[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M6MER7GETZKQJE362TVJBDE1":3,"skill-same:01M6MER7GETZKQJE362TVJBDE1":112},{"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":39,"linkOnly":40,"markdownContent":41,"markdownBody":42,"frontMatter":43,"refName":66,"commitSha":67,"skillDirectory":68,"forksCount":69,"repositoryHtmlUrl":70,"repositoryHomepageUrl":71,"ownerHtmlUrl":72,"ownerBlogUrl":73,"ownerDescription":74,"updatedAt":75,"install":76,"resources":88},"01M6MER7GETZKQJE362TVJBDE1","premortem",null,"Find how a rollout plan could fail before committing to it. Use when: asked what could go wrong or to poke holes in a 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\u002Fpremortem\u002FSKILL.md",[],[5,19,20,21,22,23,24,25,26,27,28,29,30,31,32,33,34,35,36,37,38],"go","when","v1","use","strategy","schema","contract","true","domain","adr","canonical","judgment","write","how","plan","poke","review","rollout","design","challenge","2026-11-10 10:12:30",false,"---\nname: premortem\ndescription: 'Find how a rollout plan could fail before committing to it. Use when: asked what could go wrong or to poke holes in a plan.'\npractices: [design-by-contract, adr]\nhexagonal_role: domain\nconsumes: []\nproduces: [premortem-plan-review.v1]\ncontext_rel:\n- kind: supplier-to\n  with: plan\nskill_api_version: 1\nuser-invocable: true\nmetadata:\n  capabilities: [challenge_plan]\n  effects: [write_advisory_plan_review]\n  canonical_status: canonical\n  disposition: keep_strategy\n  graph_root: true\n  tier: judgment\n  dependencies: []\n  triggers: [\"what could go wrong\", \"poke holes\", \"challenge this plan\"]\noutput_contract: schemas\u002Fpremortem-plan-review.v1.schema.json\n---\n\n# Premortem\n\nBefore implementation, a context that did not write the plan runs three checks\nin order: who verifies each costly unit, which steps are one-way doors, and a\nconstructed defeat for each premise the plan takes for granted. Report findings\nin the same order: a finding from the first or second check outranks any single\ntechnical risk the third check constructs.\nPremortem is an optional plan-challenge strategy, outside the required RPI\nsequence, and does not authorize readiness.\n\n| Use instead | When |\n|---|---|\n| [Review](..\u002Freview\u002FSKILL.md) | general advice on a plan or change |\n| [Validate](..\u002Fvalidate\u002FSKILL.md) | acceptance of a finished change |\n| [Council](..\u002Fcouncil\u002FSKILL.md) | several independent views |\n\n[Plan's shared challenge method](..\u002Fplan\u002Freferences\u002Fchallenge.md) owns optional\nexchange, dispatch and stopping rules; when no fresh context can be started,\nstep 2's labelled self-judged fallback replaces its no-stand-in rule here.\n\n## The first check: who verifies, and are they fresh?\n\nTest the plan's evidence shape before any technical risk: for every unit of\nwork, who verifies it? For an ordinary unit the author's checks and CI are the\ngate, and that is not a finding\n([Validate](..\u002Fvalidate\u002FSKILL.md#when-a-fresh-judgment-is-worth-it)). A unit is\ncostly when it meets a condition on Validate's list (a published release or\nuser instructions, a security boundary, destroyed data or tracker state, a\ndeleted protective check, behavior no deterministic check covers) or when a\nlater one-way step depends on it. The finding is a costly unit with no fresh\nauthor-distinct read planned, whoever wrote its checks, as in a closure step\n\"the implementer runs its own tests and closes\" on a unit that guards\nauthentication. Tests are enough for an ordinary unit; they do not replace the\nread a costly unit owes. Report the shape once, listing its units.\n\n## The second check: which steps are one-way doors?\n\nWalk the steps and mark each two-way (the plan can back out of it) or one-way\n(it cannot). For every one-way step name the exact undo cost, the point of no\nreturn, and who holds the handle when it is crossed: the caller, or an agent\ndeciding inside a batch. A two-way failure costs a retry; a one-way failure\ncosts the thing itself. Watch for nineteen reversible steps followed by an\nirreversible one, where the reflex trained by the first nineteen answers the\ntwentieth.