[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M6JVT9M2JH7YNABFNHE6FE0T":3,"skill-same:01M6JVT9M2JH7YNABFNHE6FE0T":73},{"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":28,"publishedAt":38,"linkOnly":39,"markdownContent":40,"markdownBody":41,"frontMatter":42,"refName":43,"commitSha":44,"skillDirectory":45,"forksCount":46,"repositoryHtmlUrl":47,"repositoryHomepageUrl":48,"ownerHtmlUrl":49,"ownerBlogUrl":50,"ownerDescription":51,"updatedAt":52,"install":53,"resources":66},"01M6JVT9M2JH7YNABFNHE6FE0T","writing-skills",null,"Use when creating new skills, editing existing skills, or verifying skills work before deployment","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\u002FGanyuanRan\u002FAegis\u002Fskills\u002Fwriting-skills\u002FSKILL.md",[18,23],{"categoryNo":19,"categoryName":20,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000018","写作与文案","SCENARIO","使用场景",{"categoryNo":24,"categoryName":25,"taxonomyType":26,"taxonomyTypeDesc":27},"01JBSEEDCAT000000000000036","内容创作者","PROFESSION","适用职业",[29,30,31,32,33,34,35,36,37],"writing","writing skills","deployment","work","editing","use","Existing","when","new","2026-11-10 10:12:30",false,"---\nname: writing-skills\ndescription: \"Use when creating new skills, editing existing skills, or verifying skills work before deployment\"\n---\n\n# Writing Skills\n\n## Purpose\n\nCreate the smallest reusable skill that changes decisions or improves task\nexecution without constraining unrelated work. Skill changes use behavior\nvalidation, not a code TDD route. This validation does not require loading `aegis:test-driven-development`.\n\n## Default Path\n\n### 1. Establish Need And Ownership\n\n- Name the reusable behavior gap, intended users\u002Fhosts, and non-goals.\n- Check whether an existing skill, project rule, host adapter, or automated\n  check already owns it. Prefer the smallest existing owner.\n- For an existing skill, inspect its references, manifests or generated copies,\n  discovery tests, and bundled resources before changing or retiring them.\n- Create a skill only for reusable, non-obvious guidance. Keep one-off project\n  conventions in the project owner and automate mechanical constraints when\n  practical.\n\n### 2. Record Behavior Before Editing\n\nUse representative tasks, not questions that merely ask the agent to recite\ninstructions.\n\n- New skill: run a no-skill control.\n- For an existing skill, run the current version first; add a no-skill ablation\n  only when testing whether the skill itself needs to exist.\n- Cover positive triggers, negative near-misses, and a pressure or application\n  case appropriate to the skill type.\n- Record decisions, missed or extra invocations, unsafe workarounds, evidence\n  references, and unknowns. Do not treat line or byte counts as behavior proof.\n\nIf meaningful behavior cannot be evaluated, stop at `needs-verification`; do\nnot claim that the skill is deployment-ready or capability-preserving.\n\n### 3. Design The Minimum Instruction Surface\n\n- Assume the agent is capable. Include only non-obvious context, decision\n  criteria, safety boundaries, and steps whose omission caused an observed gap.\n- Match specificity to risk: allow judgment for open work; use exact sequences\n  only for fragile, permission-sensitive, or safety-critical operations.\n- Keep the description concise, third-person, and discriminating. State the\n  capability and when it applies; add an exclusion only when it prevents likely\n  misrouting. Do not turn the description into a procedural shortcut.\n- Keep the executable default path and non-omittable constraints in `SKILL.md`.\n  Move substantial conditional detail to a direct reference and state the\n  evidence trigger for reading it.\n- Keep references one level deep where practical. Do not load every reference\n  by default or duplicate its content in the main body.\n- Add an example only when it materially stabilizes a decision or output. One\n  representative example is normally enough.\n- Keep portable method instructions host-neutral. Put host tool names, install\n  paths, and UI choreography in their host-owned documentation.\n\nThe canonical repository shape is `skills\u002F\u003Cskill-name>\u002FSKILL.md` with only the\nsupporting references, scripts, or assets the workflow actually uses. Use the\nrepository's host docs or the target host's live specification for optional\nmetadata instead of copying a vendor manual into the skill.\n\n### 4. Make The Smallest Change\n\nAddress observed gaps and remove superseded duplication in the same slice.\nPreserve public attribution and any externally supported contract. When\nretiring an internal owner, fallback, or resource, compose\n`aegis:anti-entropy-governance`; do not leave a compatibility copy without\ndependency evidence.\n\nDo not convert one model's phrasing, one historical incident, or a hypothetical\nedge case into a universal rule.