[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M6MES18P70ERD0GG4JRS7H8C":3,"skill-same:01M6MES18P70ERD0GG4JRS7H8C":102},{"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":40,"linkOnly":41,"markdownContent":42,"markdownBody":43,"frontMatter":44,"refName":69,"commitSha":70,"skillDirectory":71,"forksCount":72,"repositoryHtmlUrl":73,"repositoryHomepageUrl":74,"ownerHtmlUrl":75,"ownerBlogUrl":76,"ownerDescription":77,"updatedAt":78,"install":79,"resources":91},"01M6MES18P70ERD0GG4JRS7H8C","rpi",null,"Drive one accepted change through implementation and checks to done, with one fresh review only where a mistake is costly. Use when: asked to run or orchestrate work through RPI.","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\u002Frpi\u002FSKILL.md",[],[5,19,20,21,22,23,24,25,26,27,28,29,30,31,32,33,34,35,36,37,38,39],"change","result","when","machine","domain","evidence","canonical","outcome","run","human","customer","plan","work","fresh","review","done","only","design","Meta","orchestrate","validator","2026-11-10 10:12:30",false,"---\nname: rpi\ndescription: 'Drive one accepted change through implementation and checks to done, with one fresh review only where a mistake is costly. Use when: asked to run or orchestrate work through RPI.'\npractices:\n- design-by-contract\nhexagonal_role: domain\nconsumes:\n- plan\n- implement\n- validate\nproduces: []\ncontext_rel:\n- kind: customer-of\n  with: plan\n- kind: customer-of\n  with: implement\n- kind: customer-of\n  with: validate\nskill_api_version: 1\nuser-invocable: true\nmetadata:\n  graph_root: true\n  tier: meta\n  dependencies: [plan, implement, validate]\n  capabilities: [own_authorized_outcome, report]\n  effects: [modify_authorized_subject, dispatch_conditional_validator]\n  canonical_status: canonical\n  disposition: keep_strategy\noutput_contract: 'concise human-readable closeout; no machine artifact'\n---\n\n# RPI\n\nOwn the authorized outcome through finish. RPI (research, plan, implement) is\none native pass, not fixed phases: use the native coding agent and shell.\nBD or the caller's tracker owns work and handoffs; Git owns content and\ndelivery. AgentOps supplies a small charter and one fresh judgment where a\nmistake is costly, not a scheduler.\n\n## Operating charter\n\n1. Use the existing accepted outcome, scope and real bounds. A clear change\n   needs no Plan, Recall or Learn worksheet. Resolve uncertainty only when it\n   could change the implementation or acceptance decision.\n2. Take the smallest acceptance-advancing action. [Plan](..\u002Fplan\u002FSKILL.md)\n   runs only when intent is missing, an uncertainty is consequential or\n   evidence disproves the approach. Once an implementer\n   can act and a validator can judge, implement; do not keep improving the plan.\n   Approach revisions preserve acceptance and authorized scope.\n   Acceptance changes need caller authority.\n3. [Implement](..\u002Fimplement\u002FSKILL.md) and repair ordinary known defects directly.\n   A known test failure needs a fix and a discriminating check, not another\n   planning phase, council or helper.\n4. Use focused checks during edits and complete required integration checks\n   before finishing. Reuse a check result only while its inputs are unchanged;\n   rerun affected checks after changes. Reserve capacity for integration and\n   repair. Keep a subject unchanged while it is being judged.\n5. Spend validation where a mistake is costly. For an ordinary change the\n   checks and CI are the gate: finish. Obtain [Validate](..\u002Fvalidate\u002FSKILL.md)\n   from one fresh author-distinct context only when the caller asks, when a\n   mistake cannot be cheaply undone after it lands (a published release or\n   instructions users will follow, a security boundary, destroying data or\n   tracker state, deleting a check that protects the product), or when no\n   deterministic check covers the changed behavior. Use the author's model\n   family unless the caller selects additional legs; explicitly required\n   reviewers remain required.\n6. One round. Give the validator the accepted criteria, the exact subject and\n   one question written before it starts, never the author's confidence or\n   desired verdict; it does not re-run the checks. Repair what fails the\n   accepted behavior or would mislead a user, break install or the CLI, or\n   remove protection for the product; treat the rest as optional notes. Confirm\n   each repair with a check and finish. A repair does not start another\n   review, and `NOT_PROVEN` is reported with its gaps, not chased. Keep review\n   cost a fraction of the cost of the work; when it approaches that cost, stop\n   and report what is unchecked.