[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M6MP9CG0EJYBT7V4FCXEDG0A":3,"skill-same:01M6MP9CG0EJYBT7V4FCXEDG0A":64},{"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":23,"publishedAt":35,"linkOnly":36,"markdownContent":37,"markdownBody":38,"frontMatter":39,"refName":40,"commitSha":41,"skillDirectory":42,"forksCount":43,"repositoryHtmlUrl":44,"repositoryHomepageUrl":45,"ownerHtmlUrl":46,"ownerBlogUrl":47,"ownerDescription":48,"updatedAt":49,"install":50,"resources":63},"01M6MP9CG0EJYBT7V4FCXEDG0A","resuming",null,"Resume an interrupted workflow run with verify-first strategy — loads sidecar state, verifies the last step, and continues execution.","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\u002Fyimwoo\u002Fhotl-plugin\u002Fskills\u002Fresuming\u002FSKILL.md",[18],{"categoryNo":19,"categoryName":20,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000038","人力资源","PROFESSION","适用职业",[5,24,25,26,27,28,29,30,31,32,33,34],"workflow","run","state","execution","first","verify","strategy","resume","loads","with","last","2026-11-10 10:12:30",false,"---\nname: resuming\ndescription: Resume an interrupted workflow run with verify-first strategy — loads sidecar state, verifies the last step, and continues execution.\n---\n\n# HOTL Resume\n\n## Overview\n\nResume a previously interrupted workflow run. HOTL persists execution state in a sidecar file (`.hotl\u002Fstate\u002F\u003Crun-id>.json`). On resume, it uses a verify-first strategy to determine whether the interrupted step already succeeded before continuing.\n\nFor governed native runs, call `hotl-rt reconcile \u003Crun-id>` (or the selected driver's equivalent) before resuming. Treat its result as a read-only recommendation and retain this skill's verify-first rules; never infer completion from a host session status.\n\n**Announce:** \"Looking for interrupted HOTL runs...\"\n\n## Sidecar State\n\nExecution state is persisted at `.hotl\u002Fstate\u002F\u003Crun-id>.json`. This is the **authoritative source of truth** — workflow checkboxes are a human-visible mirror that may drift after a crash.\n\n### Schema\n\n```json\n{\n  \"run_id\": \"\u003Cslug>-\u003CYYYYMMDDTHHMMSSZ>-\u003C12-hex-nonce>\",\n  \"workflow_path\": \"\u002Fabs\u002Fpath\u002Fto\u002Fexecution-root\u002Fdocs\u002Fplans\u002FYYYY-MM-DD-\u003Cslug>-workflow.md\",\n  \"source_workflow_path\": \"\u002Fabs\u002Fpath\u002Fto\u002Foriginal\u002Fworkflow.md\",\n  \"workflow_slug\": \"\u003Cslug>\",\n  \"intent\": \"\u003Cfrom workflow frontmatter>\",\n  \"branch\": \"\u003Cbranch name>\",\n  \"repo_root\": \"\u002Fabs\u002Fpath\u002Fto\u002Frepo\",\n  \"execution_root\": \"\u002Fabs\u002Fpath\u002Fto\u002Frepo-or-worktree\",\n  \"worktree_path\": null,\n  \"executor_mode\": \"loop | executing-plans | subagent\",\n  \"started_at\": \"\u003CISO 8601>\",\n  \"last_update\": \"\u003CISO 8601>\",\n  \"status\": \"running | paused | blocked | ready_to_finish | completed | abandoned\",\n  \"ownership_required\": true,\n  \"controller\": {\"status\": \"active\", \"owner_id\": \"\u003Cstable-controller-id>\", \"lease_expires_epoch\": 0},\n  \"current_step\": 3,\n  \"total_steps\": 8,\n  \"steps\": [\n    {\"number\": 1, \"name\": \"\u003Cstep name>\", \"status\": \"done | in_progress | pending | failed | blocked\", \"attempts\": 1},\n    {\"number\": 2, \"name\": \"\u003Cstep name>\", \"status\": \"done\", \"attempts\": 2}\n  ],\n  \"last_verify_output\": \"\u003Ccaptured stdout\u002Fstderr from last verify>\"\n}\n```\n\n### Run ID Format\n\n`\u003Cslug>-\u003CYYYYMMDDTHHMMSSZ>-\u003C12-hex-nonce>` (e.g., `add-auth-20260320T212315Z-a1b2c3d4e5f6`). The semantic workflow slug and UTC start time keep the identifier readable; operating-system entropy keeps simultaneous runs unique across independent execution roots. Legacy timestamp-only run IDs remain readable.\n\n### Status Values\n\n- `running` — execution is in progress (or was interrupted)\n- `paused` — stopped at a `gate: human` or a `verify: human-review` checkpoint awaiting approval\n- `blocked` — stopped due to verify failure at max_iterations\n- `ready_to_finish` — all required execution evidence passed; explicit finish disposition is still pending\n- `completed` — execution evidence passed and finish disposition was recorded\n- `abandoned` — user explicitly abandoned the run\n\n## Run Resolution\n\n1. If the user provides a `run_id` → load that specific run\n2. If the user provides a workflow filename → locate matching runs by `workflow_path` or `source_workflow_path`\n3. If **one match** → use it\n4. If **multiple matches** → list all matching runs with run_id, step progress, branch, execution_root, and age. Ask the user which to resume or whether to start fresh. **Never silently choose among multiple runs.