[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M71FVR5S99QBPWVAAXMSC1GY":3,"skill-same:01M71FVR5S99QBPWVAAXMSC1GY":99},{"skillNo":4,"name":5,"nameZh":6,"description":7,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":16,"categories":17,"keywords":18,"publishedAt":39,"linkOnly":40,"markdownContent":41,"markdownBody":42,"frontMatter":43,"refName":47,"commitSha":48,"skillDirectory":49,"forksCount":14,"repositoryHtmlUrl":50,"repositoryHomepageUrl":6,"ownerHtmlUrl":51,"ownerBlogUrl":52,"ownerDescription":53,"updatedAt":54,"install":55,"resources":68},"01M71FVR5S99QBPWVAAXMSC1GY","author-subagent",null,"ALWAYS invoke this skill when creating, editing, or configuring {{! term('configured_agents') !}}. NEVER create {{! term('configured_agents') !}} without this skill.","outcomeeng\u002Fplugins","outcomeeng","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F257335685?v=4","01M71FRVRF36XYR3HRSCGFHK2R","Outcome Engineering","01M71FRVS4BZG17DWANFJ7EPNY",1,"MIT","https:\u002F\u002Fgithub.com\u002Foutcomeeng\u002Fplugins\u002Fblob\u002Fmain\u002Fsrc\u002Fplugins\u002Finstructions\u002Fskills\u002Fauthor-subagent\u002FSKILL.md",[],[19,20,21,22,23,24,25,26,27,28,29,30,31,32,33,34,35,36,37,38],"subagent","author","author subagent","path","Bash","configuration","when","role","invoke","use","input","edit","write","tool","read","editing","never","repair","target","create","2026-11-10 10:12:30",false,"---\nname: author-subagent\ndescription: >-\n  ALWAYS invoke this skill when creating, editing, or configuring {{! term('configured_agents') !}}.\n  NEVER create {{! term('configured_agents') !}} without this skill.\nargument-hint: \"\u003Cconfiguration-path-or-role> [repair-input]\"\narguments: configuration_target\nallowed-tools: Read, Glob, Write, Edit, Bash, {{! tool('use_skill') !}}\n---\n\n{!% require_skill 'instructions:subagent-standards' %!}\n\n{!% require_skill 'instructions:agent-prompt-standards' %!}\n\n{!% require_skill 'instructions:skill-standards' %!}\n\n\u003Cobjective>\nA finished {{! term('configured_agent') !}} definition and its calling-skill integration,\nready for independent verification, with native configuration and a declared result contract.\n\u003C\u002Fobjective>\n\n\u003Cconstraints>\n\n- ALWAYS: apply every rule in the `\u002Fsubagent-standards` and `\u002Fagent-prompt-standards` rule\n  catalogs to the finished definition, and return it ready for independent verification once\n  the product's author command and deterministic checks pass on it.\n- NEVER: dispatch a {{! term('configured_agent') !}} auditor or wait on an audit verdict — a\n  verdict on the definition comes from `\u002Faudit-subagent` run in an agent session separate from\n  the one that authored it.\n- ALWAYS: write to the invocation checkout. Reach a user-scope destination outside it —\n  creating, editing, or deleting — only after the operator confirms the exact absolute\n  destination; one approval covers one write.\n- NEVER: widen an approved checkout-scope write to user scope on the judgment that the\n  configured agent suits other projects.\n\n\u003C\u002Fconstraints>\n\n\u003Cintake>\n\nSelect the route from the task message:\n\n| Task message carries                                                                                   | Route                    |\n| ------------------------------------------------------------------------------------------------------ | ------------------------ |\n| A target path or role only                                                                             | `\u003Cworkflow>`             |\n| A target followed by a sealed run file and the instruction to attend to every rule the run names       | `\u003Crepair_from_run_file>` |\n| A target followed by the command line and complete output of a deterministic command that failed on it | `\u003Crepair_from_command>`  |\n\n\u003C\u002Fintake>\n\n\u003Cworkflow>\n\n1. Require `$configuration_target`. When it is empty, return a `blocked` result naming the\n   missing configuration path or role. Read the requested target and its governing requirements. Identify the role's\n   owning skill, exact configured name, destination, selected profile, and result.\n   Return a `blocked` result naming the missing input when a product decision or a required\n   input is absent. When the definition already holds the requested result, return an\n   `unchanged` result naming the committed head and the path that holds it, and edit nothing.\n2. Apply `\u002Fsubagent-standards` to placement, capabilities, profiles, isolation,\n   invocation, and evidence. Read the relevant references from the index below.\n3. For a skill-backed role, author a thin wrapper that invokes the owning skill\n   and relays its result. Keep task-specific behavior in that skill.\n4. For a marketplace source, declare `profile: standard`, `profile: strong`,\n   `profile: executor`, or `profile: fast` according to the governing selection. Let the product build\n   emit the complete native configuration. For a product-owned native definition,\n   use the selected complete configuration supplied by the loaded standards and examples.\n5. Use skill `instructions:author-skill`. Update the calling skill through it so its\n   explicit launch names the configured role and supplies only the target.\n6. Run the product's author command, then apply `\u002Fsubagent-standards` `\u003Cconfiguration_subject>`\n   to identify the authored input and exact emitted definitions, or the directly authored\n   native definition.\n7. Check the finished definition against every row of the `\u002Fsubagent-standards` and\n   `\u002Fagent-prompt-standards` rule catalogs, each row at the surface its stating section\n   names — template syntax and profile selection at the authored input, native fields,\n   permissions, and complete profile values in each emitted definition. Repair each\n   violation at its authored source and repeat steps 6 and 7 until no row is violated.