[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M6MESA1C6PKHMWZW6PK994WH":3,"skill-same:01M6MESA1C6PKHMWZW6PK994WH":228},{"skillNo":4,"name":5,"nameZh":6,"description":7,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":16,"categories":17,"keywords":23,"publishedAt":45,"linkOnly":46,"markdownContent":47,"markdownBody":48,"frontMatter":49,"refName":81,"commitSha":82,"skillDirectory":83,"forksCount":84,"repositoryHtmlUrl":85,"repositoryHomepageUrl":86,"ownerHtmlUrl":87,"ownerBlogUrl":88,"ownerDescription":89,"updatedAt":90,"install":91,"resources":103},"01M6MESA1C6PKHMWZW6PK994WH","skill-builder",null,"Create, repair, audit or consolidate agent skills (SKILL.md packages). Use when: writing or fixing a skill, its description or structure. Not for one-off lessons; use Memory.","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\u002Fskill-builder\u002FSKILL.md",[18],{"categoryNo":19,"categoryName":20,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000023","Skill与智能体开发","SCENARIO","使用场景",[24,25,26,27,28,29,30,31,32,33,34,35,36,37,38,39,40,41,42,43,44],"Skill Builder","builder","when","writing","exported","expertise","proposal","creation","consolidate","structure","pragmatic","files","conversion","distill","refactoring","Meta","audit","create","packages","valid","memory","2026-11-10 10:12:30",false,"---\nname: skill-builder\ndescription: 'Create, repair, audit or consolidate agent skills (SKILL.md packages). Use when: writing or fixing a skill, its description or structure. Not for one-off lessons; use Memory.'\npractices:\n- pragmatic-programmer\n- refactoring\nhexagonal_role: supporting\nconsumes: []\nproduces:\n- skill-source-package\n- skill-hygiene-report\n- converted-skill\n- operationalization-proposal\ncontext_rel: []\nskill_api_version: 1\nuser-invocable: true\nmetadata:\n  capabilities: [skill_builder, heal_skill, export_skill, distill_expertise]\n  effects: [write_skill_source, write_build_report, regenerate_skill_projections, repair_skill_projections, write_converted_skill_projection, write_advisory_proposal]\n  canonical_status: canonical\n  disposition: keep_specialist\n  tier: meta\n  dependencies: []\n  stability: experimental\noutput_contract: build-report.json for creation, audit-report.json for audit, target-valid exported files for conversion, or an advisory expertise proposal\n---\n# Skill Builder\n\nCreate, repair, audit or export one canonical skill package, or turn supported\nexpertise into a small authoring proposal. Before writing anything new, decide\nfrom evidence whether anything new is warranted: a request for a new skill,\ngate or tracking file usually ends as a short addition to an existing owner,\nor as no change.\n\n## Decide whether to create anything\n\nApply these before any creation step, including when the request already names\nthe new skill or file it wants:\n\n1. **Find the existing owner.** Search skills, references, checklists and\n   instruction files for one that already handles the behavior. Extend that\n   owner rather than adding a root.\n2. **Count independent occurrences.** A new skill, gate, library or workflow\n   needs three independently evidenced real occurrences and a successful\n   reapplication to a source case without missing context. Fewer occurrences\n   support only a narrow note in an existing owner; one incident is an\n   observation, not a skill. An authoritative source supports only a faithful\n   statement of that source.\n3. **Name the consumer of every new artifact.** A proposed process artifact\n   (a report, ledger, counter, dashboard or tracker) needs a concrete consumer,\n   the decision it informs, the observed defect it answers and a retirement\n   condition. If any is missing, leave it out; code written only to consume it\n   is no consumer.\n4. **No action is a valid result**, and so is a short addition to an existing\n   owner. Say what the evidence supports before drafting, build only what the\n   caller then authorizes, and return a proposal inline unless a durable one\n   was requested.\n5. **A built package proves no benefit.** Route behavioral benefit to\n   [Skill Eval](..\u002Fskill-eval\u002FSKILL.md) and acceptance judgment to\n   [Validate](..\u002Fvalidate\u002FSKILL.md).\n\nThe result shows it worked when it names the existing owner it searched, the\nnumber of independent occurrences found, and either no new file or exactly the\npackage the caller authorized.