**\n5. If **no match** → report \"No interrupted run found for this workflow.\"\n\n### Worktree-Aware Locator\n\nUse `scripts\u002Fhotl-locate-run.sh` when available:\n\n```bash\nscripts\u002Fhotl-locate-run.sh --workflow \u003Cworkflow-file>\nscripts\u002Fhotl-locate-run.sh --run-id \u003Crun-id>\n```\n\nThe locator prints a JSON array and scans:\n1. Current checkout\n2. `git worktree list --porcelain` roots for the repo\n3. HOTL's default isolated worktree root: `$(dirname \u003Crepo-root>)\u002F.hotl-worktrees\u002F$(basename \u003Crepo-root>)\u002F*`\n\nThis is required for default isolated-worktree execution. In that mode, `.hotl\u002Fstate\u002F\u003Crun-id>.json` is created inside the execution worktree, while the workflow file usually remains in the authoring checkout. A new session started from the authoring checkout must find the existing execution worktree and resume there instead of trying to create a new worktree.\n\nIf `hotl-locate-run.sh` is unavailable, manually scan the same locations. Do not run normal Branch\u002FWorktree Preflight until after you have ruled out an interrupted run; preflight will reject an existing execution worktree and can incorrectly look like a start-from-scratch path.\n\n## Controller Ownership Resolution\n\n`status: running` and `last_update` age are not ownership signals. Age alone never authorizes takeover.\n\n1. Run `hotl-rt owner status --run-id \u003Crun-id>` before any mutation.\n2. If ownership is `legacy-unclaimed` or `released`, run `owner claim --owner \u003Cstable-controller-id> --lease-seconds \u003Cbounded-lease> --run-id \u003Crun-id>`. Parse the returned one-time token without displaying it and export it as `HOTL_OWNER_TOKEN`.\n3. If the lease is `stale`, run `owner takeover --owner \u003Cstable-controller-id> --reason \u003Cauditable-recovery-reason> --lease-seconds \u003Cbounded-lease> --run-id \u003Crun-id>` and retain the new token.\n4. If another controller lease is active, do not mutate. Obtain an explicit `owner handoff` from that controller, or pause for human review before a forced `owner takeover --force` with a recorded reason.\n5. Once owned, run `owner heartbeat` before and after long verification\u002Faction work and at safe transitions. Use explicit `owner release` when stopping or after a completed finish.\n\nNever put `HOTL_OWNER_TOKEN` in chat, delegated prompts, reports, or committed files. Every resumed mutation must inherit it.\n\n## Resume Flow (Verify-First)\n\n```\n1. Load sidecar state for the resolved run\n2. Change into `execution_root` from the sidecar before invoking runtime\u002Fhelpers\n3. Resolve and claim\u002Ftake over controller ownership using the rules above, then export `HOTL_OWNER_TOKEN`\n4. Check for existing report at report_path from the sidecar\n   - If report exists: surface its path to the user and continue appending to it\n   - If the report is missing or its summary has drifted from state: let the runtime deterministically reconstruct the summary from authoritative sidecar state\n5. Run `hotl-rt reconcile \u003Crun-id>` and inspect sensitive effects before step recovery:\n   - If any effect is `in_progress` or `uncertain`, inspect the external target and use `action reconcile` with evidence. Never replay `action begin` merely because the host session disappeared.\n   - If an approved effect is `not_started`, continue through the normal `action begin` → operation → `action complete` lifecycle with its existing idempotency key.\n6. If status is `ready_to_finish`, do not rerun steps or finalize. Go directly to `hotl:finishing-a-development-branch`, record the explicit finish disposition, release ownership, and require a sufficient receipt.