\n\n### 5. Validate The Candidate\n\nRe-run the same positive, negative, and pressure\u002Fapplication scenarios under a\ncomparable model, tool, and host configuration. Compare outcomes, not wording.\n\nAlso verify:\n\n- frontmatter, name, and description parse on supported hosts;\n- intended requests still discover the skill and near-misses do not;\n- every conditional reference is reachable from an explicit trigger;\n- changed scripts run successfully;\n- retired files and instructions have no live references;\n- repository workflow, boundary, packaging, and host checks relevant to the\n  touched surface pass.\n\nIf behavior regresses, restore the missing obligation or narrow the change;\ndo not add a second owner or fallback to mask it.\n\n## Scenario Selection\n\n| Skill type | Representative evidence |\n| --- | --- |\n| Discipline or safety | realistic pressure and authorization boundaries |\n| Technique | application, variation, and missing-information cases |\n| Pattern | recognition, application, and counter-example cases |\n| Reference | retrieval, correct use, and common-gap cases |\n\nFor a complex or high-risk skill where an independent evaluator adds confidence,\nread `testing-skills-with-subagents.md`.\n\n## Completion Record\n\nKeep the result compact and auditable in natural prose or equivalent fields:\n\n- behavior gap and canonical owner;\n- baseline and candidate scenario results;\n- retained and retired obligations\u002Fresources;\n- trigger and reference checks;\n- verification commands and uncovered hosts\u002Fmodels;\n- status: `verified`, `needs-verification`, or `blocked`.\n\nThis is method-pack evidence, not authoritative completion or deployment\napproval.\n","# Writing Skills\n\n## Purpose\n\nCreate the smallest reusable skill that changes decisions or improves task\nexecution without constraining unrelated work. Skill changes use behavior\nvalidation, not a code TDD route. This validation does not require loading `aegis:test-driven-development`.\n\n## Default Path\n\n### 1. Establish Need And Ownership\n\n- Name the reusable behavior gap, intended users\u002Fhosts, and non-goals.\n- Check whether an existing skill, project rule, host adapter, or automated\n  check already owns it. Prefer the smallest existing owner.\n- For an existing skill, inspect its references, manifests or generated copies,\n  discovery tests, and bundled resources before changing or retiring them.\n- Create a skill only for reusable, non-obvious guidance. Keep one-off project\n  conventions in the project owner and automate mechanical constraints when\n  practical.\n\n### 2. Record Behavior Before Editing\n\nUse representative tasks, not questions that merely ask the agent to recite\ninstructions.\n\n- New skill: run a no-skill control.\n- For an existing skill, run the current version first; add a no-skill ablation\n  only when testing whether the skill itself needs to exist.\n- Cover positive triggers, negative near-misses, and a pressure or application\n  case appropriate to the skill type.\n- Record decisions, missed or extra invocations, unsafe workarounds, evidence\n  references, and unknowns. Do not treat line or byte counts as behavior proof.\n\nIf meaningful behavior cannot be evaluated, stop at `needs-verification`; do\nnot claim that the skill is deployment-ready or capability-preserving.\n\n### 3. Design The Minimum Instruction Surface\n\n- Assume the agent is capable. Include only non-obvious context, decision\n  criteria, safety boundaries, and steps whose omission caused an observed gap.\n- Match specificity to risk: allow judgment for open work; use exact sequences\n  only for fragile, permission-sensitive, or safety-critical operations.\n- Keep the description concise, third-person, and discriminating. State the\n  capability and when it applies; add an exclusion only when it prevents likely\n  misrouting. Do not turn the description into a procedural shortcut.\n- Keep the executable default path and non-omittable constraints in `SKILL.md`.\n  Move substantial conditional detail to a direct reference and state the\n  evidence trigger for reading it.\n- Keep references one level deep where practical. Do not load every reference\n  by default or duplicate its content in the main body.\n- Add an example only when it materially stabilizes a decision or output. One\n  representative example is normally enough.\n- Keep portable method instructions host-neutral. Put host tool names, install\n  paths, and UI choreography in their host-owned documentation.\n\nThe canonical repository shape is `skills\u002F\u003Cskill-name>\u002FSKILL.md` with only the\nsupporting references, scripts, or assets the workflow actually uses. Use the\nrepository's host docs or the target host's live specification for optional\nmetadata instead of copying a vendor manual into the skill.