[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M6MEP6P2854YWDM9J775DQDR":3,"skill-same:01M6MEP6P2854YWDM9J775DQDR":113},{"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":26,"publishedAt":49,"linkOnly":50,"markdownContent":51,"markdownBody":52,"frontMatter":53,"refName":78,"commitSha":79,"skillDirectory":80,"forksCount":81,"repositoryHtmlUrl":82,"repositoryHomepageUrl":83,"ownerHtmlUrl":84,"ownerBlogUrl":85,"ownerDescription":86,"updatedAt":87,"install":88,"resources":100},"01M6MEP6P2854YWDM9J775DQDR","craft-goal",null,"Draft or lint a bounded long-running goal prompt with a finish line and hard limits. Use when: asked to craft or lint a goal (a \u002Fgoal prompt); one change goes to Plan.","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\u002Fboshu2\u002Fagentops\u002Fskills\u002Fcraft-goal\u002FSKILL.md",[18,23],{"categoryNo":19,"categoryName":20,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000007","代码审查","SCENARIO","使用场景",{"categoryNo":24,"categoryName":25,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000023","Skill与智能体开发",[27,28,29,30,31,32,33,34,35,36,37,38,39,40,41,42,43,44,45,46,47,48],"craft goal","goal","craft","finish","when","limits","bounded","paste","canonical","line","judgment","human","design","lean","outcome","decision","plan","Safety","acceptance","create","change","safe","2026-11-10 10:12:30",false,"---\nname: craft-goal\ndescription: 'Draft or lint a bounded long-running goal prompt with a finish line and hard limits. Use when: asked to craft or lint a goal (a \u002Fgoal prompt); one change goes to Plan.'\npractices:\n- lean-startup\n- design-by-contract\nskill_api_version: 1\nhexagonal_role: supporting\nconsumes:\n- caller-outcome\n- goal-acceptance\nproduces:\n- outer-goal-prompt\n- goal-safety-report\ncontext_rel:\n- kind: supplier-to\n  with: plan\nuser-invocable: true\nmetadata:\n  tier: judgment\n  dependencies: []\n  capabilities: [\"goal_prompt_design\",\"goal_prompt_lint\"]\n  effects: []\n  canonical_status: canonical\n  disposition: keep_strategy\n  stability: stable\noutput_contract: 'human-readable SAFE_TO_CREATE, USE_PLAN, or UNSAFE_GOAL decision; copy-paste outer-goal prompt when safe; exact budgets, assumptions, and lint findings'\n---\n\n# Craft Goal\n\nCraft or lint a goal prompt: the contract a long-running goal runtime follows\nover a bead graph, picking each next experiment (one build bead) until a\nfrozen finish line is proven or a limit stops it. The number of experiments\nneed not be known in advance. A goal is safe when success is decidable, every\nexperiment is bounded, evidence keeps its provenance, and the authorization\nenvelope cannot silently renew itself.\n\n**Authority boundary.** The emitted prompt and safety report are inert\ncaller-owned text. Crafting creates no goal, starts no runtime, mutates no\nbead and confers no standing authorization. The prompt drives work only when\na caller pastes it into their own goal runtime, under their own authority and\nwithin the non-renewing envelope they set. Craft Goal reads tracker state when\npresent and needs no tracker installed to compile a prompt; the goal it writes\nruns on one.\n\nAsked to craft (\"craft a goal\", \"turn this into a goal\"), return the decision,\nthen the filled prompt and settings when safe. Asked to lint (\"lint\u002Freview\nthis goal\", \"is this safe\"), return the decision and findings, plus a rewrite\nwhen supplied facts permit one.\n\n## Admission: decide first\n\n**Fuzzy route is acceptable; fuzzy success is not.** Before goal creation the\ncaller must know the outcome, what evidence would prove it, non-goals,\nauthority, and the tracker the goal runs on (any with status, dependencies and\nnotes; BD is one); the exact experiment graph may still be unknown. Write each\nterminal criterion as a Given\u002FWhen\u002FThen with an observable result and name\neach domain term once; the caller can settle these with Interview first.\n\n- `USE_PLAN`: one shaped change with no verdict-driven follow-on; hand it to\n  [Plan](..\u002Fplan\u002FSKILL.md) or native execution (RPI only if the caller selects it).\n- `SAFE_TO_CREATE`: a terminal outcome that may need several related\n  experiments, with those decisions and the budgets below supplied. A shaped\n  goal with no beads may begin with 1 bounded discovery wave that creates the\n  root and initial experiment beads.\n- `UNSAFE_GOAL`: no falsifiable first question or terminal evidence can be\n  named (route that intent to idea or plan work), or the request is indefinite\n  monitoring or event reaction, which is an automation, not a terminal goal.