[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M6MEQ5048475J8H7F8VR2767":3,"skill-same:01M6MEQ5048475J8H7F8VR2767":116},{"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":41,"linkOnly":42,"markdownContent":43,"markdownBody":44,"frontMatter":45,"refName":75,"commitSha":76,"skillDirectory":77,"forksCount":78,"repositoryHtmlUrl":79,"repositoryHomepageUrl":80,"ownerHtmlUrl":81,"ownerBlogUrl":82,"ownerDescription":83,"updatedAt":84,"install":85,"resources":97},"01M6MEQ5048475J8H7F8VR2767","implement",null,"Make the code change a ticket or bug report asks for, then prove it with the repo's own checks. Use when: told to fix, change or build something, such as \"fix this bug\".","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\u002Fimplement\u002FSKILL.md",[],[5,19,20,21,22,23,24,25,26,27,28,29,30,31,32,33,34,35,36,37,38,39,40],"refactoring","bug report","when","ticket","identity","experiment","canonical","flow","judgment","bug","config","at","customer","next","native","change","plan","batch","code","implementing","ci","fix","2026-11-10 10:12:30",false,"---\nname: implement\ndescription: 'Make the code change a ticket or bug report asks for, then prove it with the repo''s own checks. Use when: told to fix, change or build something, such as \"fix this bug\".'\npractices:\n- tdd\n- refactoring\n- small-batch-flow\nhexagonal_role: driving-adapter\nconsumes: []\nproduces:\n- subject-manifest.v1\noutput_contract: 'content identity, author context ID and check facts through the native handoff; subject-manifest.v1 at the judgment boundary'\ncontext_rel:\n- kind: customer-of\n  with: plan\nskill_api_version: 1\nuser-invocable: true\nmetadata:\n  graph_root: true\n  tier: execution\n  dependencies: []\n  capabilities: [execute_one_experiment, collect_factual_evidence]\n  effects: [modify_declared_subject, derive_subject_manifest]\n  canonical_status: canonical\n  disposition: keep\n  triggers: [\"execute the next wave\", \"per-lane evidence\", \"fix this bug\", \"CI is red\", \"loosen the assertion\"]\n---\n\n# Implement\n\nImplement the accepted outcome. Repair ordinary known defects directly. Use the\nexisting intent; a clear edit needs no Plan first. An incoming report nobody\nhas accepted yet goes to [Triage](..\u002Ftriage\u002FSKILL.md) first. Implement owns source changes\nand factual checks.\n\n## Rules that decide the result\n\n- **Fix the cause, not the oracle.** Never loosen an assertion, tolerance,\n  golden, fixture or suppression, or substitute a mock or placeholder, to turn\n  a check green; nor change what the check runs against: code that acts\n  differently under test or CI, a newly silenced failure path, or a check made\n  non-blocking or skipped. A check that fails against accepted behavior points\n  at a product defect; changing what the check accepts is an acceptance change\n  and needs caller authority.\n- **Find live consumers before editing.** Search the callers, readers, scripts,\n  docs and tests of every edited function, type, path, format or message. For\n  each one, state whether the change affects it and which check covers it. When\n  retiring or renaming, consumers include installations, lookups and old-name\n  invocations; preserve historical provenance. If the replaced interface never\n  merged or shipped and every consumer update fits the scope, update them and\n  delete the old version in the same change, with no alias or shim; otherwise\n  keep the old version working or report it.\n- **Name discriminating checks.** A behavioral change preserves RED\n  for the expected missing behavior: name the check that fails before the edit\n  and passes after ([Test's proof rule](..\u002Ftest\u002FSKILL.md#critical-constraints)),\n  plus the check for each affected consumer.\n- **Report only what ran.** Give exact commands and results. List every check\n  you did not or could not run as not run. Never call unrun work verified,\n  fixed or green. Output can show as soon as a command runs, so keep secrets\n  out when you build it: credentials stay in the environment, output that may\n  carry tokens goes to a file, and only redacted excerpts are shown.\n\nWhen changing a public failure path, preserve its native failure signal and\ncheck that its recovery advice matches any work already performed. For uncertain\nwrite outcomes or unattended callers, use only the relevant checks in\n[Test's error recovery method](..\u002Ftest\u002Freferences\u002Ferror-recovery.md).\n\nFor an accepted bounded shortcut, review feedback or a defect your change\nintroduced, an authorized commit, history rewrite or merge conflict, dependency\nupgrade, removal, blocked operation, a decision read from another tool's state\nor your own uncertain write, use only the matching [change safety method](references\u002Fchange-safety.md).