\n7. Stop at completed acceptance, cancellation, refusal, a spent real bound, a\n   pending caller decision or an unresolved causal stall after the help below.\n   A choice the accepted outcome depends on that lies outside existing\n   authority (changed acceptance, wider scope, an irreversible step it does not\n   cover) is the caller's decision, not a stall, so no helper applies. Finish\n   the independent authorized work, then stop and return the choice instead of\n   waiting on it, handed over in full: what raised it, what you found, the\n   options with their tradeoffs and your recommendation. A count or a link is\n   not a handover, and the result is never `done` while a choice is open.\n   Adjacent improvements are not permission to expand the goal. Report them\n   briefly only when useful; do not turn them into another work batch.\n\n## Delegation and handoffs\n\nWhen delegation is authorized and useful, select the runtime's task-only\ndispatch option for independent work: a short prompt in a full-history fork\nstill carries the full history, and prompt wording proves neither isolation nor\na smaller inherited context. Supply accepted intent and scope, the exact\nsubject, relevant evidence, remaining bounds, the result's consumer and check\nownership; resume an author for direct repair when useful. At completion,\nverify the expected subject and required results; a quiet or partial status is\nnot success. Integrate as Implement's\n[delegated work](..\u002Fimplement\u002Freferences\u002Fdelegated-work.md) describes, carrying each worker's `not_as_briefed` and `gaps` lines into\nthe closeout below.\n\n## Causal stall and bounds\n\nName a stall by what you observed, never by a count:\n\n- Unknown cause: a check fails and neither its output nor the diff points to a\n  change or assumption you can name.\n- Recurrence: a check that passed after a repair fails again for the same cause.\n- No progress: the failing check's output and the diff are unchanged since the\n  previous attempt, or a delegated worker's last observed activity has not\n  changed since you last looked.\n- Wrong objective: a caller correction, or a check of the accepted example,\n  shows the work aims at something acceptance does not ask for.\n\nAny of the four admits at most one bounded fresh helper for that incident\nwithin authority and bounds; if it stays unresolved, the stalled Result names\nits observed fact.\nGive it the failed assumption, evidence and one discriminating question. Resume\nonly with a different testable approach; an unhelpful answer ends the attempt.\nDo not chain helpers or rename the incident. Known failures get direct repair.\nCancellation, refusal and spent hard time\u002Fcost\u002Fquota skip help.\n\nRespect actual caller\u002Fnative limits, including explicit repair-round bounds.\nRetries, compaction, helpers and new subjects never renew them; retry count\nalone is not a spent budget, and prompt text proves no native enforcement. If\ninterruption threatens evidence, preserve accepted intent, exact subject, check\nresults, unresolved cause, bounds and helper use in the native handoff.\n[Outer-goal guidance](references\u002Fouter-goal.md) remains optional.\n\n## Evidence and boundaries\n\nWhen a validator is used, bind accepted intent, complete changed paths, the\nexact subject and its check results using\n[Validate's Subject rules](..\u002Fvalidate\u002FSKILL.md#subject), including its status\nlisting and file hashes for uncommitted work.\nWhere the repository records AgentOps evidence bindings, run the orphaned-evidence\nscan [Implement](..\u002Fimplement\u002FSKILL.md#workflow) step 6 details; without `ao`,\nlist the scan under Not checked. Requested proof goes to protected storage outside\nGit that the caller selects; preserve legacy `.agents\u002F` evidence. [Validate](..\u002Fvalidate\u002FSKILL.md#rules-that-decide-the-verdict)'s\ndecision order sets a requested binding verdict, which the author cannot issue.\n\n[Memory](..\u002Fmemory\u002FSKILL.md), specialists and runtime adapters are on demand;\nno-match and no-change are valid. Read [boundaries](references\u002Fboundaries.md)\nwhen authority, scope, evidence or delivery is at issue. Do not invent a\nruntime, hidden machine artifact or workflow to finish an ordinary change.\n\n## Closeout\n\nReport in this shape. Plans, activity, reviews and saved pages earn no\ncapability credit, and an unchecked item is reported, not a reason to keep\nvalidating. The report is the result; create no machine artifact for it. A\npersisted verdict, when a caller or declared consumer requires one, is\nValidate's `verdict.v2`.