\n\n## Choose the requested operation\n\n`\u003Cskill-dir>` is the directory that contains this SKILL.md. Claude Code shows it\nas \"Base directory for this skill\"; Codex lists this skill's SKILL.md path; in\nan AgentOps source checkout it is `skills\u002Fskill-builder`. Replace `\u003Cskill-dir>`\nwith that absolute path before running a command. The working directory stays\nthe user's repository. If the host did not show where this skill is installed,\nuse the directory of the SKILL.md you read. If you cannot determine it, do not\nguess a path or run a same-named script from the current repository; say the\nbundled script is unavailable and apply the rules and doctrine here to the\npackage by hand and use its repository's own checks.\n\n| Need | Entry point | Runs only with |\n|---|---|---|\n| Create a source package | `bash \"\u003Cskill-dir>\u002Fscripts\u002Fbuild.sh\" from-scratch \u003Cslug>`, `from-template \u003Cslug> --like \u003Cexisting-slug>` or `absorb-external \u003Cslug> --from \u003Cpath>` | an AgentOps source checkout with Go |\n| Check package structure | `bash \"\u003Cskill-dir>\u002Fscripts\u002Fheal.sh\" --check [--strict] skills\u002F\u003Cslug>` | Go in a source checkout, or `ao` 3.9 or later elsewhere |\n| Repair the skill mesh | `bash \"\u003Cskill-dir>\u002Fscripts\u002Fheal.sh\" --fix skills\u002F\u003Cslug>` | an AgentOps source checkout with Go |\n| Inspect audit evidence | `bash \"\u003Cskill-dir>\u002Fscripts\u002Faudit.sh\" [--profile canonical\\|portable\\|external-observation] [--json \u003Cpath>] skills\u002F\u003Cslug>` | Go in a source checkout, or `ao` 3.9 or later elsewhere |\n| Merge overlapping skills | [Consolidate](#consolidate) | nothing bundled |\n| Export to another platform | [Conversion](#conversion) | Bash 4.3 or later |\n| Make repeated expertise reusable | [Distill expertise](#distill-expertise) | nothing bundled |\n\nRun only the selected operation. A plugin install ships these scripts but no\n`ao` binary or Go source: without `ao` on PATH, `audit.sh` exits 127 with\n`ao: not found` and `heal.sh` exits 2. Then apply the\n[source template](references\u002Fskill-template.md) and\n[authoring doctrine](references\u002Fauthoring-doctrine.md) by hand and use the\ntarget repository's own checks. `build.sh` and `heal.sh --fix` work on\n`skills\u002F` of an AgentOps source checkout and refuse with exit 2 elsewhere, such\nas from a plugin install, instead of writing into its cache; `heal.sh --fix`\nchecks the source first, so a target with findings exits 1 before that refusal.\n`heal.sh` in either mode checks only its own root's `skills\u002F` and resolves a\nrelative target there, not in the current directory. For a skill in another\nrepository or a user's skills directory, apply the rules and doctrine here to\nthat directory and use its own checks; with `ao` installed, `audit.sh` resolves\ntargets from the current directory and has `portable` and\n`external-observation` profiles, so it is the bundled check there.\nRoots, inputs, report destinations, exit codes and recovery from partial\ncreation are in [build and check mechanics](references\u002Fbuild-mechanics.md).\n\n## Create and maintain\n\nTreat external skills as structural signals only. Clean-room output must not\ncopy their names, prose, prompts, scripts or examples. Every creation mode\nwrites the same blank scaffold: `from-template` only checks the named skill and\nrecords it as `source_hint`, and `absorb-external` only verifies its input.\nNeither imports another skill's content or metadata.\n\n`build.sh` creates one incomplete source package containing only\n`SKILL.md` with `metadata.authoring_state: scaffold`; helpers, references and\nassets are conditional on the actual behavior. Replace the placeholders and\nstate applicability, inputs, authority, result, completion and failure in the\nlayout that makes them clear. An ending such as \"hand off\" or \"then stop\" can\nend the caller's turn when the skill runs inline; read\n[endings](references\u002Fauthoring-doctrine.md#state-authority-and-a-usable-failure-path)\nbefore writing one. Remove the scaffold state only after authoring the\nbehavior; strict source checks reject it. Removing it is an author assertion,\nnot proof of semantic completeness.\n\nBefore editing a skill after a miss or a review finding, read\n[changing existing text](references\u002Fauthoring-doctrine.md#change-existing-text-at-its-owning-layer);\nit decides when text stays unchanged, when a list stays explicit, and what to\ncheck before cutting a line.\n\nEdit `skills\u002F\u003Cslug>\u002F` as the source owner. Check the completed source with\n`bash \"\u003Cskill-dir>\u002Fscripts\u002Fheal.sh\" --check --strict skills\u002F\u003Cslug>`. In an\nAgentOps source checkout only, run `bash scripts\u002Fregen-all.sh` from the\nrepository root to regenerate every owned projection, including\n`plugin\u002Fskills\u002F`; `bash \"\u003Cskill-dir>\u002Fscripts\u002Fheal.sh\" --fix skills\u002F\u003Cslug>`\nregenerates only the skill mesh and leaves plugin copies unchanged. Inspect the\ngenerated diff; hand-edit no projection. A clean check says nothing about\nbehavior: when an edit changes\nwhen the skill routes, what it asks, when it stops, what it commits or\npublishes or how it degrades, or cuts a line that recorded provenance protects,\nreport that behavior as unmeasured unless a [Skill Eval](..