\nThese methods preserve existing authority; they grant no new operation.\n\nFor authorized service operations, load only the relevant procedure from\n[operations methods](references\u002Foperations.md) (reliability, delivery, incident\nrecovery, resilience, toil); ordinary edits owe no operations phase.\n\n## Workflow\n\n1. Read intent, acceptance, scope and repository boundaries before the first\n   write; reuse loaded contracts. [RPI boundaries](..\u002Frpi\u002Freferences\u002Fboundaries.md)\n   apply when RPI is selected; caller-selected episode tracking follows the\n   [session association reference](..\u002Forchestrate\u002Freferences\u002Fsession-associations.md#work-to-session-associations).\n   Note the revision and files already modified, staged or untracked; report\n   only your own as changed, and ask the caller before editing one holding\n   others' edits.\n2. Carry the accepted behavior examples forward unchanged. Use repository\n   domain names in symbols and tests; check observable outcomes through the\n   relevant interface. Run the smallest applicable check before and after\n   editing. Pure refactors, relocations or docs may have an honest green\n   baseline. Prefer existing tests or small discriminating probes.\n3. Make the smallest in-scope change. When repairing discovery or checks,\n   preserve the consumer's existing input selection; fixing an error path does\n   not authorize a wider scan. Use a negative control when exclusion matters.\n   Check a representative change against existing constraints before bulk\n   propagation, and the authored source set before broad regeneration. A\n   scripted edit across files first confirms that each anchor matches exactly\n   once; on zero or several matches, write nothing and re-derive it. Repair\n   known failures directly and verify the exact result with a check; a repair\n   does not start another review. A disproved assumption may change the\n   approach within scope; use Plan only for consequential uncertainty.\n4. Read the repository's actual check recipe, including instrumentation and\n   environment, rather than reconstructing it from memory. Run targeted tests\n   and lint\u002Fstatic checks before broad integration, and required full checks at\n   integration. Reuse exact-input receipts only while source, tool and relevant\n   environment match. Neither bypass required hooks nor replay a check just to\n   rename its receipt. A required CI job's known failure is actionable before\n   the run ends: repair it within scope, keep the failed subject's evidence and\n   rerun affected checks. Pending jobs do not imply success. A new check, hook\n   or lint rule counts once the aggregate command or CI runs it (a Git hook needs\n   an install path; `.git\u002Fhooks` is not cloned) and it fails on a deliberate\n   violation; else list it under `gaps` as not wired. Use a local server already\n   on a port only if it provably serves this checkout; stop only processes you started.\n5. Refactor while acceptance remains green. Inspect changed tests, fixtures,\n   goldens, tolerances, suppressions and specification text against original\n   intent before handoff. Reread that intent at its source, not a compacted\n   summary, and check the whole delta against it, untracked files included.\n   Remove leftovers of abandoned approaches, temporary probes (one shared\n   marker lets a single search prove none remain) and files your checks made;\n   list any path you cannot explain under `gaps` as a scope amendment.\n6. Have the runtime derive actual changed paths and content identity: read\n   changed paths from Git (`git status --porcelain`,\n   `git diff --name-only \u003Cbase>`), never from memory;\n   `ao provenance manifest --root \u003Crepo>` with one `--include \u003Cpath>` per\n   declared path digests only the paths you declare and runs no Git. A delegated\n   increment awaiting integration returns an exact commit or runtime-derived\n   content digests, author context ID and check facts in the existing handoff.