\n\nGoals come in different sizes: size the wave and hard envelopes to the\noutcome, never to one universal budget. Do not invent acceptance, authority,\ngraph semantics, tracker or campaign size; return `UNSAFE_GOAL` with the\nmissing decisions. The caller owns revision and goal creation.\n\n## What a safe goal holds\n\n- **Closed outcome, adaptive route.** Freeze terminal acceptance. New facts may\n  change hypotheses and dependencies, never silently enlarge success.\n- **Bead graph as memory.** The tracker is durable memory, not a parallel goal\n  ledger: the root epic holds outer intent and each build bead one experiment,\n  so compaction cannot erase the record. A decision bead resolves through the\n  method Navigate names for it, not through a build.\n  [Navigate](..\u002Fnavigate\u002FSKILL.md) owns the walk each wave applies: graph\n  contract, ratchet, discovery classes and checkpoint.\n- **Proof stays outside the goal.** The goal consumes each verdict unchanged:\n  orchestration cannot author its own proof. Fresh validation is for\n  [Validate's costly cases](..\u002Fvalidate\u002FSKILL.md#when-a-fresh-judgment-is-worth-it)\n  only, since a review per bead multiplies cost across the graph.\n- **Two-level bounds.** Every experiment and every wave is bounded, and the\n  whole goal has monotonic hard ceilings, so a new wave cannot mint a new\n  campaign.\n\nThe template's experiment policy and breaker carry these into the runtime.\nThey prevent the **completion treadmill**, where discoveries keep becoming\nrequirements and activity continues without new information, and\n**first-red abandonment**, where one falsified hypothesis ends a viable\ncampaign.\n\n## Budgets and HOLD\n\nDeclare both envelopes with numbers before any work is selected, helper and\nvalidation costs included:\n\n- **Wave:** experiments, concurrency, wall time or tokens, live attempts, and\n  a checkpoint at its end.\n- **Goal:** total experiments, wall time or tokens, live attempts, compactions,\n  and any patch or surface limit for the whole campaign.\n\nName the native control that enforces each claimed hard limit and how the\nremaining allowance is observed. Objective text is an instruction, not\nenforcement: never report an unmeasured aggregate as a remaining balance, and\nnever claim the goal is paused from prose alone. No helper, retry, new\nsubject, compaction or wave renews the goal allowance.\n\nThe template's **Breaker and helper** section is the one list of HOLD triggers\n(implementation stops for causal review) and helper rules; fill its threshold\nand keep every line.\n\n## Lint rubric\n\n| Dimension | Passes when the prompt |\n|---|---|\n| outcome | names one larger caller-visible result. |\n| evidence | gives each terminal criterion as a Given\u002FWhen\u002FThen with its authoritative proof. |\n| domain terms | defines each domain term once and reuses only that word. |\n| admission | fits a goal: several related experiments, a falsifiable first question, a terminal finish. |\n| bead graph | names the tracker and the root epic or its bounded bootstrap rule, and ties each experiment to an unmet criterion or named blocking uncertainty. |\n| experiment boundary | makes one build bead one bounded experiment (native execution, or one RPI when the caller selects it; decision beads resolve as Navigate names), takes checks and CI as an ordinary bead's result, limits fresh validation to the costly cases and consumes verdicts unchanged. |\n| ratchet | counts progress only as evidence tied to an unmet criterion or blocking uncertainty, never activity, counts or digests. |\n| discovery | keeps all three classes (necessary-now, linked-follow-up, HOLD\u002Frescope) and never downgrades a necessary-now discovery to linked-follow-up. |\n| wave budget | sets numeric experiment, concurrency, time or token and live-attempt limits per wave, with a checkpoint. |\n| hard budget | sets numeric campaign totals that nothing resets, naming the enforcing control or the unmeasured aggregate. |\n| breaker | sets the numeric no-ratchet threshold and every HOLD trigger in the template's breaker. |\n| helper | sends a requested acceptance change or operator-reserved decision straight to `NEEDS_OPERATOR`, allows at most one helper per other HOLD incident, maps `UNSTUCK` and `ESCALATE`, and stops implementation on `NEEDS_OPERATOR`. |\n| scope | states non-goals and exact read, write, external and Git authority. |\n| self-hosting | is n\u002Fa unless the goal repairs the factory (agent system) it runs on; then its authority repairs from an ordinary shell or worktree and runs that factory only as a declared bounded canary. |\n| terminal reports | defines `ACHIEVED`, `NOT_ACHIEVED` and `NEEDS_OPERATOR`. |\n\n## Output\n\nFill [the copy-paste-only goal prompt](references\u002Fgoal-prompt.md): keep its\nheadings and terminal semantics and replace every angle-bracket field. Return,\nin order:\n\n1. A first line that starts with exactly one decision: `SAFE_TO_CREATE`,\n   `USE_PLAN` or `UNSAFE_GOAL`. `SAFE_TO_CREATE` judges prompt content; it does\n   not certify native enforcement or create a goal.