\u002Fskill-eval\u002FSKILL.md)\nresult measured that behavior, and name what was missing (a runner, a host or\nthe caller's authorization). Typo, path and formatting edits need no such note.\n\nCreation is staged, not atomic. If a later stage fails, keep the created source\nand any report and follow [recovery](references\u002Fbuild-mechanics.md#staged-creation-and-recovery);\nnever call a partial result a completed package or delete it to rerun creation.\nA missing script, reference or runtime blocks only the operation that needs it;\nname it and continue the rest.\n\nThe default audit reports conformance, effects, behavior and authoring\nsuspicions separately, with no total or verdict; effects and behavior stay\n`NOT_PROVEN` because it runs no skill. Checks, exit codes and the opt-in legacy\nschema are in [audit checks](references\u002Faudit-checks.md); what Codex reads is in\n[Codex parity](references\u002Fcodex-parity.md).\n\n## Consolidate\n\nMerge only when two skills own the same behavior; a shared passage or two is a\ncross-link, not a merge. Apply the decision rules above, then pick one owner:\nkeep the skill with the stronger contract (clearer applicability, authority,\nresult and failure path) and move into it only the rules the other has and it\nlacks. Before retiring the other name, search the skills, references,\ninstruction files, goal prompts, workflows and docs for callers that invoke it\nby name, point each at the owner, and keep the old name until every caller does.\nIn the AgentOps repository, also record the retired name and its new owner in\n`docs\u002FMIGRATION.md` and add the slug to `REMOVED_SKILLS` in\n`scripts\u002Fcheck-cathedral-cut-conformance.py`, which fails if the skill comes\nback; never delete a skill there without that tombstone. A merge can move\nrouting, so report as unmeasured whether the requests the retired skill caught\nnow reach the owner unless a routing or [Skill Eval](..\u002Fskill-eval\u002FSKILL.md)\nresult measured it.\n\n## Conversion\n\nRun `bash \"\u003Cskill-dir>\u002Fscripts\u002Fconverter\u002Fconvert.sh\" \u003Csource-skill-dir> \u003Ctarget>\n[output-dir]` to export one package, or `--all`, to `codex`, `cursor` or `test`\noutside the shipped tree. Before an export, read\n[running the converter](references\u002Fconverter\u002Fskill-bundle-schema.md#run-the-converter)\nfor path resolution, the default output and its refusals. Preserve the source;\nfix the source or adapter, never the exported output.\n\n## Distill expertise\n\nWhen the caller wants a reusable rule, apply the decision rules above and begin\nwith cited occurrences or a named authoritative source. State the trigger,\ndesired behavior, inputs, outputs, limits and a negative or holdout case the\nrule decides correctly, with short source excerpts and resolvable citations.\nUse Research's [pattern mode](..\u002Fresearch\u002FSKILL.md#pattern-evidence) when the\nclaim needs exemplars and a holdout, and\n[Memory's source and destination rules](..\u002Fmemory\u002FSKILL.md) for mined material.\nA proposal-only request ends with the proposal. For an actual package edit, use\nthe [source template](references\u002Fskill-template.md) for required fields and the\nadmission test in [changing existing text](references\u002Fauthoring-doctrine.md#change-existing-text-at-its-owning-layer)\nto decide which prose earns a place.\n","# Skill Builder\n\nCreate, repair, audit or export one canonical skill package, or turn supported\nexpertise into a small authoring proposal. Before writing anything new, decide\nfrom evidence whether anything new is warranted: a request for a new skill,\ngate or tracking file usually ends as a short addition to an existing owner,\nor as no change.\n\n## Decide whether to create anything\n\nApply these before any creation step, including when the request already names\nthe new skill or file it wants:\n\n1. **Find the existing owner.** Search skills, references, checklists and\n   instruction files for one that already handles the behavior. Extend that\n   owner rather than adding a root.\n2. **Count independent occurrences.