\n\n### 4. Make The Smallest Change\n\nAddress observed gaps and remove superseded duplication in the same slice.\nPreserve public attribution and any externally supported contract. When\nretiring an internal owner, fallback, or resource, compose\n`aegis:anti-entropy-governance`; do not leave a compatibility copy without\ndependency evidence.\n\nDo not convert one model's phrasing, one historical incident, or a hypothetical\nedge case into a universal rule.\n\n### 5. Validate The Candidate\n\nRe-run the same positive, negative, and pressure\u002Fapplication scenarios under a\ncomparable model, tool, and host configuration. Compare outcomes, not wording.\n\nAlso verify:\n\n- frontmatter, name, and description parse on supported hosts;\n- intended requests still discover the skill and near-misses do not;\n- every conditional reference is reachable from an explicit trigger;\n- changed scripts run successfully;\n- retired files and instructions have no live references;\n- repository workflow, boundary, packaging, and host checks relevant to the\n  touched surface pass.\n\nIf behavior regresses, restore the missing obligation or narrow the change;\ndo not add a second owner or fallback to mask it.\n\n## Scenario Selection\n\n| Skill type | Representative evidence |\n| --- | --- |\n| Discipline or safety | realistic pressure and authorization boundaries |\n| Technique | application, variation, and missing-information cases |\n| Pattern | recognition, application, and counter-example cases |\n| Reference | retrieval, correct use, and common-gap cases |\n\nFor a complex or high-risk skill where an independent evaluator adds confidence,\nread `testing-skills-with-subagents.md`.\n\n## Completion Record\n\nKeep the result compact and auditable in natural prose or equivalent fields:\n\n- behavior gap and canonical owner;\n- baseline and candidate scenario results;\n- retained and retired obligations\u002Fresources;\n- trigger and reference checks;\n- verification commands and uncovered hosts\u002Fmodels;\n- status: `verified`, `needs-verification`, or `blocked`.\n\nThis is method-pack evidence, not authoritative completion or deployment\napproval.\n",{"name":5,"description":7},"main","b0f0a87593c578a7898eccaf1b363f7f87c1f99b","plugins\u002FGanyuanRan\u002FAegis\u002Fskills\u002Fwriting-skills",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":54,"prompt":64,"zipAvailable":65},[55,58,61],{"tool":56,"command":57},"npx","npx skills add hashgraph-online\u002Fawesome-codex-plugins --skill writing-skills",{"tool":59,"command":60},"bunx","bunx skills add hashgraph-online\u002Fawesome-codex-plugins --skill writing-skills",{"tool":62,"command":63},"pnpm","pnpm dlx skills add hashgraph-online\u002Fawesome-codex-plugins --skill writing-skills","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Fhashgraph-online\u002Fawesome-codex-plugins\u002Fblob\u002Fmain\u002Fplugins\u002FGanyuanRan\u002FAegis\u002Fskills\u002Fwriting-skills\u002FSKILL.md",true,[67],{"path":68,"resourceType":69,"resourceTypeDesc":70,"sizeBytes":71,"sourceHtmlUrl":72},"testing-skills-with-subagents.md","REFERENCE","参考文档",2801,"https:\u002F\u002Fgithub.com\u002Fhashgraph-online\u002Fawesome-codex-plugins\u002Fblob\u002Fmain\u002Fplugins\u002FGanyuanRan\u002FAegis\u002Fskills\u002Fwriting-skills\u002Ftesting-skills-with-subagents.md",[74,84,92,100,108,116],{"skillNo":75,"name":76,"nameZh":6,"description":77,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":78,"licenseFileUrl":79,"sourceHtmlUrl":80,"categories":81,"keywords":82,"publishedAt":83},"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":85,"name":86,"nameZh":6,"description":87,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":78,"licenseFileUrl":88,"sourceHtmlUrl":89,"categories":90,"keywords":91,"publishedAt":83},"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":93,"name":94,"nameZh":6,"description":95,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":78,"licenseFileUrl":96,"sourceHtmlUrl":97,"categories":98,"keywords":99,"publishedAt":83},"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":101,"name":102,"nameZh":6,"description":103,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":78,"licenseFileUrl":104,"sourceHtmlUrl":105,"categories":106,"keywords":107,"publishedAt":83},"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":109,"name":110,"nameZh":6,"description":111,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":78,"licenseFileUrl":112,"sourceHtmlUrl":113,"categories":114,"keywords":115,"publishedAt":83},"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":117,"name":118,"nameZh":6,"description":119,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":78,"licenseFileUrl":120,"sourceHtmlUrl":121,"categories":122,"keywords":123,"publishedAt":83},"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",[],[]]