\n2. For `UNSAFE_GOAL`, each missing decision; the caller can settle them with\n   Interview.\n3. When safe, the filled prompt; the settings: for each hard limit, the native\n   control the caller sets to enforce it (such as the goal runtime's own token\n   cap), or that it stays unmeasured; and the assumptions made, which cover\n   only reversible wording or sourced facts. A number, criterion or authority\n   the caller did not supply is a missing decision, never an assumption; label\n   any suggested value a proposal.\n4. Lint lines. In lint mode, one per rubric dimension: pass, n\u002Fa, or the\n   finding. In craft mode, only the rows the draft still fails; each is a\n   missing decision, so the decision cannot be `SAFE_TO_CREATE`.\n\n## Stop\n\nThis skill makes one pass, craft or lint, then returns. It never creates or\nruns a goal and never mutates beads. The goal it writes stops at its first\nterminal report: `ACHIEVED`, `NOT_ACHIEVED` or `NEEDS_OPERATOR`.\n","# Craft Goal\n\nCraft or lint a goal prompt: the contract a long-running goal runtime follows\nover a bead graph, picking each next experiment (one build bead) until a\nfrozen finish line is proven or a limit stops it. The number of experiments\nneed not be known in advance. A goal is safe when success is decidable, every\nexperiment is bounded, evidence keeps its provenance, and the authorization\nenvelope cannot silently renew itself.\n\n**Authority boundary.** The emitted prompt and safety report are inert\ncaller-owned text. Crafting creates no goal, starts no runtime, mutates no\nbead and confers no standing authorization. The prompt drives work only when\na caller pastes it into their own goal runtime, under their own authority and\nwithin the non-renewing envelope they set. Craft Goal reads tracker state when\npresent and needs no tracker installed to compile a prompt; the goal it writes\nruns on one.\n\nAsked to craft (\"craft a goal\", \"turn this into a goal\"), return the decision,\nthen the filled prompt and settings when safe. Asked to lint (\"lint\u002Freview\nthis goal\", \"is this safe\"), return the decision and findings, plus a rewrite\nwhen supplied facts permit one.\n\n## Admission: decide first\n\n**Fuzzy route is acceptable; fuzzy success is not.** Before goal creation the\ncaller must know the outcome, what evidence would prove it, non-goals,\nauthority, and the tracker the goal runs on (any with status, dependencies and\nnotes; BD is one); the exact experiment graph may still be unknown. Write each\nterminal criterion as a Given\u002FWhen\u002FThen with an observable result and name\neach domain term once; the caller can settle these with Interview first.\n\n- `USE_PLAN`: one shaped change with no verdict-driven follow-on; hand it to\n  [Plan](..\u002Fplan\u002FSKILL.md) or native execution (RPI only if the caller selects it).\n- `SAFE_TO_CREATE`: a terminal outcome that may need several related\n  experiments, with those decisions and the budgets below supplied. A shaped\n  goal with no beads may begin with 1 bounded discovery wave that creates the\n  root and initial experiment beads.\n- `UNSAFE_GOAL`: no falsifiable first question or terminal evidence can be\n  named (route that intent to idea or plan work), or the request is indefinite\n  monitoring or event reaction, which is an automation, not a terminal goal.\n\nGoals come in different sizes: size the wave and hard envelopes to the\noutcome, never to one universal budget. Do not invent acceptance, authority,\ngraph semantics, tracker or campaign size; return `UNSAFE_GOAL` with the\nmissing decisions. The caller owns revision and goal creation.\n\n## What a safe goal holds\n\n- **Closed outcome, adaptive route.** Freeze terminal acceptance. New facts may\n  change hypotheses and dependencies, never silently enlarge success.\n- **Bead graph as memory.** The tracker is durable memory, not a parallel goal\n  ledger: the root epic holds outer intent and each build bead one experiment,\n  so compaction cannot erase the record. A decision bead resolves through the\n  method Navigate names for it, not through a build.