** A new skill, gate, library or workflow\n   needs three independently evidenced real occurrences and a successful\n   reapplication to a source case without missing context. Fewer occurrences\n   support only a narrow note in an existing owner; one incident is an\n   observation, not a skill. An authoritative source supports only a faithful\n   statement of that source.\n3. **Name the consumer of every new artifact.** A proposed process artifact\n   (a report, ledger, counter, dashboard or tracker) needs a concrete consumer,\n   the decision it informs, the observed defect it answers and a retirement\n   condition. If any is missing, leave it out; code written only to consume it\n   is no consumer.\n4. **No action is a valid result**, and so is a short addition to an existing\n   owner. Say what the evidence supports before drafting, build only what the\n   caller then authorizes, and return a proposal inline unless a durable one\n   was requested.\n5. **A built package proves no benefit.** Route behavioral benefit to\n   [Skill Eval](..\u002Fskill-eval\u002FSKILL.md) and acceptance judgment to\n   [Validate](..\u002Fvalidate\u002FSKILL.md).\n\nThe result shows it worked when it names the existing owner it searched, the\nnumber of independent occurrences found, and either no new file or exactly the\npackage the caller authorized.\n\n## Choose the requested operation\n\n`\u003Cskill-dir>` is the directory that contains this SKILL.md. Claude Code shows it\nas \"Base directory for this skill\"; Codex lists this skill's SKILL.md path; in\nan AgentOps source checkout it is `skills\u002Fskill-builder`. Replace `\u003Cskill-dir>`\nwith that absolute path before running a command. The working directory stays\nthe user's repository. If the host did not show where this skill is installed,\nuse the directory of the SKILL.md you read. If you cannot determine it, do not\nguess a path or run a same-named script from the current repository; say the\nbundled script is unavailable and apply the rules and doctrine here to the\npackage by hand and use its repository's own checks.\n\n| Need | Entry point | Runs only with |\n|---|---|---|\n| Create a source package | `bash \"\u003Cskill-dir>\u002Fscripts\u002Fbuild.sh\" from-scratch \u003Cslug>`, `from-template \u003Cslug> --like \u003Cexisting-slug>` or `absorb-external \u003Cslug> --from \u003Cpath>` | an AgentOps source checkout with Go |\n| Check package structure | `bash \"\u003Cskill-dir>\u002Fscripts\u002Fheal.sh\" --check [--strict] skills\u002F\u003Cslug>` | Go in a source checkout, or `ao` 3.9 or later elsewhere |\n| Repair the skill mesh | `bash \"\u003Cskill-dir>\u002Fscripts\u002Fheal.sh\" --fix skills\u002F\u003Cslug>` | an AgentOps source checkout with Go |\n| Inspect audit evidence | `bash \"\u003Cskill-dir>\u002Fscripts\u002Faudit.sh\" [--profile canonical\\|portable\\|external-observation] [--json \u003Cpath>] skills\u002F\u003Cslug>` | Go in a source checkout, or `ao` 3.9 or later elsewhere |\n| Merge overlapping skills | [Consolidate](#consolidate) | nothing bundled |\n| Export to another platform | [Conversion](#conversion) | Bash 4.3 or later |\n| Make repeated expertise reusable | [Distill expertise](#distill-expertise) | nothing bundled |\n\nRun only the selected operation. A plugin install ships these scripts but no\n`ao` binary or Go source: without `ao` on PATH, `audit.sh` exits 127 with\n`ao: not found` and `heal.sh` exits 2. Then apply the\n[source template](references\u002Fskill-template.md) and\n[authoring doctrine](references\u002Fauthoring-doctrine.md) by hand and use the\ntarget repository's own checks. `build.sh` and `heal.sh --fix` work on\n`skills\u002F` of an AgentOps source checkout and refuse with exit 2 elsewhere, such\nas from a plugin install, instead of writing into its cache; `heal.sh --fix`\nchecks the source first, so a target with findings exits 1 before that refusal.\n`heal.sh` in either mode checks only its own root's `skills\u002F` and resolves a\nrelative target there, not in the current directory. For a skill in another\nrepository or a user's skills directory, apply the rules and doctrine here to\nthat directory and use its own checks; with `ao` installed, `audit.sh` resolves\ntargets from the current directory and has `portable` and\n`external-observation` profiles, so it is the bundled check there.\nRoots, inputs, report destinations, exit codes and recovery from partial\ncreation are in [build and check mechanics](references\u002Fbuild-mechanics.md).\n\n## Create and maintain\n\nTreat external skills as structural signals only. Clean-room output must not\ncopy their names, prose, prompts, scripts or examples. Every creation mode\nwrites the same blank scaffold: `from-template` only checks the named skill and\nrecords it as `source_hint`, and `absorb-external` only verifies its input.\nNeither imports another skill's content or metadata.