreferred ADR Auto Backfill source. Preserve decision signals, source refs,\nalternatives, compatibility, retirement, drift, and baseline-sync questions.\n\n## Start Protocol\n\nBefore execution:\n\n1. Capture requested outcome, scope, non-goals, risks, parent plan\u002Fgoal, success\n   evidence, and stop states (`done | blocked | needs-verification |\n   scope-exceeded`).\n2. Identify required baseline refs and record acknowledged, cited, and missing\n   refs. Missing authority pauses in `needs-baseline-readback`.\n3. Choose inline or durable state once, then record the todo map, active slice,\n   completed slices\u002Fevidence, blockers, next step, and current branch\u002FHEAD.\n4. When an `Execution Readiness View` exists, retain its intent lock, scope\n   fence, baseline lock, compatibility\u002Fretirement boundary, tests, reviews,\n   evidence, and rewind rules.\n5. For a new helper-backed record, use `durable-work-guidance.md` to create and\n   structurally check it before implementation.\n\n## Retry Convergence Protocol\n\nA failed verification is another attempt in the current slice, not a new\nslice. Keep failed-attempt telemetry out of terminal evidence and normal\ncommits. Only `evidence-finalized`, `blocked`, or `abandoned` is terminal.\nWhen retry state reaches `process-artifact-pressure`, stop auto-retry and route\nto `systematic-debugging` or `verification-before-completion`. Load the durable\nreference only when the attempt\u002Fevidence commands or sidecar rules are needed.\n\n## Per-Slice Protocol\n\nBefore each slice, state the current goal\u002Ftodo, intended edits, explicit\nnon-edits, verification, and readiness alignment. A bounded parent-plan or\nno-parent slice uses the compact Slice Card rather than a new plan\u002Fspec.\n\nAfter each slice, update completed todos, evidence refs, newly used baseline\nrefs, blockers, next step, and drift decision. When an active helper-backed work record exists, read `durable-work-guidance.md` and update that same record;\nnever create another workstream for bookkeeping.\n\nWhen patch-shape\u002Fripple triage, an H-class finding, or a bounded compatibility\nmitigation fired, a locally green result does not clear the direction. Retain\n`PatchShape`, `CanonicalOwner`, `UpwardDrillSignal`, latest outcome, and one\nbounded evidence ref; do not copy raw logs or full diffs. If no fresh evidence\nexists, the state is `needs-verification` or `partial`. For repairs or\noptimization, retain the causal scope, evidence references, unresolved\ninfluences that could change the solution, and verification coverage in the\nsame checkpoint. Compression must not turn one confirmed cause into a complete\nroot claim or erase counterevidence; recheck these unknowns before resuming\nretained changes. Do not add a parallel causal record.\n\n## Resume Protocol\n\nResume in this order:\n\n1. Read original intent, parent plan\u002Fgoal, latest checkpoint and resume hint.\n   Reconcile current user instructions: continuation, amendment, pause, or\n   replacement. Preserve outstanding deliverables; update authorized scope\n   before treating a valid amendment as drift. Internal milestones are not\n   substitutes for the user's delivered result.\n2. Re-read required baseline refs and relevant active `CONTEXT.md` language.\n3. Read the `Execution Readiness View` when present.\n4. Compare checkpoint branch\u002FHEAD, completed commits, evidence refs, and claims\n   with the current worktree.\n   Treat inherited completion claims as unverified until the worktree confirms\n   them. Correct contradictions in the checkpoint, disclose them in the final\n   report, and do not republish stale claims as current.\n   Preserve the claim's subject, scope and resume-time state; distinguish that\n   from later repair and from historical execution you cannot verify. One\n   accurate correction may cover related claims. The record must adopt it,\n   without elsewhere denying it or assigning it to another scope. A reviewer's\n   classification is contestable: if material disagreement remains unresolved\n   after checking evidence, retain `needs-verification` without forcing assent.\n   If evidence resolves it, retain the supported conclusion and verify normally.\n5. Compare the active slice against intent lock, scope fence, baseline lock,\n   compatibility\u002Fretirement boundary, tests, reviews, and non-goals.\n6. Re-run the drift decision, then name the next smallest authorized action.