\n  [Navigate](..\u002Fnavigate\u002FSKILL.md) owns the walk each wave applies: graph\n  contract, ratchet, discovery classes and checkpoint.\n- **Proof stays outside the goal.** The goal consumes each verdict unchanged:\n  orchestration cannot author its own proof. Fresh validation is for\n  [Validate's costly cases](..\u002Fvalidate\u002FSKILL.md#when-a-fresh-judgment-is-worth-it)\n  only, since a review per bead multiplies cost across the graph.\n- **Two-level bounds.** Every experiment and every wave is bounded, and the\n  whole goal has monotonic hard ceilings, so a new wave cannot mint a new\n  campaign.\n\nThe template's experiment policy and breaker carry these into the runtime.\nThey prevent the **completion treadmill**, where discoveries keep becoming\nrequirements and activity continues without new information, and\n**first-red abandonment**, where one falsified hypothesis ends a viable\ncampaign.\n\n## Budgets and HOLD\n\nDeclare both envelopes with numbers before any work is selected, helper and\nvalidation costs included:\n\n- **Wave:** experiments, concurrency, wall time or tokens, live attempts, and\n  a checkpoint at its end.\n- **Goal:** total experiments, wall time or tokens, live attempts, compactions,\n  and any patch or surface limit for the whole campaign.\n\nName the native control that enforces each claimed hard limit and how the\nremaining allowance is observed. Objective text is an instruction, not\nenforcement: never report an unmeasured aggregate as a remaining balance, and\nnever claim the goal is paused from prose alone. No helper, retry, new\nsubject, compaction or wave renews the goal allowance.\n\nThe template's **Breaker and helper** section is the one list of HOLD triggers\n(implementation stops for causal review) and helper rules; fill its threshold\nand keep every line.\n\n## Lint rubric\n\n| Dimension | Passes when the prompt |\n|---|---|\n| outcome | names one larger caller-visible result. |\n| evidence | gives each terminal criterion as a Given\u002FWhen\u002FThen with its authoritative proof. |\n| domain terms | defines each domain term once and reuses only that word. |\n| admission | fits a goal: several related experiments, a falsifiable first question, a terminal finish. |\n| bead graph | names the tracker and the root epic or its bounded bootstrap rule, and ties each experiment to an unmet criterion or named blocking uncertainty. |\n| experiment boundary | makes one build bead one bounded experiment (native execution, or one RPI when the caller selects it; decision beads resolve as Navigate names), takes checks and CI as an ordinary bead's result, limits fresh validation to the costly cases and consumes verdicts unchanged. |\n| ratchet | counts progress only as evidence tied to an unmet criterion or blocking uncertainty, never activity, counts or digests. |\n| discovery | keeps all three classes (necessary-now, linked-follow-up, HOLD\u002Frescope) and never downgrades a necessary-now discovery to linked-follow-up. |\n| wave budget | sets numeric experiment, concurrency, time or token and live-attempt limits per wave, with a checkpoint. |\n| hard budget | sets numeric campaign totals that nothing resets, naming the enforcing control or the unmeasured aggregate. |\n| breaker | sets the numeric no-ratchet threshold and every HOLD trigger in the template's breaker. |\n| helper | sends a requested acceptance change or operator-reserved decision straight to `NEEDS_OPERATOR`, allows at most one helper per other HOLD incident, maps `UNSTUCK` and `ESCALATE`, and stops implementation on `NEEDS_OPERATOR`. |\n| scope | states non-goals and exact read, write, external and Git authority. |\n| self-hosting | is n\u002Fa unless the goal repairs the factory (agent system) it runs on; then its authority repairs from an ordinary shell or worktree and runs that factory only as a declared bounded canary. |\n| terminal reports | defines `ACHIEVED`, `NOT_ACHIEVED` and `NEEDS_OPERATOR`. |\n\n## Output\n\nFill [the copy-paste-only goal prompt](references\u002Fgoal-prompt.md): keep its\nheadings and terminal semantics and replace every angle-bracket field. Return,\nin order:\n\n1. A first line that starts with exactly one decision: `SAFE_TO_CREATE`,\n   `USE_PLAN` or `UNSAFE_GOAL`. `SAFE_TO_CREATE` judges prompt content; it does\n   not certify native enforcement or create a goal.\n2. For `UNSAFE_GOAL`, each missing decision; the caller can settle them with\n   Interview.