\n\nThe named failure mode is **reversibility asserted, not traced**: a rollback\nsection that says \"fully reversible\" while one step revokes a credential,\nforce-pushes or publishes. A material irreversible action outside existing\ncaller authority is a finding; [Plan's Who decides](..\u002Fplan\u002FSKILL.md#who-decides)\nowns undo cost and authorization, and prior authorization stays valid, so do\nnot demand repeated approval at the crossing or call every uncertain detail\nirreversible. Stop condition: every step carries a mark, and every one-way mark\ncarries its undo cost.\n\n## The third check: construct the failure\n\nDraw candidate failures from what the plan takes for granted, not from a\ngeneric risk list. Typical premises: a tool or service behaving as the plan\ndescribes, the work holding at volumes far above or below what it expects where\nvolume matters, steps finishing in the stated order and time, and acceptance,\nedge behavior, scope and dependencies being complete. Aim first at the decision\nother steps rest on, and at any one-way step whose deciding premise is inferred\nrather than cited. Name the fact that would show each premise false; when it\ncan be looked up now, look it up instead of reporting the premise as a risk.\n\nFor every candidate failure, attempt a concrete defeat: write the input,\ncommand sequence or repository state that would make the plan fail, and run or\ncite the check that shows whether the plan survives it. When execution is not\navailable, the constructed input or sequence plus a cited fact (file and line,\ndocumented behavior, an observed output) counts as the attempt. A failure you\ncould not construct is reported as attempted-and-blocked with the obstacle\nnamed, which is itself evidence for the plan. The named failure mode is\narmchair pessimism: imagined risks with no construction, which reads as\ndiligence while testing nothing. A finding with neither a construction nor a\nblocking fact is deleted, not softened.\n\n## Workflow\n\n1. Resolve the existing intent source and inspect its acceptance, non-goals,\n   evidence requirements and declared write scope.\n2. Judge from a context that did not write the plan, following the shared\n   challenge method for identity, model selection, authorization and bounds. A\n   plan the caller wrote can be judged here, with the caller as author. If this\n   context wrote the plan and no fresh context can be started, run the checks\n   anyway, state that the independence leg is missing, and return inline\n   findings; never describe them as independent.\n3. Run the three checks against cited repository facts. For integration or\n   extension plans where anchoring on the working design is the risk, add the\n   [derivation-diff challenge](references\u002Fderivation-diff.md).\n4. Return one complete, bounded set of concrete findings with checked and\n   not-checked scope, then stop: the caller decides whether to revise the plan\n   or invoke RPI.\n\n## It's working if\n\nObservable in the output:\n\n- each unit names its verifier, and costly units with no fresh author-distinct\n  read are one finding listing those units; an ordinary unit graded by its\n  author's checks and CI is no finding;\n- each step is marked, and each one-way mark names its undo cost and point of\n  no return;\n- each finding cites a defeat attempt or the fact that blocked it;\n- the set is bounded: a review that flags every step has reported nothing.\n\n## Boundary\n\nEmit advisory findings, no verdict of any version, readiness, admission or\npermission. Do not implement, validate the candidate, retry, repair, schedule,\nclaim, change acceptance, operate Git, close work, release or deliver. Council\nor [Idea Genie](..\u002Fidea-genie\u002FSKILL.md#duel-mode) duel mode may be\ncaller-supplied evidence, but Premortem requires neither and cannot turn\nconsensus into approval. Any plan edit creates a new subject for a later\ncaller-initiated Premortem.