\n7. Repair workflow checkboxes from sidecar if drift is detected\n   (crash may have interrupted between sidecar write and checkbox update)\n8. Find the current unfinished step (first step without status: `done`; `in_progress`, `pending`, `failed`, and `blocked` are unfinished)\n9. Run `owner heartbeat`, then check verify type for that step:\n\n   a. Machine-runnable verify (type: shell or type: artifact):\n      → Run verify first\n      → If verify PASSES: mark step complete, advance to next step\n      → If verify FAILS: re-run the step body from the beginning\n\n   b. Browser verify (type: browser):\n      → If browser tooling available: run verify\n      → If unavailable: downgrade to human-review with check text\n\n   c. Human-review verify or no verify:\n      → Pause and ask: \"Step N was in progress when the session ended.\n        Re-run the step, or skip after manual inspection?\"\n\n10. Continue normal execution from the resumed point, using the original `run_id` and `HOTL_OWNER_TOKEN` for every owner\u002Fstep\u002Fgate\u002Faction\u002Fbudget\u002Ffinalize\u002Ffinish mutation\n11. If the resumed run reaches `ready_to_finish`, keep using that same `run_id` when invoking `hotl:finishing-a-development-branch`; `completed` is valid only after finish disposition\n12. Use the original executor mode (loop, executing-plans, or subagent)\n```\n\n## Checkpoint Drift Repair\n\nOn resume, compare sidecar step statuses with workflow checkboxes:\n- If sidecar says `done` but checkbox shows `[ ]` → update to `[x]`\n- If sidecar says `pending` but checkbox shows `[x]` → update to `[ ]`\n- Log any repairs: \"Repaired checkbox drift: Step N marked done from sidecar state\"\n\n## What This Skill Does NOT Do\n\n- Does not silently choose among unrelated interrupted runs; scope by `run_id` or workflow, then ask when multiple matches remain\n- Does not resume runs in a different executor mode than originally started\n- Does not merge partial work from two interrupted runs of the same workflow\n","# HOTL Resume\n\n## Overview\n\nResume a previously interrupted workflow run. HOTL persists execution state in a sidecar file (`.hotl\u002Fstate\u002F\u003Crun-id>.json`). On resume, it uses a verify-first strategy to determine whether the interrupted step already succeeded before continuing.\n\nFor governed native runs, call `hotl-rt reconcile \u003Crun-id>` (or the selected driver's equivalent) before resuming. Treat its result as a read-only recommendation and retain this skill's verify-first rules; never infer completion from a host session status.\n\n**Announce:** \"Looking for interrupted HOTL runs...\"\n\n## Sidecar State\n\nExecution state is persisted at `.hotl\u002Fstate\u002F\u003Crun-id>.json`. This is the **authoritative source of truth** — workflow checkboxes are a human-visible mirror that may drift after a crash.\n\n### Schema\n\n```json\n{\n  \"run_id\": \"\u003Cslug>-\u003CYYYYMMDDTHHMMSSZ>-\u003C12-hex-nonce>\",\n  \"workflow_path\": \"\u002Fabs\u002Fpath\u002Fto\u002Fexecution-root\u002Fdocs\u002Fplans\u002FYYYY-MM-DD-\u003Cslug>-workflow.md\",\n  \"source_workflow_path\": \"\u002Fabs\u002Fpath\u002Fto\u002Foriginal\u002Fworkflow.md\",\n  \"workflow_slug\": \"\u003Cslug>\",\n  \"intent\": \"\u003Cfrom workflow frontmatter>\",\n  \"branch\": \"\u003Cbranch name>\",\n  \"repo_root\": \"\u002Fabs\u002Fpath\u002Fto\u002Frepo\",\n  \"execution_root\": \"\u002Fabs\u002Fpath\u002Fto\u002Frepo-or-worktree\",\n  \"worktree_path\": null,\n  \"executor_mode\": \"loop | executing-plans | subagent\",\n  \"started_at\": \"\u003CISO 8601>\",\n  \"last_update\": \"\u003CISO 8601>\",\n  \"status\": \"running | paused | blocked | ready_to_finish | completed | abandoned\",\n  \"ownership_required\": true,\n  \"controller\": {\"status\": \"active\", \"owner_id\": \"\u003Cstable-controller-id>\", \"lease_expires_epoch\": 0},\n  \"current_step\": 3,\n  \"total_steps\": 8,\n  \"steps\": [\n    {\"number\": 1, \"name\": \"\u003Cstep name>\", \"status\": \"done | in_progress | pending | failed | blocked\", \"attempts\": 1},\n    {\"number\": 2, \"name\": \"\u003Cstep name>\", \"status\": \"done\", \"attempts\": 2}\n  ],\n  \"last_verify_output\": \"\u003Ccaptured stdout\u002Fstderr from last verify>\"\n}\n```\n\n### Run ID Format\n\n`\u003Cslug>-\u003CYYYYMMDDTHHMMSSZ>-\u003C12-hex-nonce>` (e.g., `add-auth-20260320T212315Z-a1b2c3d4e5f6`). The semantic workflow slug and UTC start time keep the identifier readable; operating-system entropy keeps simultaneous runs unique across independent execution roots. Legacy timestamp-only run IDs remain readable.