\n\n```text\nResult:         done | stopped: \u003Ccancelled | refused | needs decision: \u003Cchoice> | bound spent | stalled: \u003Cunknown cause | recurrence | no progress | wrong objective> - \u003Cobserved fact>> | NOT_PLANNED | NOT_BUILT\nSubject:        \u003Ccommit, branch or diff identity>\nAcceptance:     \u003Ccriterion> -> \u003Cevidence: check, receipt or ref>, one line each\nChecked:        \u003Cchecks run on the final subject, with results>\nNot checked:    \u003Cwhat was not run or not covered, and why> | none\nJudgment:       none (checks and CI gate an ordinary change) | \u003Cvalidator context id>: PASS | FAIL | NOT_PROVEN\nNot as briefed: \u003Csteps refused, held, worked around or unverified, and departures from the literal ask, one line with its reason each> | none\nLimits:         \u003Cgaps: material missing evidence and known failures; each open decision in full; adjacent work noticed but not done> | none\n```\n\nA departure is a call made within authority that the caller would want to\nknow: building differently than asked, declining or disputing a finding, or\nfollowing a mid-run steer. Routine fixes stay out; with no such call, add none.\n\n`NOT_PLANNED` (stopped before an actionable slice existed) and `NOT_BUILT`\n(stopped before a candidate change existed) describe progress, not semantic\nverdicts.\n","# RPI\n\nOwn the authorized outcome through finish. RPI (research, plan, implement) is\none native pass, not fixed phases: use the native coding agent and shell.\nBD or the caller's tracker owns work and handoffs; Git owns content and\ndelivery. AgentOps supplies a small charter and one fresh judgment where a\nmistake is costly, not a scheduler.\n\n## Operating charter\n\n1. Use the existing accepted outcome, scope and real bounds. A clear change\n   needs no Plan, Recall or Learn worksheet. Resolve uncertainty only when it\n   could change the implementation or acceptance decision.\n2. Take the smallest acceptance-advancing action. [Plan](..\u002Fplan\u002FSKILL.md)\n   runs only when intent is missing, an uncertainty is consequential or\n   evidence disproves the approach. Once an implementer\n   can act and a validator can judge, implement; do not keep improving the plan.\n   Approach revisions preserve acceptance and authorized scope.\n   Acceptance changes need caller authority.\n3. [Implement](..\u002Fimplement\u002FSKILL.md) and repair ordinary known defects directly.\n   A known test failure needs a fix and a discriminating check, not another\n   planning phase, council or helper.\n4. Use focused checks during edits and complete required integration checks\n   before finishing. Reuse a check result only while its inputs are unchanged;\n   rerun affected checks after changes. Reserve capacity for integration and\n   repair. Keep a subject unchanged while it is being judged.\n5. Spend validation where a mistake is costly. For an ordinary change the\n   checks and CI are the gate: finish. Obtain [Validate](..\u002Fvalidate\u002FSKILL.md)\n   from one fresh author-distinct context only when the caller asks, when a\n   mistake cannot be cheaply undone after it lands (a published release or\n   instructions users will follow, a security boundary, destroying data or\n   tracker state, deleting a check that protects the product), or when no\n   deterministic check covers the changed behavior. Use the author's model\n   family unless the caller selects additional legs; explicitly required\n   reviewers remain required.\n6. One round. Give the validator the accepted criteria, the exact subject and\n   one question written before it starts, never the author's confidence or\n   desired verdict; it does not re-run the checks. Repair what fails the\n   accepted behavior or would mislead a user, break install or the CLI, or\n   remove protection for the product; treat the rest as optional notes. Confirm\n   each repair with a check and finish. A repair does not start another\n   review, and `NOT_PROVEN` is reported with its gaps, not chased. Keep review\n   cost a fraction of the cost of the work; when it approaches that cost, stop\n   and report what is unchecked.\n7. Stop at completed acceptance, cancellation, refusal, a spent real bound, a\n   pending caller decision or an unresolved causal stall after the help below.