\n\n## Output\n\nReturn findings inline by default:\n\n```text\nFindings (in check order, then most consequential first within each check)\n1. \u003Cstep> - \u003Chow it fails> - \u003Cconstruction, or the fact that blocked it> - \u003Cconsequence>\nVerifiers: \u003Cunit>: \u003Cwho verifies>\nSteps: \u003Cstep>: two-way | one-way - \u003Cundo cost> - \u003Cpoint of no return> - \u003Cwho holds the handle>\nChecked: \u003Cwhat was examined>. Not checked: \u003Cwhat was not>.\nIndependence: \u003Cjudge context, distinct from author> or \"missing: \u003Creason>\"\n```\n\nWhen the caller requests a durable review, follow\n[durable review](references\u002Fdurable-review.md) to return and check\n`premortem-plan-review.v1`. An empty finding set means only that this\noptional challenge found no concrete defect; it is never a lifecycle gate.\n","# Premortem\n\nBefore implementation, a context that did not write the plan runs three checks\nin order: who verifies each costly unit, which steps are one-way doors, and a\nconstructed defeat for each premise the plan takes for granted. Report findings\nin the same order: a finding from the first or second check outranks any single\ntechnical risk the third check constructs.\nPremortem is an optional plan-challenge strategy, outside the required RPI\nsequence, and does not authorize readiness.\n\n| Use instead | When |\n|---|---|\n| [Review](..\u002Freview\u002FSKILL.md) | general advice on a plan or change |\n| [Validate](..\u002Fvalidate\u002FSKILL.md) | acceptance of a finished change |\n| [Council](..\u002Fcouncil\u002FSKILL.md) | several independent views |\n\n[Plan's shared challenge method](..\u002Fplan\u002Freferences\u002Fchallenge.md) owns optional\nexchange, dispatch and stopping rules; when no fresh context can be started,\nstep 2's labelled self-judged fallback replaces its no-stand-in rule here.\n\n## The first check: who verifies, and are they fresh?\n\nTest the plan's evidence shape before any technical risk: for every unit of\nwork, who verifies it? For an ordinary unit the author's checks and CI are the\ngate, and that is not a finding\n([Validate](..\u002Fvalidate\u002FSKILL.md#when-a-fresh-judgment-is-worth-it)). A unit is\ncostly when it meets a condition on Validate's list (a published release or\nuser instructions, a security boundary, destroyed data or tracker state, a\ndeleted protective check, behavior no deterministic check covers) or when a\nlater one-way step depends on it. The finding is a costly unit with no fresh\nauthor-distinct read planned, whoever wrote its checks, as in a closure step\n\"the implementer runs its own tests and closes\" on a unit that guards\nauthentication. Tests are enough for an ordinary unit; they do not replace the\nread a costly unit owes. Report the shape once, listing its units.\n\n## The second check: which steps are one-way doors?\n\nWalk the steps and mark each two-way (the plan can back out of it) or one-way\n(it cannot). For every one-way step name the exact undo cost, the point of no\nreturn, and who holds the handle when it is crossed: the caller, or an agent\ndeciding inside a batch. A two-way failure costs a retry; a one-way failure\ncosts the thing itself. Watch for nineteen reversible steps followed by an\nirreversible one, where the reflex trained by the first nineteen answers the\ntwentieth.\n\nThe named failure mode is **reversibility asserted, not traced**: a rollback\nsection that says \"fully reversible\" while one step revokes a credential,\nforce-pushes or publishes. A material irreversible action outside existing\ncaller authority is a finding; [Plan's Who decides](..\u002Fplan\u002FSKILL.md#who-decides)\nowns undo cost and authorization, and prior authorization stays valid, so do\nnot demand repeated approval at the crossing or call every uncertain detail\nirreversible. Stop condition: every step carries a mark, and every one-way mark\ncarries its undo cost.\n\n## The third check: construct the failure\n\nDraw candidate failures from what the plan takes for granted, not from a\ngeneric risk list. Typical premises: a tool or service behaving as the plan\ndescribes, the work holding at volumes far above or below what it expects where\nvolume matters, steps finishing in the stated order and time, and acceptance,\nedge behavior, scope and dependencies being complete. Aim first at the decision\nother steps rest on, and at any one-way step whose deciding premise is inferred\nrather than cited. Name the fact that would show each premise false; when it\ncan be looked up now, look it up instead of reporting the premise as a risk.