\n\n### Status Values\n\n- `running` — execution is in progress (or was interrupted)\n- `paused` — stopped at a `gate: human` or a `verify: human-review` checkpoint awaiting approval\n- `blocked` — stopped due to verify failure at max_iterations\n- `ready_to_finish` — all required execution evidence passed; explicit finish disposition is still pending\n- `completed` — execution evidence passed and finish disposition was recorded\n- `abandoned` — user explicitly abandoned the run\n\n## Run Resolution\n\n1. If the user provides a `run_id` → load that specific run\n2. If the user provides a workflow filename → locate matching runs by `workflow_path` or `source_workflow_path`\n3. If **one match** → use it\n4. If **multiple matches** → list all matching runs with run_id, step progress, branch, execution_root, and age. Ask the user which to resume or whether to start fresh. **Never silently choose among multiple runs.**\n5. If **no match** → report \"No interrupted run found for this workflow.\"\n\n### Worktree-Aware Locator\n\nUse `scripts\u002Fhotl-locate-run.sh` when available:\n\n```bash\nscripts\u002Fhotl-locate-run.sh --workflow \u003Cworkflow-file>\nscripts\u002Fhotl-locate-run.sh --run-id \u003Crun-id>\n```\n\nThe locator prints a JSON array and scans:\n1. Current checkout\n2. `git worktree list --porcelain` roots for the repo\n3. HOTL's default isolated worktree root: `$(dirname \u003Crepo-root>)\u002F.hotl-worktrees\u002F$(basename \u003Crepo-root>)\u002F*`\n\nThis is required for default isolated-worktree execution. In that mode, `.hotl\u002Fstate\u002F\u003Crun-id>.json` is created inside the execution worktree, while the workflow file usually remains in the authoring checkout. A new session started from the authoring checkout must find the existing execution worktree and resume there instead of trying to create a new worktree.\n\nIf `hotl-locate-run.sh` is unavailable, manually scan the same locations. Do not run normal Branch\u002FWorktree Preflight until after you have ruled out an interrupted run; preflight will reject an existing execution worktree and can incorrectly look like a start-from-scratch path.\n\n## Controller Ownership Resolution\n\n`status: running` and `last_update` age are not ownership signals. Age alone never authorizes takeover.\n\n1. Run `hotl-rt owner status --run-id \u003Crun-id>` before any mutation.\n2. If ownership is `legacy-unclaimed` or `released`, run `owner claim --owner \u003Cstable-controller-id> --lease-seconds \u003Cbounded-lease> --run-id \u003Crun-id>`. Parse the returned one-time token without displaying it and export it as `HOTL_OWNER_TOKEN`.\n3. If the lease is `stale`, run `owner takeover --owner \u003Cstable-controller-id> --reason \u003Cauditable-recovery-reason> --lease-seconds \u003Cbounded-lease> --run-id \u003Crun-id>` and retain the new token.\n4. If another controller lease is active, do not mutate. Obtain an explicit `owner handoff` from that controller, or pause for human review before a forced `owner takeover --force` with a recorded reason.\n5. Once owned, run `owner heartbeat` before and after long verification\u002Faction work and at safe transitions. Use explicit `owner release` when stopping or after a completed finish.\n\nNever put `HOTL_OWNER_TOKEN` in chat, delegated prompts, reports, or committed files. Every resumed mutation must inherit it.\n\n## Resume Flow (Verify-First)\n\n```\n1. Load sidecar state for the resolved run\n2. Change into `execution_root` from the sidecar before invoking runtime\u002Fhelpers\n3. Resolve and claim\u002Ftake over controller ownership using the rules above, then export `HOTL_OWNER_TOKEN`\n4. Check for existing report at report_path from the sidecar\n   - If report exists: surface its path to the user and continue appending to it\n   - If the report is missing or its summary has drifted from state: let the runtime deterministically reconstruct the summary from authoritative sidecar state\n5. Run `hotl-rt reconcile \u003Crun-id>` and inspect sensitive effects before step recovery:\n   - If any effect is `in_progress` or `uncertain`, inspect the external target and use `action reconcile` with evidence. Never replay `action begin` merely because the host session disappeared.\n   - If an approved effect is `not_started`, continue through the normal `action begin` → operation → `action complete` lifecycle with its existing idempotency key.\n6. If status is `ready_to_finish`, do not rerun steps or finalize. Go directly to `hotl:finishing-a-development-branch`, record the explicit finish disposition, release ownership, and require a sufficient receipt.