\n   A choice the accepted outcome depends on that lies outside existing\n   authority (changed acceptance, wider scope, an irreversible step it does not\n   cover) is the caller's decision, not a stall, so no helper applies. Finish\n   the independent authorized work, then stop and return the choice instead of\n   waiting on it, handed over in full: what raised it, what you found, the\n   options with their tradeoffs and your recommendation. A count or a link is\n   not a handover, and the result is never `done` while a choice is open.\n   Adjacent improvements are not permission to expand the goal. Report them\n   briefly only when useful; do not turn them into another work batch.\n\n## Delegation and handoffs\n\nWhen delegation is authorized and useful, select the runtime's task-only\ndispatch option for independent work: a short prompt in a full-history fork\nstill carries the full history, and prompt wording proves neither isolation nor\na smaller inherited context. Supply accepted intent and scope, the exact\nsubject, relevant evidence, remaining bounds, the result's consumer and check\nownership; resume an author for direct repair when useful. At completion,\nverify the expected subject and required results; a quiet or partial status is\nnot success. Integrate as Implement's\n[delegated work](..\u002Fimplement\u002Freferences\u002Fdelegated-work.md) describes, carrying each worker's `not_as_briefed` and `gaps` lines into\nthe closeout below.\n\n## Causal stall and bounds\n\nName a stall by what you observed, never by a count:\n\n- Unknown cause: a check fails and neither its output nor the diff points to a\n  change or assumption you can name.\n- Recurrence: a check that passed after a repair fails again for the same cause.\n- No progress: the failing check's output and the diff are unchanged since the\n  previous attempt, or a delegated worker's last observed activity has not\n  changed since you last looked.\n- Wrong objective: a caller correction, or a check of the accepted example,\n  shows the work aims at something acceptance does not ask for.\n\nAny of the four admits at most one bounded fresh helper for that incident\nwithin authority and bounds; if it stays unresolved, the stalled Result names\nits observed fact.\nGive it the failed assumption, evidence and one discriminating question. Resume\nonly with a different testable approach; an unhelpful answer ends the attempt.\nDo not chain helpers or rename the incident. Known failures get direct repair.\nCancellation, refusal and spent hard time\u002Fcost\u002Fquota skip help.\n\nRespect actual caller\u002Fnative limits, including explicit repair-round bounds.\nRetries, compaction, helpers and new subjects never renew them; retry count\nalone is not a spent budget, and prompt text proves no native enforcement. If\ninterruption threatens evidence, preserve accepted intent, exact subject, check\nresults, unresolved cause, bounds and helper use in the native handoff.\n[Outer-goal guidance](references\u002Fouter-goal.md) remains optional.\n\n## Evidence and boundaries\n\nWhen a validator is used, bind accepted intent, complete changed paths, the\nexact subject and its check results using\n[Validate's Subject rules](..\u002Fvalidate\u002FSKILL.md#subject), including its status\nlisting and file hashes for uncommitted work.\nWhere the repository records AgentOps evidence bindings, run the orphaned-evidence\nscan [Implement](..\u002Fimplement\u002FSKILL.md#workflow) step 6 details; without `ao`,\nlist the scan under Not checked. Requested proof goes to protected storage outside\nGit that the caller selects; preserve legacy `.agents\u002F` evidence. [Validate](..\u002Fvalidate\u002FSKILL.md#rules-that-decide-the-verdict)'s\ndecision order sets a requested binding verdict, which the author cannot issue.\n\n[Memory](..\u002Fmemory\u002FSKILL.md), specialists and runtime adapters are on demand;\nno-match and no-change are valid. Read [boundaries](references\u002Fboundaries.md)\nwhen authority, scope, evidence or delivery is at issue. Do not invent a\nruntime, hidden machine artifact or workflow to finish an ordinary change.\n\n## Closeout\n\nReport in this shape. Plans, activity, reviews and saved pages earn no\ncapability credit, and an unchecked item is reported, not a reason to keep\nvalidating. The report is the result; create no machine artifact for it. A\npersisted verdict, when a caller or declared consumer requires one, is\nValidate's `verdict.v2`.