\n\nFor every candidate failure, attempt a concrete defeat: write the input,\ncommand sequence or repository state that would make the plan fail, and run or\ncite the check that shows whether the plan survives it. When execution is not\navailable, the constructed input or sequence plus a cited fact (file and line,\ndocumented behavior, an observed output) counts as the attempt. A failure you\ncould not construct is reported as attempted-and-blocked with the obstacle\nnamed, which is itself evidence for the plan. The named failure mode is\narmchair pessimism: imagined risks with no construction, which reads as\ndiligence while testing nothing. A finding with neither a construction nor a\nblocking fact is deleted, not softened.\n\n## Workflow\n\n1. Resolve the existing intent source and inspect its acceptance, non-goals,\n   evidence requirements and declared write scope.\n2. Judge from a context that did not write the plan, following the shared\n   challenge method for identity, model selection, authorization and bounds. A\n   plan the caller wrote can be judged here, with the caller as author. If this\n   context wrote the plan and no fresh context can be started, run the checks\n   anyway, state that the independence leg is missing, and return inline\n   findings; never describe them as independent.\n3. Run the three checks against cited repository facts. For integration or\n   extension plans where anchoring on the working design is the risk, add the\n   [derivation-diff challenge](references\u002Fderivation-diff.md).\n4. Return one complete, bounded set of concrete findings with checked and\n   not-checked scope, then stop: the caller decides whether to revise the plan\n   or invoke RPI.\n\n## It's working if\n\nObservable in the output:\n\n- each unit names its verifier, and costly units with no fresh author-distinct\n  read are one finding listing those units; an ordinary unit graded by its\n  author's checks and CI is no finding;\n- each step is marked, and each one-way mark names its undo cost and point of\n  no return;\n- each finding cites a defeat attempt or the fact that blocked it;\n- the set is bounded: a review that flags every step has reported nothing.\n\n## Boundary\n\nEmit advisory findings, no verdict of any version, readiness, admission or\npermission. Do not implement, validate the candidate, retry, repair, schedule,\nclaim, change acceptance, operate Git, close work, release or deliver. Council\nor [Idea Genie](..\u002Fidea-genie\u002FSKILL.md#duel-mode) duel mode may be\ncaller-supplied evidence, but Premortem requires neither and cannot turn\nconsensus into approval. Any plan edit creates a new subject for a later\ncaller-initiated Premortem.\n\n## Output\n\nReturn findings inline by default:\n\n```text\nFindings (in check order, then most consequential first within each check)\n1. \u003Cstep> - \u003Chow it fails> - \u003Cconstruction, or the fact that blocked it> - \u003Cconsequence>\nVerifiers: \u003Cunit>: \u003Cwho verifies>\nSteps: \u003Cstep>: two-way | one-way - \u003Cundo cost> - \u003Cpoint of no return> - \u003Cwho holds the handle>\nChecked: \u003Cwhat was examined>. Not checked: \u003Cwhat was not>.\nIndependence: \u003Cjudge context, distinct from author> or \"missing: \u003Creason>\"\n```\n\nWhen the caller requests a durable review, follow\n[durable review](references\u002Fdurable-review.md) to return and check\n`premortem-plan-review.v1`. An empty finding set means only that this\noptional challenge found no concrete defect; it is never a lifecycle gate.