\n   Copy that ID from the session, subagent or thread ID the runtime exposes, or\n   label a caller-supplied one as supplied; otherwise report it as unknown,\n   never made up. The integrating caller derives `subject-manifest.v1` (AgentOps\n   schema [subject-manifest.v1.schema.json](https:\u002F\u002Fgithub.com\u002Fboshu2\u002Fagentops\u002Fblob\u002Fmain\u002Fschemas\u002Fsubject-manifest.v1.schema.json), AgentOps source checkout only) over the complete final\n   subject before judgment; an independently judged increment needs its own\n   manifest. Do not generate both merely because work was delegated. Where the\n   repository records AgentOps evidence bindings, also run the advisory\n   `ao provenance evidence-orphans --root \u003Crepo-root>` with one `--changed \u003Cpath>`\n   per derived path. Disclose the rows whose cause is `changed_path` or `both`\n   (they bind your paths); count the rest under `gaps` as pre-existing drift,\n   and refresh a binding only when its owner asks. Without `ao`, list it under\n   `not run`.\n7. Return the handoff below.\n\n## Handoff\n\nKeep full logs at their source; do not duplicate inventories or status documents.\n\n```text\nchanged:        \u003Cruntime-derived paths>; identity: \u003Ccommit or content digests>\nauthor:         \u003Cruntime session\u002Fsubagent\u002Fthread ID, \"ID (supplied)\" or \"unknown\">; when an integrator or fresh read follows\nchecks:         \u003Cexact command> -> \u003Cresult>, one per line; before and after for a behavioral change\nnot run:        \u003Ccheck> -> \u003Creason>; \"none\" only when every relevant check ran\nconsumers:      \u003Cfile:line> -> \u003Ccovering check, or \"uncovered\">\nnot_as_briefed: \u003Csteps refused, held, worked around or unverified, one line with its reason each> | none\ngaps:           \u003Cmissing or truncated evidence, known failures, scope amendments needed> | none\ncause:          \u003Cdefect repairs only: trigger -> mechanism -> symptom at file:line; sites left as follow-up>\n```\n\nReport an uncovered live consumer for a caller scope amendment and continue\nindependent authorized work. Disclose a reversible implementation choice only\nwhen its alternative has a material consequence the caller may want to change;\nname the choice, alternative and reason in the handoff, without a fixed worksheet.\nGenerated companions already included as scope require no new approval; a change\nto accepted direction, behavior or acceptance always needs caller authority.\n\n## Diagnosis, scaffolding and delegated work\n\nBefore repairing a failure you cannot yet explain, read and follow the\n[diagnosis loop](references\u002Fdifficult-failures.md#diagnosis-loop). The same\nfile holds the experiments for races, leaked state, hangs, regressions and\nfailures that cross components.\n\nWhen scaffolding is the requested change, start from the repository's existing\nlayout (or the ecosystem's standard one for a new project) and one working\nvertical slice; avoid placeholder success paths and a new framework for a\none-off operation.\n\nPrefer current-session execution. When delegation is authorized, or the caller\nasks for a one-shot adapter or a factory, read\n[delegated work](references\u002Fdelegated-work.md) before dispatching or writing it.\n\n## Finish\n\nSpecialists advise only; known defects stay implementation work. A genuine\ncausal stall admits one bounded fresh helper under RPI's\n[stall rule](..\u002Frpi\u002FSKILL.md#causal-stall-and-bounds); retries renew no bound.\n\nReturn facts, not semantic PASS. An implement-only handoff does not authorize\nGit, tracker or delivery transitions; existing caller authority remains usable.\nA full outcome request finishes on its checks and CI; it continues to one fresh\nindependent judgment only on [Validate's triggers](..\u002Fvalidate\u002FSKILL.md#when-a-fresh-judgment-is-worth-it).\n","# Implement\n\nImplement the accepted outcome. Repair ordinary known defects directly. Use the\nexisting intent; a clear edit needs no Plan first. An incoming report nobody\nhas accepted yet goes to [Triage](..\u002Ftriage\u002FSKILL.md) first. Implement owns source changes\nand factual checks.\n\n## Rules that decide the result\n\n- **Fix the cause, not the oracle.** Never loosen an assertion, tolerance,\n  golden, fixture or suppression, or substitute a mock or placeholder, to turn\n  a check green; nor change what the check runs against: code that acts\n  differently under test or CI, a newly silenced failure path, or a check made\n  non-blocking or skipped. A check that fails against accepted behavior points\n  at a product defect; changing what the check accepts is an acceptance change\n  and needs caller authority.\n- **Find live consumers before editing.** Search the callers, readers, scripts,\n  docs and tests of every edited function, type, path, format or message. For\n  each one, state whether the change affects it and which check covers it. When\n  retiring or renaming, consumers include installations, lookups and old-name\n  invocations; preserve historical provenance. If the replaced interface never\n  merged or shipped and every consumer update fits the scope, update them and\n  delete the old version in the same change, with no alias or shim; otherwise\n  keep the old version working or report it.