\n\n`build.sh` creates one incomplete source package containing only\n`SKILL.md` with `metadata.authoring_state: scaffold`; helpers, references and\nassets are conditional on the actual behavior. Replace the placeholders and\nstate applicability, inputs, authority, result, completion and failure in the\nlayout that makes them clear. An ending such as \"hand off\" or \"then stop\" can\nend the caller's turn when the skill runs inline; read\n[endings](references\u002Fauthoring-doctrine.md#state-authority-and-a-usable-failure-path)\nbefore writing one. Remove the scaffold state only after authoring the\nbehavior; strict source checks reject it. Removing it is an author assertion,\nnot proof of semantic completeness.\n\nBefore editing a skill after a miss or a review finding, read\n[changing existing text](references\u002Fauthoring-doctrine.md#change-existing-text-at-its-owning-layer);\nit decides when text stays unchanged, when a list stays explicit, and what to\ncheck before cutting a line.\n\nEdit `skills\u002F\u003Cslug>\u002F` as the source owner. Check the completed source with\n`bash \"\u003Cskill-dir>\u002Fscripts\u002Fheal.sh\" --check --strict skills\u002F\u003Cslug>`. In an\nAgentOps source checkout only, run `bash scripts\u002Fregen-all.sh` from the\nrepository root to regenerate every owned projection, including\n`plugin\u002Fskills\u002F`; `bash \"\u003Cskill-dir>\u002Fscripts\u002Fheal.sh\" --fix skills\u002F\u003Cslug>`\nregenerates only the skill mesh and leaves plugin copies unchanged. Inspect the\ngenerated diff; hand-edit no projection. A clean check says nothing about\nbehavior: when an edit changes\nwhen the skill routes, what it asks, when it stops, what it commits or\npublishes or how it degrades, or cuts a line that recorded provenance protects,\nreport that behavior as unmeasured unless a [Skill Eval](..\u002Fskill-eval\u002FSKILL.md)\nresult measured that behavior, and name what was missing (a runner, a host or\nthe caller's authorization). Typo, path and formatting edits need no such note.\n\nCreation is staged, not atomic. If a later stage fails, keep the created source\nand any report and follow [recovery](references\u002Fbuild-mechanics.md#staged-creation-and-recovery);\nnever call a partial result a completed package or delete it to rerun creation.\nA missing script, reference or runtime blocks only the operation that needs it;\nname it and continue the rest.\n\nThe default audit reports conformance, effects, behavior and authoring\nsuspicions separately, with no total or verdict; effects and behavior stay\n`NOT_PROVEN` because it runs no skill. Checks, exit codes and the opt-in legacy\nschema are in [audit checks](references\u002Faudit-checks.md); what Codex reads is in\n[Codex parity](references\u002Fcodex-parity.md).\n\n## Consolidate\n\nMerge only when two skills own the same behavior; a shared passage or two is a\ncross-link, not a merge. Apply the decision rules above, then pick one owner:\nkeep the skill with the stronger contract (clearer applicability, authority,\nresult and failure path) and move into it only the rules the other has and it\nlacks. Before retiring the other name, search the skills, references,\ninstruction files, goal prompts, workflows and docs for callers that invoke it\nby name, point each at the owner, and keep the old name until every caller does.\nIn the AgentOps repository, also record the retired name and its new owner in\n`docs\u002FMIGRATION.md` and add the slug to `REMOVED_SKILLS` in\n`scripts\u002Fcheck-cathedral-cut-conformance.py`, which fails if the skill comes\nback; never delete a skill there without that tombstone. A merge can move\nrouting, so report as unmeasured whether the requests the retired skill caught\nnow reach the owner unless a routing or [Skill Eval](..\u002Fskill-eval\u002FSKILL.md)\nresult measured it.\n\n## Conversion\n\nRun `bash \"\u003Cskill-dir>\u002Fscripts\u002Fconverter\u002Fconvert.sh\" \u003Csource-skill-dir> \u003Ctarget>\n[output-dir]` to export one package, or `--all`, to `codex`, `cursor` or `test`\noutside the shipped tree. Before an export, read\n[running the converter](references\u002Fconverter\u002Fskill-bundle-schema.md#run-the-converter)\nfor path resolution, the default output and its refusals. Preserve the source;\nfix the source or adapter, never the exported output.\n\n## Distill expertise\n\nWhen the caller wants a reusable rule, apply the decision rules above and begin\nwith cited occurrences or a named authoritative source. State the trigger,\ndesired behavior, inputs, outputs, limits and a negative or holdout case the\nrule decides correctly, with short source excerpts and resolvable citations.