\n7. Repair workflow checkboxes from sidecar if drift is detected\n   (crash may have interrupted between sidecar write and checkbox update)\n8. Find the current unfinished step (first step without status: `done`; `in_progress`, `pending`, `failed`, and `blocked` are unfinished)\n9. Run `owner heartbeat`, then check verify type for that step:\n\n   a. Machine-runnable verify (type: shell or type: artifact):\n      → Run verify first\n      → If verify PASSES: mark step complete, advance to next step\n      → If verify FAILS: re-run the step body from the beginning\n\n   b. Browser verify (type: browser):\n      → If browser tooling available: run verify\n      → If unavailable: downgrade to human-review with check text\n\n   c. Human-review verify or no verify:\n      → Pause and ask: \"Step N was in progress when the session ended.\n        Re-run the step, or skip after manual inspection?\"\n\n10. Continue normal execution from the resumed point, using the original `run_id` and `HOTL_OWNER_TOKEN` for every owner\u002Fstep\u002Fgate\u002Faction\u002Fbudget\u002Ffinalize\u002Ffinish mutation\n11. If the resumed run reaches `ready_to_finish`, keep using that same `run_id` when invoking `hotl:finishing-a-development-branch`; `completed` is valid only after finish disposition\n12. Use the original executor mode (loop, executing-plans, or subagent)\n```\n\n## Checkpoint Drift Repair\n\nOn resume, compare sidecar step statuses with workflow checkboxes:\n- If sidecar says `done` but checkbox shows `[ ]` → update to `[x]`\n- If sidecar says `pending` but checkbox shows `[x]` → update to `[ ]`\n- Log any repairs: \"Repaired checkbox drift: Step N marked done from sidecar state\"\n\n## What This Skill Does NOT Do\n\n- Does not silently choose among unrelated interrupted runs; scope by `run_id` or workflow, then ask when multiple matches remain\n- Does not resume runs in a different executor mode than originally started\n- Does not merge partial work from two interrupted runs of the same workflow\n",{"name":5,"description":7},"main","2b63f856ce19c2a797929cacabd9e0fc936812fa","plugins\u002Fyimwoo\u002Fhotl-plugin\u002Fskills\u002Fresuming",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":51,"prompt":61,"zipAvailable":62},[52,55,58],{"tool":53,"command":54},"npx","npx skills add hashgraph-online\u002Fawesome-codex-plugins --skill resuming",{"tool":56,"command":57},"bunx","bunx skills add hashgraph-online\u002Fawesome-codex-plugins --skill resuming",{"tool":59,"command":60},"pnpm","pnpm dlx skills add hashgraph-online\u002Fawesome-codex-plugins --skill resuming","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Fhashgraph-online\u002Fawesome-codex-plugins\u002Fblob\u002Fmain\u002Fplugins\u002Fyimwoo\u002Fhotl-plugin\u002Fskills\u002Fresuming\u002FSKILL.md",true,[],[65,75,83,91,99,107],{"skillNo":66,"name":67,"nameZh":6,"description":68,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":69,"licenseFileUrl":70,"sourceHtmlUrl":71,"categories":72,"keywords":73,"publishedAt":74},"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":76,"name":77,"nameZh":6,"description":78,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":69,"licenseFileUrl":79,"sourceHtmlUrl":80,"categories":81,"keywords":82,"publishedAt":74},"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":84,"name":85,"nameZh":6,"description":86,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":69,"licenseFileUrl":87,"sourceHtmlUrl":88,"categories":89,"keywords":90,"publishedAt":74},"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":92,"name":93,"nameZh":6,"description":94,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":69,"licenseFileUrl":95,"sourceHtmlUrl":96,"categories":97,"keywords":98,"publishedAt":74},"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":100,"name":101,"nameZh":6,"description":102,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":69,"licenseFileUrl":103,"sourceHtmlUrl":104,"categories":105,"keywords":106,"publishedAt":74},"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":108,"name":109,"nameZh":6,"description":110,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":69,"licenseFileUrl":111,"sourceHtmlUrl":112,"categories":113,"keywords":114,"publishedAt":74},"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",[],[]]