\n- **Name discriminating checks.** A behavioral change preserves RED\n  for the expected missing behavior: name the check that fails before the edit\n  and passes after ([Test's proof rule](..\u002Ftest\u002FSKILL.md#critical-constraints)),\n  plus the check for each affected consumer.\n- **Report only what ran.** Give exact commands and results. List every check\n  you did not or could not run as not run. Never call unrun work verified,\n  fixed or green. Output can show as soon as a command runs, so keep secrets\n  out when you build it: credentials stay in the environment, output that may\n  carry tokens goes to a file, and only redacted excerpts are shown.\n\nWhen changing a public failure path, preserve its native failure signal and\ncheck that its recovery advice matches any work already performed. For uncertain\nwrite outcomes or unattended callers, use only the relevant checks in\n[Test's error recovery method](..\u002Ftest\u002Freferences\u002Ferror-recovery.md).\n\nFor an accepted bounded shortcut, review feedback or a defect your change\nintroduced, an authorized commit, history rewrite or merge conflict, dependency\nupgrade, removal, blocked operation, a decision read from another tool's state\nor your own uncertain write, use only the matching [change safety method](references\u002Fchange-safety.md).\nThese methods preserve existing authority; they grant no new operation.\n\nFor authorized service operations, load only the relevant procedure from\n[operations methods](references\u002Foperations.md) (reliability, delivery, incident\nrecovery, resilience, toil); ordinary edits owe no operations phase.\n\n## Workflow\n\n1. Read intent, acceptance, scope and repository boundaries before the first\n   write; reuse loaded contracts. [RPI boundaries](..\u002Frpi\u002Freferences\u002Fboundaries.md)\n   apply when RPI is selected; caller-selected episode tracking follows the\n   [session association reference](..\u002Forchestrate\u002Freferences\u002Fsession-associations.md#work-to-session-associations).\n   Note the revision and files already modified, staged or untracked; report\n   only your own as changed, and ask the caller before editing one holding\n   others' edits.\n2. Carry the accepted behavior examples forward unchanged. Use repository\n   domain names in symbols and tests; check observable outcomes through the\n   relevant interface. Run the smallest applicable check before and after\n   editing. Pure refactors, relocations or docs may have an honest green\n   baseline. Prefer existing tests or small discriminating probes.\n3. Make the smallest in-scope change. When repairing discovery or checks,\n   preserve the consumer's existing input selection; fixing an error path does\n   not authorize a wider scan. Use a negative control when exclusion matters.\n   Check a representative change against existing constraints before bulk\n   propagation, and the authored source set before broad regeneration. A\n   scripted edit across files first confirms that each anchor matches exactly\n   once; on zero or several matches, write nothing and re-derive it. Repair\n   known failures directly and verify the exact result with a check; a repair\n   does not start another review. A disproved assumption may change the\n   approach within scope; use Plan only for consequential uncertainty.\n4. Read the repository's actual check recipe, including instrumentation and\n   environment, rather than reconstructing it from memory. Run targeted tests\n   and lint\u002Fstatic checks before broad integration, and required full checks at\n   integration. Reuse exact-input receipts only while source, tool and relevant\n   environment match. Neither bypass required hooks nor replay a check just to\n   rename its receipt. A required CI job's known failure is actionable before\n   the run ends: repair it within scope, keep the failed subject's evidence and\n   rerun affected checks. Pending jobs do not imply success. A new check, hook\n   or lint rule counts once the aggregate command or CI runs it (a Git hook needs\n   an install path; `.git\u002Fhooks` is not cloned) and it fails on a deliberate\n   violation; else list it under `gaps` as not wired. Use a local server already\n   on a port only if it provably serves this checkout; stop only processes you started.