\nUse Research's [pattern mode](..\u002Fresearch\u002FSKILL.md#pattern-evidence) when the\nclaim needs exemplars and a holdout, and\n[Memory's source and destination rules](..\u002Fmemory\u002FSKILL.md) for mined material.\nA proposal-only request ends with the proposal. For an actual package edit, use\nthe [source template](references\u002Fskill-template.md) for required fields and the\nadmission test in [changing existing text](references\u002Fauthoring-doctrine.md#change-existing-text-at-its-owning-layer)\nto decide which prose earns a place.\n",{"name":5,"consumes":50,"metadata":51,"produces":69,"practices":74,"context_rel":76,"description":7,"hexagonal_role":77,"user-invocable":78,"output_contract":79,"skill_api_version":80},[],{"tier":52,"effects":53,"stability":60,"disposition":61,"capabilities":62,"dependencies":67,"canonical_status":68},"meta",[54,55,56,57,58,59],"write_skill_source","write_build_report","regenerate_skill_projections","repair_skill_projections","write_converted_skill_projection","write_advisory_proposal","experimental","keep_specialist",[63,64,65,66],"skill_builder","heal_skill","export_skill","distill_expertise",[],"canonical",[70,71,72,73],"skill-source-package","skill-hygiene-report","converted-skill","operationalization-proposal",[75,38],"pragmatic-programmer",[],"supporting",true,"build-report.json for creation, audit-report.json for audit, target-valid exported files for conversion, or an advisory expertise proposal",1,"main","347aedf8480cd92b21f761e97b7343a45898f5fa","plugins\u002Fboshu2\u002Fagentops\u002Fskills\u002Fskill-builder",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":92,"prompt":102,"zipAvailable":78},[93,96,99],{"tool":94,"command":95},"npx","npx skills add hashgraph-online\u002Fawesome-codex-plugins --skill skill-builder",{"tool":97,"command":98},"bunx","bunx skills add hashgraph-online\u002Fawesome-codex-plugins --skill skill-builder",{"tool":100,"command":101},"pnpm","pnpm dlx skills add hashgraph-online\u002Fawesome-codex-plugins --skill skill-builder","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Fhashgraph-online\u002Fawesome-codex-plugins\u002Fblob\u002Fmain\u002Fplugins\u002Fboshu2\u002Fagentops\u002Fskills\u002Fskill-builder\u002FSKILL.md",[104,110,114,118,122,126,130,134,138,142,146,150,154,158,164,168,172,176,180,184,188,192,196,200,204,208,212,216,220,224],{"path":105,"resourceType":106,"resourceTypeDesc":107,"sizeBytes":108,"sourceHtmlUrl":109},"references\u002Faudit-checks.md","REFERENCE","参考文档",4250,"https:\u002F\u002Fgithub.com\u002Fhashgraph-online\u002Fawesome-codex-plugins\u002Fblob\u002Fmain\u002Fplugins\u002Fboshu2\u002Fagentops\u002Fskills\u002Fskill-builder\u002Freferences\u002Faudit-checks.md",{"path":111,"resourceType":106,"resourceTypeDesc":107,"sizeBytes":112,"sourceHtmlUrl":113},"references\u002Fauthoring-doctrine.md",12060,"https:\u002F\u002Fgithub.com\u002Fhashgraph-online\u002Fawesome-codex-plugins\u002Fblob\u002Fmain\u002Fplugins\u002Fboshu2\u002Fagentops\u002Fskills\u002Fskill-builder\u002Freferences\u002Fauthoring-doctrine.md",{"path":115,"resourceType":106,"resourceTypeDesc":107,"sizeBytes":116,"sourceHtmlUrl":117},"references\u002Fbuild-mechanics.md",5101,"https:\u002F\u002Fgithub.com\u002Fhashgraph-online\u002Fawesome-codex-plugins\u002Fblob\u002Fmain\u002Fplugins\u002Fboshu2\u002Fagentops\u002Fskills\u002Fskill-builder\u002Freferences\u002Fbuild-mechanics.md",{"path":119,"resourceType":106,"resourceTypeDesc":107,"sizeBytes":120,"sourceHtmlUrl":121},"references\u002Fcodex-parity.md",2398,"https:\u002F\u002Fgithub.com\u002Fhashgraph-online\u002Fawesome-codex-plugins\u002Fblob\u002Fmain\u002Fplugins\u002Fboshu2\u002Fagentops\u002Fskills\u002Fskill-builder\u002Freferences\u002Fcodex-parity.md",{"path":123,"resourceType":106,"resourceTypeDesc":107,"sizeBytes":124,"sourceHtmlUrl":125},"references\u002Fconverter\u002Fskill-bundle-schema.md",4654,"https:\u002F\u002Fgithub.com\u002Fhashgraph-online\u002Fawesome-codex-plugins\u002Fblob\u002Fmain\u002Fplugins\u002Fboshu2\u002Fagentops\u002Fskills\u002Fskill-builder\u002Freferences\u002Fconverter\u002Fskill-bundle-schema.md",{"path":127,"resourceType":106,"resourceTypeDesc":107,"sizeBytes":128,"sourceHtmlUrl":129},"references\u002Fheal.feature",1104,"https:\u002F\u002Fgithub.com\u002Fhashgraph-online\u002Fawesome-codex-plugins\u002Fblob\u002Fmain\u002Fplugins\u002Fboshu2\u002Fagentops\u002Fskills\u002Fskill-builder\u002Freferences\u002Fheal.feature",{"path":131,"resourceType":106,"resourceTypeDesc":107,"sizeBytes":132,"sourceHtmlUrl":133},"references\u002Fskill-auditor.feature",2121,"https:\u002F\u002Fgithub.com\u002Fhashgraph-online\u002Fawesome-codex-plugins\u002Fblob\u002Fmain\u002Fplugins\u002