\n\n```text\nResult:         done | stopped: \u003Ccancelled | refused | needs decision: \u003Cchoice> | bound spent | stalled: \u003Cunknown cause | recurrence | no progress | wrong objective> - \u003Cobserved fact>> | NOT_PLANNED | NOT_BUILT\nSubject:        \u003Ccommit, branch or diff identity>\nAcceptance:     \u003Ccriterion> -> \u003Cevidence: check, receipt or ref>, one line each\nChecked:        \u003Cchecks run on the final subject, with results>\nNot checked:    \u003Cwhat was not run or not covered, and why> | none\nJudgment:       none (checks and CI gate an ordinary change) | \u003Cvalidator context id>: PASS | FAIL | NOT_PROVEN\nNot as briefed: \u003Csteps refused, held, worked around or unverified, and departures from the literal ask, one line with its reason each> | none\nLimits:         \u003Cgaps: material missing evidence and known failures; each open decision in full; adjacent work noticed but not done> | none\n```\n\nA departure is a call made within authority that the caller would want to\nknow: building differently than asked, declining or disputing a finding, or\nfollowing a mid-run steer. Routine fixes stay out; with no such call, add none.\n\n`NOT_PLANNED` (stopped before an actionable slice existed) and `NOT_BUILT`\n(stopped before a candidate change existed) describe progress, not semantic\nverdicts.\n",{"name":5,"consumes":45,"metadata":48,"produces":59,"practices":60,"context_rel":62,"description":7,"hexagonal_role":23,"user-invocable":53,"output_contract":67,"skill_api_version":68},[30,46,47],"implement","validate",{"tier":49,"effects":50,"graph_root":53,"disposition":54,"capabilities":55,"dependencies":58,"canonical_status":25},"meta",[51,52],"modify_authorized_subject","dispatch_conditional_validator",true,"keep_strategy",[56,57],"own_authorized_outcome","report",[30,46,47],[],[61],"design-by-contract",[63,65,66],{"kind":64,"with":30},"customer-of",{"kind":64,"with":46},{"kind":64,"with":47},"concise human-readable closeout; no machine artifact",1,"main","347aedf8480cd92b21f761e97b7343a45898f5fa","plugins\u002Fboshu2\u002Fagentops\u002Fskills\u002Frpi",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":80,"prompt":90,"zipAvailable":53},[81,84,87],{"tool":82,"command":83},"npx","npx skills add hashgraph-online\u002Fawesome-codex-plugins --skill rpi",{"tool":85,"command":86},"bunx","bunx skills add hashgraph-online\u002Fawesome-codex-plugins --skill rpi",{"tool":88,"command":89},"pnpm","pnpm dlx skills add hashgraph-online\u002Fawesome-codex-plugins --skill rpi","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Fhashgraph-online\u002Fawesome-codex-plugins\u002Fblob\u002Fmain\u002Fplugins\u002Fboshu2\u002Fagentops\u002Fskills\u002Frpi\u002FSKILL.md",[92,98],{"path":93,"resourceType":94,"resourceTypeDesc":95,"sizeBytes":96,"sourceHtmlUrl":97},"references\u002Fboundaries.md","REFERENCE","参考文档",4039,"https:\u002F\u002Fgithub.com\u002Fhashgraph-online\u002Fawesome-codex-plugins\u002Fblob\u002Fmain\u002Fplugins\u002Fboshu2\u002Fagentops\u002Fskills\u002Frpi\u002Freferences\u002Fboundaries.md",{"path":99,"resourceType":94,"resourceTypeDesc":95,"sizeBytes":100,"sourceHtmlUrl":101},"references\u002Fouter-goal.md",1562,"https:\u002F\u002Fgithub.com\u002Fhashgraph-online\u002Fawesome-codex-plugins\u002Fblob\u002Fmain\u002Fplugins\u002Fboshu2\u002Fagentops\u002Fskills\u002Frpi\u002Freferences\u002Fouter-goal.md",[103,113,121,129,137,145],{"skillNo":104,"name":105,"nameZh":6,"description":106,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":107,"licenseFileUrl":108,"sourceHtmlUrl":109,"categories":110,"keywords":111,"publishedAt":112},"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":114,"name":115,"nameZh":6,"description":116,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":107,"licenseFileUrl":117,"sourceHtmlUrl":118,"categories":119,"keywords":120,"publishedAt":112},"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":122,"name":123,"nameZh":6,"description":124,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":107,"licenseFileUrl":125,"sourceHtmlUrl":126,"categories":127,"keywords":128,"publishedAt":112},"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":130,"name":131,"nameZh":6,"description":132,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":107,"licenseFileUrl":133,"sourceHtmlUrl":134,"categories":135,"keywords":136,"publishedAt":112},"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":138,"name":139,"nameZh":6,"description":140,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":107,"licenseFileUrl":141,"sourceHtmlUrl":142,"categories":143,"keywords":144,"publishedAt":112},"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":146,"name":147,"nameZh":6,"description":148,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":107,"licenseFileUrl":149,"sourceHtmlUrl":150,"categories":151,"keywords":152,"publishedAt":112},"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",[],[]]