\n\nAny disagreement among plan, checkpoint, baseline, context, readiness view, or\nworktree pauses execution. A semantic conflict routes to\n`establishing-project-context`; an unplanned repair re-reads the retained\ninvariant, owner seam, patch shape, and causal topology, then route comparison to\n`systematic-debugging`. A new carrier name alone does not prove a new direction. Never resume from memory alone.\n\n## Drift Check\n\nCheck original intent and stop condition, parent scope\u002Facceptance, compatibility,\nnew owners\u002Ffallbacks\u002Fadapters\u002Fbranches, retirement, evidence freshness, and any\nreadiness locks. Allowed decisions are `continue`, `pause-for-user`,\n`needs-baseline-readback`, `needs-verification`, and `blocked`.\n\nNever emit `gate-passed`, `completion-granted`, or `authoritatively-safe`.\n\n## Completion Candidate Protocol\n\nBefore a completion claim:\n\n1. Use `aegis:verification-before-completion`.\n2. Confirm every todo has status, blockers are resolved\u002Fexternalized, evidence\n   covers acceptance, and drift has no blocking state.\n3. If a durable record exists, load `durable-work-guidance.md` for the completion\n   bundle and structural workspace check.\n4. For durable architecture work, pass the work record, proof bundle and ADR signals\n   to verification for ADR Backfill Check.\n\nGenerated packs are future-runtime inputs only. Method Pack output remains\nverified evidence and advisory judgment, not authoritative completion.\n\n## Minimal Reporting Shape\n\nReport naturally and omit empty structures. Keep these semantic slots visible:\n`Aegis Visibility`; current todo\u002Factive\u002Fcompleted\u002Fnext; baseline usage decision;\nreadiness state when present; fresh evidence; inherited-claim corrections when\na resumed record overstated its state; retry\u002Fconvergence state when\nrelevant; drift decision; risk\u002Funknown; and the next smallest safe action.\n",{"name":5,"description":7},"main","b0f0a87593c578a7898eccaf1b363f7f87c1f99b","plugins\u002FGanyuanRan\u002FAegis\u002Fskills\u002Flong-task-continuation",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":46,"prompt":56,"zipAvailable":57},[47,50,53],{"tool":48,"command":49},"npx","npx skills add hashgraph-online\u002Fawesome-codex-plugins --skill long-task-continuation",{"tool":51,"command":52},"bunx","bunx skills add hashgraph-online\u002Fawesome-codex-plugins --skill long-task-continuation",{"tool":54,"command":55},"pnpm","pnpm dlx skills add hashgraph-online\u002Fawesome-codex-plugins --skill long-task-continuation","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Fhashgraph-online\u002Fawesome-codex-plugins\u002Fblob\u002Fmain\u002Fplugins\u002FGanyuanRan\u002FAegis\u002Fskills\u002Flong-task-continuation\u002FSKILL.md",true,[59],{"path":60,"resourceType":61,"resourceTypeDesc":62,"sizeBytes":63,"sourceHtmlUrl":64},"durable-work-guidance.md","REFERENCE","参考文档",5783,"https:\u002F\u002Fgithub.com\u002Fhashgraph-online\u002Fawesome-codex-plugins\u002Fblob\u002Fmain\u002Fplugins\u002FGanyuanRan\u002FAegis\u002Fskills\u002Flong-task-continuation\u002Fdurable-work-guidance.md",[66,76,84,92,100,108],{"skillNo":67,"name":68,"nameZh":6,"description":69,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":70,"licenseFileUrl":71,"sourceHtmlUrl":72,"categories":73,"keywords":74,"publishedAt":75},"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":77,"name":78,"nameZh":6,"description":79,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":70,"licenseFileUrl":80,"sourceHtmlUrl":81,"categories":82,"keywords":83,"publishedAt":75},"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":85,"name":86,"nameZh":6,"description":87,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":70,"licenseFileUrl":88,"sourceHtmlUrl":89,"categories":90,"keywords":91,"publishedAt":75},"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":93,"name":94,"nameZh":6,"description":95,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":70,"licenseFileUrl":96,"sourceHtmlUrl":97,"categories":98,"keywords":99,"publishedAt":75},"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":101,"name":102,"nameZh":6,"description":103,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":70,"licenseFileUrl":104,"sourceHtmlUrl":105,"categories":106,"keywords":107,"publishedAt":75},"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":109,"name":110,"nameZh":6,"description":111,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":70,"licenseFileUrl":112,"sourceHtmlUrl":113,"categories":114,"keywords":115,"publishedAt":75},"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",[],[]]