Fboshu2\u002Fagentops\u002Fskills\u002Fskill-builder\u002Freferences\u002Fskill-auditor.feature",{"path":135,"resourceType":106,"resourceTypeDesc":107,"sizeBytes":136,"sourceHtmlUrl":137},"references\u002Fskill-builder.feature",1883,"https:\u002F\u002Fgithub.com\u002Fhashgraph-online\u002Fawesome-codex-plugins\u002Fblob\u002Fmain\u002Fplugins\u002Fboshu2\u002Fagentops\u002Fskills\u002Fskill-builder\u002Freferences\u002Fskill-builder.feature",{"path":139,"resourceType":106,"resourceTypeDesc":107,"sizeBytes":140,"sourceHtmlUrl":141},"references\u002Fskill-conformance-profiles.yaml",4604,"https:\u002F\u002Fgithub.com\u002Fhashgraph-online\u002Fawesome-codex-plugins\u002Fblob\u002Fmain\u002Fplugins\u002Fboshu2\u002Fagentops\u002Fskills\u002Fskill-builder\u002Freferences\u002Fskill-conformance-profiles.yaml",{"path":143,"resourceType":106,"resourceTypeDesc":107,"sizeBytes":144,"sourceHtmlUrl":145},"references\u002Fskill-template.md",2120,"https:\u002F\u002Fgithub.com\u002Fhashgraph-online\u002Fawesome-codex-plugins\u002Fblob\u002Fmain\u002Fplugins\u002Fboshu2\u002Fagentops\u002Fskills\u002Fskill-builder\u002Freferences\u002Fskill-template.md",{"path":147,"resourceType":106,"resourceTypeDesc":107,"sizeBytes":148,"sourceHtmlUrl":149},"schemas\u002Faudit-report-legacy.json",17816,"https:\u002F\u002Fgithub.com\u002Fhashgraph-online\u002Fawesome-codex-plugins\u002Fblob\u002Fmain\u002Fplugins\u002Fboshu2\u002Fagentops\u002Fskills\u002Fskill-builder\u002Fschemas\u002Faudit-report-legacy.json",{"path":151,"resourceType":106,"resourceTypeDesc":107,"sizeBytes":152,"sourceHtmlUrl":153},"schemas\u002Faudit-report.json",5576,"https:\u002F\u002Fgithub.com\u002Fhashgraph-online\u002Fawesome-codex-plugins\u002Fblob\u002Fmain\u002Fplugins\u002Fboshu2\u002Fagentops\u002Fskills\u002Fskill-builder\u002Fschemas\u002Faudit-report.json",{"path":155,"resourceType":106,"resourceTypeDesc":107,"sizeBytes":156,"sourceHtmlUrl":157},"schemas\u002Fbuild-report.json",765,"https:\u002F\u002Fgithub.com\u002Fhashgraph-online\u002Fawesome-codex-plugins\u002Fblob\u002Fmain\u002Fplugins\u002Fboshu2\u002Fagentops\u002Fskills\u002Fskill-builder\u002Fschemas\u002Fbuild-report.json",{"path":159,"resourceType":160,"resourceTypeDesc":161,"sizeBytes":162,"sourceHtmlUrl":163},"scripts\u002Faudit-legacy.sh","SCRIPT","脚本",18130,"https:\u002F\u002Fgithub.com\u002Fhashgraph-online\u002Fawesome-codex-plugins\u002Fblob\u002Fmain\u002Fplugins\u002Fboshu2\u002Fagentops\u002Fskills\u002Fskill-builder\u002Fscripts\u002Faudit-legacy.sh",{"path":165,"resourceType":160,"resourceTypeDesc":161,"sizeBytes":166,"sourceHtmlUrl":167},"scripts\u002Faudit.sh",941,"https:\u002F\u002Fgithub.com\u002Fhashgraph-online\u002Fawesome-codex-plugins\u002Fblob\u002Fmain\u002Fplugins\u002Fboshu2\u002Fagentops\u002Fskills\u002Fskill-builder\u002Fscripts\u002Faudit.sh",{"path":169,"resourceType":160,"resourceTypeDesc":161,"sizeBytes":170,"sourceHtmlUrl":171},"scripts\u002Fauthoring_scan.py",7310,"https:\u002F\u002Fgithub.com\u002Fhashgraph-online\u002Fawesome-codex-plugins\u002Fblob\u002Fmain\u002Fplugins\u002Fboshu2\u002Fagentops\u002Fskills\u002Fskill-builder\u002Fscripts\u002Fauthoring_scan.py",{"path":173,"resourceType":160,"resourceTypeDesc":161,"sizeBytes":174,"sourceHtmlUrl":175},"scripts\u002Fbuild.sh",1249,"https:\u002F\u002Fgithub.com\u002Fhashgraph-online\u002Fawesome-codex-plugins\u002Fblob\u002Fmain\u002Fplugins\u002Fboshu2\u002Fagentops\u002Fskills\u002Fskill-builder\u002Fscripts\u002Fbuild.sh",{"path":177,"resourceType":160,"resourceTypeDesc":161,"sizeBytes":178,"sourceHtmlUrl":179},"scripts\u002Fconformance_profile.py",18381,"https:\u002F\u002Fgithub.com\u002Fhashgraph-online\u002Fawesome-codex-plugins\u002Fblob\u002Fmain\u002Fplugins\u002Fboshu2\u002Fagentops\u002Fskills\u002Fskill-builder\u002Fscripts\u002Fconformance_profile.py",{"path":181,"resourceType":160,"resourceTypeDesc":161,"sizeBytes":182,"sourceHtmlUrl":183},"scripts\u002Fconverter\u002Fconvert.sh",25810,"https:\u002F\u002Fgithub.com\u002Fhashgraph-online\u002Fawesome-codex-plugins\u002Fblob\u002Fmain\u002Fplugins\u002Fboshu2\u002Fagentops\u002Fskills\u002Fskill-builder\u002Fscripts\u002Fconverter\u002Fconvert.sh",{"path":185,"resourceType":160,"resourceTypeDesc":161,"sizeBytes":186,"sourceHtmlUrl":187},"scripts\u002Fconverter\u002Fvalidate.sh",4445,"https:\u002F\u002Fgithub.com\u002Fhashgraph-online\u002Fawesome-codex-plugins\u002Fblob\u002Fmain\u002Fplugins\u002Fboshu2\u002Fagentops\u002Fskills\u002Fskill-builder\u002Fscripts\u002Fconverter\u002Fvalidate.sh",{"path":189,"resourceType":160,"resourceTypeDesc":161,"sizeBytes":190,"sourceHtmlUrl":191},"scripts\u002Fcraft_score.py",12354,"https:\u002F\u002Fgithub.com\u002Fhashgraph-online