\n3. When safe, the filled prompt; the settings: for each hard limit, the native\n   control the caller sets to enforce it (such as the goal runtime's own token\n   cap), or that it stays unmeasured; and the assumptions made, which cover\n   only reversible wording or sourced facts. A number, criterion or authority\n   the caller did not supply is a missing decision, never an assumption; label\n   any suggested value a proposal.\n4. Lint lines. In lint mode, one per rubric dimension: pass, n\u002Fa, or the\n   finding. In craft mode, only the rows the draft still fails; each is a\n   missing decision, so the decision cannot be `SAFE_TO_CREATE`.\n\n## Stop\n\nThis skill makes one pass, craft or lint, then returns. It never creates or\nruns a goal and never mutates beads. The goal it writes stops at its first\nterminal report: `ACHIEVED`, `NOT_ACHIEVED` or `NEEDS_OPERATOR`.\n",{"name":5,"consumes":54,"metadata":57,"produces":65,"practices":68,"context_rel":71,"description":7,"hexagonal_role":74,"user-invocable":75,"output_contract":76,"skill_api_version":77},[55,56],"caller-outcome","goal-acceptance",{"tier":37,"effects":58,"stability":59,"disposition":60,"capabilities":61,"dependencies":64,"canonical_status":35},[],"stable","keep_strategy",[62,63],"goal_prompt_design","goal_prompt_lint",[],[66,67],"outer-goal-prompt","goal-safety-report",[69,70],"lean-startup","design-by-contract",[72],{"kind":73,"with":43},"supplier-to","supporting",true,"human-readable SAFE_TO_CREATE, USE_PLAN, or UNSAFE_GOAL decision; copy-paste outer-goal prompt when safe; exact budgets, assumptions, and lint findings",1,"main","2b63f856ce19c2a797929cacabd9e0fc936812fa","plugins\u002Fboshu2\u002Fagentops\u002Fskills\u002Fcraft-goal",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":89,"prompt":99,"zipAvailable":75},[90,93,96],{"tool":91,"command":92},"npx","npx skills add hashgraph-online\u002Fawesome-codex-plugins --skill craft-goal",{"tool":94,"command":95},"bunx","bunx skills add hashgraph-online\u002Fawesome-codex-plugins --skill craft-goal",{"tool":97,"command":98},"pnpm","pnpm dlx skills add hashgraph-online\u002Fawesome-codex-plugins --skill craft-goal","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Fhashgraph-online\u002Fawesome-codex-plugins\u002Fblob\u002Fmain\u002Fplugins\u002Fboshu2\u002Fagentops\u002Fskills\u002Fcraft-goal\u002FSKILL.md",[101,107],{"path":102,"resourceType":103,"resourceTypeDesc":104,"sizeBytes":105,"sourceHtmlUrl":106},"references\u002Fgoal-prompt.md","REFERENCE","参考文档",4733,"https:\u002F\u002Fgithub.com\u002Fhashgraph-online\u002Fawesome-codex-plugins\u002Fblob\u002Fmain\u002Fplugins\u002Fboshu2\u002Fagentops\u002Fskills\u002Fcraft-goal\u002Freferences\u002Fgoal-prompt.md",{"path":108,"resourceType":109,"resourceTypeDesc":110,"sizeBytes":111,"sourceHtmlUrl":112},"scripts\u002Fvalidate.sh","SCRIPT","脚本",273,"https:\u002F\u002Fgithub.com\u002Fhashgraph-online\u002Fawesome-codex-plugins\u002Fblob\u002Fmain\u002Fplugins\u002Fboshu2\u002Fagentops\u002Fskills\u002Fcraft-goal\u002Fscripts\u002Fvalidate.sh",[114,124,132,140,148,156],{"skillNo":115,"name":116,"nameZh":6,"description":117,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":118,"licenseFileUrl":119,"sourceHtmlUrl":120,"categories":121,"keywords":122,"publishedAt":123},"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":125,"name":126,"nameZh":6,"description":127,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":118,"licenseFileUrl":128,"sourceHtmlUrl":129,"categories":130,"keywords":131,"publishedAt":123},"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":133,"name":134,"nameZh":6,"description":135,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":118,"licenseFileUrl":136,"sourceHtmlUrl":137,"categories":138,"keywords":139,"publishedAt":123},"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":141,"name":142,"nameZh":6,"description":143,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":118,"licenseFileUrl":144,"sourceHtmlUrl":145,"categories":146,"keywords":147,"publishedAt":123},"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":149,"name":150,"nameZh":6,"description":151,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":118,"licenseFileUrl":152,"sourceHtmlUrl":153,"categories":154,"keywords":155,"publishedAt":123},"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":157,"name":158,"nameZh":6,"description":159,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":118,"licenseFileUrl":160,"sourceHtmlUrl":161,"categories":162,"keywords":163,"publishedAt":123},"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",[],[]]