\n5. Refactor while acceptance remains green. Inspect changed tests, fixtures,\n   goldens, tolerances, suppressions and specification text against original\n   intent before handoff. Reread that intent at its source, not a compacted\n   summary, and check the whole delta against it, untracked files included.\n   Remove leftovers of abandoned approaches, temporary probes (one shared\n   marker lets a single search prove none remain) and files your checks made;\n   list any path you cannot explain under `gaps` as a scope amendment.\n6. Have the runtime derive actual changed paths and content identity: read\n   changed paths from Git (`git status --porcelain`,\n   `git diff --name-only \u003Cbase>`), never from memory;\n   `ao provenance manifest --root \u003Crepo>` with one `--include \u003Cpath>` per\n   declared path digests only the paths you declare and runs no Git. A delegated\n   increment awaiting integration returns an exact commit or runtime-derived\n   content digests, author context ID and check facts in the existing handoff.\n   Copy that ID from the session, subagent or thread ID the runtime exposes, or\n   label a caller-supplied one as supplied; otherwise report it as unknown,\n   never made up. The integrating caller derives `subject-manifest.v1` (AgentOps\n   schema [subject-manifest.v1.schema.json](https:\u002F\u002Fgithub.com\u002Fboshu2\u002Fagentops\u002Fblob\u002Fmain\u002Fschemas\u002Fsubject-manifest.v1.schema.json), AgentOps source checkout only) over the complete final\n   subject before judgment; an independently judged increment needs its own\n   manifest. Do not generate both merely because work was delegated. Where the\n   repository records AgentOps evidence bindings, also run the advisory\n   `ao provenance evidence-orphans --root \u003Crepo-root>` with one `--changed \u003Cpath>`\n   per derived path. Disclose the rows whose cause is `changed_path` or `both`\n   (they bind your paths); count the rest under `gaps` as pre-existing drift,\n   and refresh a binding only when its owner asks. Without `ao`, list it under\n   `not run`.\n7. Return the handoff below.\n\n## Handoff\n\nKeep full logs at their source; do not duplicate inventories or status documents.\n\n```text\nchanged:        \u003Cruntime-derived paths>; identity: \u003Ccommit or content digests>\nauthor:         \u003Cruntime session\u002Fsubagent\u002Fthread ID, \"ID (supplied)\" or \"unknown\">; when an integrator or fresh read follows\nchecks:         \u003Cexact command> -> \u003Cresult>, one per line; before and after for a behavioral change\nnot run:        \u003Ccheck> -> \u003Creason>; \"none\" only when every relevant check ran\nconsumers:      \u003Cfile:line> -> \u003Ccovering check, or \"uncovered\">\nnot_as_briefed: \u003Csteps refused, held, worked around or unverified, one line with its reason each> | none\ngaps:           \u003Cmissing or truncated evidence, known failures, scope amendments needed> | none\ncause:          \u003Cdefect repairs only: trigger -> mechanism -> symptom at file:line; sites left as follow-up>\n```\n\nReport an uncovered live consumer for a caller scope amendment and continue\nindependent authorized work. Disclose a reversible implementation choice only\nwhen its alternative has a material consequence the caller may want to change;\nname the choice, alternative and reason in the handoff, without a fixed worksheet.\nGenerated companions already included as scope require no new approval; a change\nto accepted direction, behavior or acceptance always needs caller authority.\n\n## Diagnosis, scaffolding and delegated work\n\nBefore repairing a failure you cannot yet explain, read and follow the\n[diagnosis loop](references\u002Fdifficult-failures.md#diagnosis-loop). The same\nfile holds the experiments for races, leaked state, hangs, regressions and\nfailures that cross components.\n\nWhen scaffolding is the requested change, start from the repository's existing\nlayout (or the ecosystem's standard one for a new project) and one working\nvertical slice; avoid placeholder success paths and a new framework for a\none-off operation.\n\nPrefer current-session execution. When delegation is authorized, or the caller\nasks for a one-shot adapter or a factory, read\n[delegated work](references\u002Fdelegated-work.md) before dispatching or writing it.\n\n## Finish\n\nSpecialists advise only; known defects stay implementation work. A genuine\ncausal stall admits one bounded fresh helper under RPI's\n[stall rule](..\u002Frpi\u002FSKILL.md#causal-stall-and-bounds); retries renew no bound.\n\nReturn facts, not semantic PASS. An implement-only handoff does not authorize\nGit, tracker or delivery transitions; existing caller authority remains usable.