\u002Fawesome-codex-plugins\u002Fblob\u002Fmain\u002Fplugins\u002Fboshu2\u002Fagentops\u002Fskills\u002Fskill-builder\u002Fscripts\u002Fcraft_score.py",{"path":193,"resourceType":160,"resourceTypeDesc":161,"sizeBytes":194,"sourceHtmlUrl":195},"scripts\u002Fheal.sh",2149,"https:\u002F\u002Fgithub.com\u002Fhashgraph-online\u002Fawesome-codex-plugins\u002Fblob\u002Fmain\u002Fplugins\u002Fboshu2\u002Fagentops\u002Fskills\u002Fskill-builder\u002Fscripts\u002Fheal.sh",{"path":197,"resourceType":160,"resourceTypeDesc":161,"sizeBytes":198,"sourceHtmlUrl":199},"scripts\u002Finit.sh",518,"https:\u002F\u002Fgithub.com\u002Fhashgraph-online\u002Fawesome-codex-plugins\u002Fblob\u002Fmain\u002Fplugins\u002Fboshu2\u002Fagentops\u002Fskills\u002Fskill-builder\u002Fscripts\u002Finit.sh",{"path":201,"resourceType":160,"resourceTypeDesc":161,"sizeBytes":202,"sourceHtmlUrl":203},"scripts\u002Frun-ao.sh",752,"https:\u002F\u002Fgithub.com\u002Fhashgraph-online\u002Fawesome-codex-plugins\u002Fblob\u002Fmain\u002Fplugins\u002Fboshu2\u002Fagentops\u002Fskills\u002Fskill-builder\u002Fscripts\u002Frun-ao.sh",{"path":205,"resourceType":160,"resourceTypeDesc":161,"sizeBytes":206,"sourceHtmlUrl":207},"scripts\u002Fscan_descriptions.py",21746,"https:\u002F\u002Fgithub.com\u002Fhashgraph-online\u002Fawesome-codex-plugins\u002Fblob\u002Fmain\u002Fplugins\u002Fboshu2\u002Fagentops\u002Fskills\u002Fskill-builder\u002Fscripts\u002Fscan_descriptions.py",{"path":209,"resourceType":160,"resourceTypeDesc":161,"sizeBytes":210,"sourceHtmlUrl":211},"scripts\u002Fscore_agentops_skill.py",12324,"https:\u002F\u002Fgithub.com\u002Fhashgraph-online\u002Fawesome-codex-plugins\u002Fblob\u002Fmain\u002Fplugins\u002Fboshu2\u002Fagentops\u002Fskills\u002Fskill-builder\u002Fscripts\u002Fscore_agentops_skill.py",{"path":213,"resourceType":160,"resourceTypeDesc":161,"sizeBytes":214,"sourceHtmlUrl":215},"scripts\u002Ftest-authoring-mutations.sh",3353,"https:\u002F\u002Fgithub.com\u002Fhashgraph-online\u002Fawesome-codex-plugins\u002Fblob\u002Fmain\u002Fplugins\u002Fboshu2\u002Fagentops\u002Fskills\u002Fskill-builder\u002Fscripts\u002Ftest-authoring-mutations.sh",{"path":217,"resourceType":160,"resourceTypeDesc":161,"sizeBytes":218,"sourceHtmlUrl":219},"scripts\u002Ftest-craft-mutations.sh",3210,"https:\u002F\u002Fgithub.com\u002Fhashgraph-online\u002Fawesome-codex-plugins\u002Fblob\u002Fmain\u002Fplugins\u002Fboshu2\u002Fagentops\u002Fskills\u002Fskill-builder\u002Fscripts\u002Ftest-craft-mutations.sh",{"path":221,"resourceType":160,"resourceTypeDesc":161,"sizeBytes":222,"sourceHtmlUrl":223},"scripts\u002Ftest-mutation-boundaries.sh",2537,"https:\u002F\u002Fgithub.com\u002Fhashgraph-online\u002Fawesome-codex-plugins\u002Fblob\u002Fmain\u002Fplugins\u002Fboshu2\u002Fagentops\u002Fskills\u002Fskill-builder\u002Fscripts\u002Ftest-mutation-boundaries.sh",{"path":225,"resourceType":160,"resourceTypeDesc":161,"sizeBytes":226,"sourceHtmlUrl":227},"scripts\u002Fvalidate.sh",3853,"https:\u002F\u002Fgithub.com\u002Fhashgraph-online\u002Fawesome-codex-plugins\u002Fblob\u002Fmain\u002Fplugins\u002Fboshu2\u002Fagentops\u002Fskills\u002Fskill-builder\u002Fscripts\u002Fvalidate.sh",[229,239,247,255,263,271],{"skillNo":230,"name":231,"nameZh":6,"description":232,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":233,"licenseFileUrl":234,"sourceHtmlUrl":235,"categories":236,"keywords":237,"publishedAt":238},"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":240,"name":241,"nameZh":6,"description":242,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":233,"licenseFileUrl":243,"sourceHtmlUrl":244,"categories":245,"keywords":246,"publishedAt":238},"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":248,"name":249,"nameZh":6,"description":250,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":233,"licenseFileUrl":251,"sourceHtmlUrl":252,"categories":253,"keywords":254,"publishedAt":238},"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":256,"name":257,"nameZh":6,"description":258,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":233,"licenseFileUrl":259,"sourceHtmlUrl":260,"categories":261,"keywords":262,"publishedAt":238},"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":264,"name":265,"nameZh":6,"description":266,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":233,"licenseFileUrl":267,"sourceHtmlUrl":268,"categories":269,"keywords":270,"publishedAt":238},"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":272,"name":273,"nameZh":6,"description":274,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":233,"licenseFileUrl":275,"sourceHtmlUrl":276,"categories":277,"keywords":278,"publishedAt":238},"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",[],[]]