\n",{"name":5,"consumes":44,"metadata":45,"produces":57,"practices":59,"context_rel":61,"description":7,"hexagonal_role":27,"user-invocable":52,"output_contract":64,"skill_api_version":65},[],{"tier":30,"effects":46,"triggers":48,"graph_root":52,"disposition":53,"capabilities":54,"dependencies":56,"canonical_status":29},[47],"write_advisory_plan_review",[49,50,51],"what could go wrong","poke holes","challenge this plan",true,"keep_strategy",[55],"challenge_plan",[],[58],"premortem-plan-review.v1",[60,28],"design-by-contract",[62],{"kind":63,"with":33},"supplier-to","schemas\u002Fpremortem-plan-review.v1.schema.json",1,"main","40706766fd37c03ca624f5206741fef55dd2a684","plugins\u002Fboshu2\u002Fagentops\u002Fskills\u002Fpremortem",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":77,"prompt":87,"zipAvailable":52},[78,81,84],{"tool":79,"command":80},"npx","npx skills add hashgraph-online\u002Fawesome-codex-plugins --skill premortem",{"tool":82,"command":83},"bunx","bunx skills add hashgraph-online\u002Fawesome-codex-plugins --skill premortem",{"tool":85,"command":86},"pnpm","pnpm dlx skills add hashgraph-online\u002Fawesome-codex-plugins --skill premortem","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Fhashgraph-online\u002Fawesome-codex-plugins\u002Fblob\u002Fmain\u002Fplugins\u002Fboshu2\u002Fagentops\u002Fskills\u002Fpremortem\u002FSKILL.md",[89,95,99,102,108],{"path":90,"resourceType":91,"resourceTypeDesc":92,"sizeBytes":93,"sourceHtmlUrl":94},"references\u002Fderivation-diff.md","REFERENCE","参考文档",1540,"https:\u002F\u002Fgithub.com\u002Fhashgraph-online\u002Fawesome-codex-plugins\u002Fblob\u002Fmain\u002Fplugins\u002Fboshu2\u002Fagentops\u002Fskills\u002Fpremortem\u002Freferences\u002Fderivation-diff.md",{"path":96,"resourceType":91,"resourceTypeDesc":92,"sizeBytes":97,"sourceHtmlUrl":98},"references\u002Fdurable-review.md",1734,"https:\u002F\u002Fgithub.com\u002Fhashgraph-online\u002Fawesome-codex-plugins\u002Fblob\u002Fmain\u002Fplugins\u002Fboshu2\u002Fagentops\u002Fskills\u002Fpremortem\u002Freferences\u002Fdurable-review.md",{"path":64,"resourceType":91,"resourceTypeDesc":92,"sizeBytes":100,"sourceHtmlUrl":101},1283,"https:\u002F\u002Fgithub.com\u002Fhashgraph-online\u002Fawesome-codex-plugins\u002Fblob\u002Fmain\u002Fplugins\u002Fboshu2\u002Fagentops\u002Fskills\u002Fpremortem\u002Fschemas\u002Fpremortem-plan-review.v1.schema.json",{"path":103,"resourceType":104,"resourceTypeDesc":105,"sizeBytes":106,"sourceHtmlUrl":107},"scripts\u002Fvalidate-output.sh","SCRIPT","脚本",2419,"https:\u002F\u002Fgithub.com\u002Fhashgraph-online\u002Fawesome-codex-plugins\u002Fblob\u002Fmain\u002Fplugins\u002Fboshu2\u002Fagentops\u002Fskills\u002Fpremortem\u002Fscripts\u002Fvalidate-output.sh",{"path":109,"resourceType":104,"resourceTypeDesc":105,"sizeBytes":110,"sourceHtmlUrl":111},"scripts\u002Fvalidate.sh",1584,"https:\u002F\u002Fgithub.com\u002Fhashgraph-online\u002Fawesome-codex-plugins\u002Fblob\u002Fmain\u002Fplugins\u002Fboshu2\u002Fagentops\u002Fskills\u002Fpremortem\u002Fscripts\u002Fvalidate.sh",[113,123,131,139,147,155],{"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":117,"licenseFileUrl":118,"sourceHtmlUrl":119,"categories":120,"keywords":121,"publishedAt":122},"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":124,"name":125,"nameZh":6,"description":126,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":117,"licenseFileUrl":127,"sourceHtmlUrl":128,"categories":129,"keywords":130,"publishedAt":122},"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":132,"name":133,"nameZh":6,"description":134,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":117,"licenseFileUrl":135,"sourceHtmlUrl":136,"categories":137,"keywords":138,"publishedAt":122},"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":140,"name":141,"nameZh":6,"description":142,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":117,"licenseFileUrl":143,"sourceHtmlUrl":144,"categories":145,"keywords":146,"publishedAt":122},"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":148,"name":149,"nameZh":6,"description":150,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":117,"licenseFileUrl":151,"sourceHtmlUrl":152,"categories":153,"keywords":154,"publishedAt":122},"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":156,"name":157,"nameZh":6,"description":158,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":117,"licenseFileUrl":159,"sourceHtmlUrl":160,"categories":161,"keywords":162,"publishedAt":122},"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",[],[]]