\nA full outcome request finishes on its checks and CI; it continues to one fresh\nindependent judgment only on [Validate's triggers](..\u002Fvalidate\u002FSKILL.md#when-a-fresh-judgment-is-worth-it).\n",{"name":5,"consumes":46,"metadata":47,"produces":64,"practices":66,"context_rel":69,"description":7,"hexagonal_role":72,"user-invocable":58,"output_contract":73,"skill_api_version":74},[],{"tier":48,"effects":49,"triggers":52,"graph_root":58,"disposition":59,"capabilities":60,"dependencies":63,"canonical_status":25},"execution",[50,51],"modify_declared_subject","derive_subject_manifest",[53,54,55,56,57],"execute the next wave","per-lane evidence","fix this bug","CI is red","loosen the assertion",true,"keep",[61,62],"execute_one_experiment","collect_factual_evidence",[],[65],"subject-manifest.v1",[67,19,68],"tdd","small-batch-flow",[70],{"kind":71,"with":35},"customer-of","driving-adapter","content identity, author context ID and check facts through the native handoff; subject-manifest.v1 at the judgment boundary",1,"main","347aedf8480cd92b21f761e97b7343a45898f5fa","plugins\u002Fboshu2\u002Fagentops\u002Fskills\u002Fimplement",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":86,"prompt":96,"zipAvailable":58},[87,90,93],{"tool":88,"command":89},"npx","npx skills add hashgraph-online\u002Fawesome-codex-plugins --skill implement",{"tool":91,"command":92},"bunx","bunx skills add hashgraph-online\u002Fawesome-codex-plugins --skill implement",{"tool":94,"command":95},"pnpm","pnpm dlx skills add hashgraph-online\u002Fawesome-codex-plugins --skill implement","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Fhashgraph-online\u002Fawesome-codex-plugins\u002Fblob\u002Fmain\u002Fplugins\u002Fboshu2\u002Fagentops\u002Fskills\u002Fimplement\u002FSKILL.md",[98,104,108,112],{"path":99,"resourceType":100,"resourceTypeDesc":101,"sizeBytes":102,"sourceHtmlUrl":103},"references\u002Fchange-safety.md","REFERENCE","参考文档",7891,"https:\u002F\u002Fgithub.com\u002Fhashgraph-online\u002Fawesome-codex-plugins\u002Fblob\u002Fmain\u002Fplugins\u002Fboshu2\u002Fagentops\u002Fskills\u002Fimplement\u002Freferences\u002Fchange-safety.md",{"path":105,"resourceType":100,"resourceTypeDesc":101,"sizeBytes":106,"sourceHtmlUrl":107},"references\u002Fdelegated-work.md",1406,"https:\u002F\u002Fgithub.com\u002Fhashgraph-online\u002Fawesome-codex-plugins\u002Fblob\u002Fmain\u002Fplugins\u002Fboshu2\u002Fagentops\u002Fskills\u002Fimplement\u002Freferences\u002Fdelegated-work.md",{"path":109,"resourceType":100,"resourceTypeDesc":101,"sizeBytes":110,"sourceHtmlUrl":111},"references\u002Fdifficult-failures.md",10170,"https:\u002F\u002Fgithub.com\u002Fhashgraph-online\u002Fawesome-codex-plugins\u002Fblob\u002Fmain\u002Fplugins\u002Fboshu2\u002Fagentops\u002Fskills\u002Fimplement\u002Freferences\u002Fdifficult-failures.md",{"path":113,"resourceType":100,"resourceTypeDesc":101,"sizeBytes":114,"sourceHtmlUrl":115},"references\u002Foperations.md",8010,"https:\u002F\u002Fgithub.com\u002Fhashgraph-online\u002Fawesome-codex-plugins\u002Fblob\u002Fmain\u002Fplugins\u002Fboshu2\u002Fagentops\u002Fskills\u002Fimplement\u002Freferences\u002Foperations.md",[117,127,135,143,151,159],{"skillNo":118,"name":119,"nameZh":6,"description":120,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":121,"licenseFileUrl":122,"sourceHtmlUrl":123,"categories":124,"keywords":125,"publishedAt":126},"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":128,"name":129,"nameZh":6,"description":130,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":121,"licenseFileUrl":131,"sourceHtmlUrl":132,"categories":133,"keywords":134,"publishedAt":126},"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":136,"name":137,"nameZh":6,"description":138,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":121,"licenseFileUrl":139,"sourceHtmlUrl":140,"categories":141,"keywords":142,"publishedAt":126},"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":144,"name":145,"nameZh":6,"description":146,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":121,"licenseFileUrl":147,"sourceHtmlUrl":148,"categories":149,"keywords":150,"publishedAt":126},"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":152,"name":153,"nameZh":6,"description":154,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":121,"licenseFileUrl":155,"sourceHtmlUrl":156,"categories":157,"keywords":158,"publishedAt":126},"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":160,"name":161,"nameZh":6,"description":162,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":121,"licenseFileUrl":163,"sourceHtmlUrl":164,"categories":165,"keywords":166,"publishedAt":126},"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",[],[]]