\n8. Run the focused deterministic checks, then preserve the exact definition through the\n   product's normal checkpoint workflow. A later edit repeats steps 6 to 8, so the\n   returned definition is the state those checks passed on.\n9. Return the configuration path, the configured role, the emitted definitions, and the\n   verification still outstanding under `\u002Fsubagent-standards`: an `\u002Faudit-subagent` run in\n   a separate agent session, and native loading with one minimal isolated execution of the\n   emitted definition.\n\nThis skill launches no configuration it authors.\n\n\u003C\u002Fworkflow>\n\n\u003Crepair_from_run_file>\n\nRead every finding to repair, by its `\u003Cunit>:\u003Crule-id>` key, from the run file alone, and read\nthe definition to repair from the unit the run records for it. Ignore any summary, remedy, or\nclass name in the task message. Attend to every rule the run names and sweep each named class\nacross the whole target. Then follow the `\u003Crepair>` steps.\n\n\u003C\u002Frepair_from_run_file>\n\n\u003Crepair_from_command>\n\nRepair the defect the command's output names at its authored source, never in an emitted\ndefinition. Then follow the `\u003Crepair>` steps.\n\n\u003C\u002Frepair_from_command>\n\n\u003Crepair>\n\n1. Repair each finding across every instance the cited clause covers, and change nothing the\n   clause does not require.\n2. Before returning, list every same-class site and every dependency the repair changed — a\n   renamed field, a changed profile, a changed result contract — and resolve each, in the\n   authored input and in each emitted definition.\n3. Run workflow steps 6 to 8 on the repaired definition.\n4. Return the repaired definition with, for each repair, the clause applied and the check that\n   shows the class closed, plus the outstanding verification the workflow names. Return a\n   `blocked` result naming the missing input when the run file or the command output is absent.\n\n\u003C\u002Frepair>\n\n\u003Creference>\n\nRead only the references relevant to the role's actual work:\n\n- [subagents.md](${CLAUDE_SKILL_DIR}\u002Freferences\u002Fsubagents.md): native definitions,\n  complete profile examples, capability selection, and skill-backed wrappers.\n- [write-subagent-prompts.md](${CLAUDE_SKILL_DIR}\u002Freferences\u002Fwrite-subagent-prompts.md):\n  converting a role requirement into a focused prompt and result contract.\n- [evaluation-and-testing.md](${CLAUDE_SKILL_DIR}\u002Freferences\u002Fevaluation-and-testing.md):\n  evidence design, native loading, and retained invocation results.\n- [error-handling-and-recovery.md](${CLAUDE_SKILL_DIR}\u002Freferences\u002Ferror-handling-and-recovery.md):\n  diagnosing failure boundaries and returning actionable evidence.\n- [context-management.md](${CLAUDE_SKILL_DIR}\u002Freferences\u002Fcontext-management.md):\n  independent target discovery and bounded context for long work.\n- [orchestration-patterns.md](${CLAUDE_SKILL_DIR}\u002Freferences\u002Forchestration-patterns.md):\n  explicit dependencies between skill-requested calls.\n- [debugging-agents.md](${CLAUDE_SKILL_DIR}\u002Freferences\u002Fdebugging-agents.md):\n  inspecting native observations without changing the attempted launch.\n\n\u003C\u002Freference>\n\n\u003Cfailure_modes>\n\n**Claude retained independent configuration fields.**\n\nClaude's examples selected a model separately from its reasoning controls and omitted\ncontrols the harness requires. A model chosen apart from its profile drifts from the\nconfiguration owner, and a hand-assembled block leaves out whatever that owner adds.\nDeclare one central profile and use its complete native configuration as one unit.\n\n**Claude prescribed a retired tool contract in invocation advice.**\n\nClaude's handoff prescribed return fields and lifecycle tools an earlier tool version\nexposed. The advice was copied from earlier guidance instead of read from the current\nnative tool schema. Use the invocation mechanics of the root harness instruction file\n`\u002Fsubagent-standards` `\u003Cinvocation>` names and the current native schema, and report the\nactual result.\n\n\u003C\u002Ffailure_modes>\n\n\u003Csuccess_criteria>\n\n- The definition implements the governing role and the complete selected native profile.\n- The finished definition violates no rule in the `\u002Fsubagent-standards` or\n  `\u002Fagent-prompt-standards` rule catalog and is returned with no audit dispatched or awaited.\n- The calling skill's launch instruction names the exact configured role and supplies only the target.\n- The product's author command and focused deterministic checks exit zero on the returned\n  definition, and every emitted definition the result names exists at its path.\n- The result names the configuration path, the configured role, each emitted definition, the\n  pending `\u002Faudit-subagent` run, and the pending native loading and minimal isolated execution.\n- A repair returns, for each finding, the clause applied and the check that shows the class\n  closed, with every same-class site and changed dependency resolved.\n- A definition that already holds the requested result returns `unchanged`; an absent input\n  or composed skill returns `blocked`.\n- No configuration load or execution approval is claimed before its actual result exists.\n\n\u003C\u002Fsuccess_criteria>\n","{!% require_skill 'instructions:subagent-standards' %!}\n\n{!% require_skill 'instructions:agent-prompt-standards' %!}\n\n{!% require_skill 'instructions:skill-standards' %!}\n\n\u003Cobjective>\nA finished {{! term('configured_agent') !}} definition and its calling-skill integration,\nready for independent verification, with native configuration and a declared result contract.\n\u003C\u002Fobjective>\n\n\u003Cconstraints>\n\n- ALWAYS: apply every rule in the `\u002Fsubagent-standards` and `\u002Fagent-prompt-standards` rule\n  catalogs to the finished definition, and return it ready for independent verification once\n  the product's author command and deterministic checks pass on it.\n- NEVER: dispatch a {{! term('configured_agent') !}} auditor or wait on an audit verdict — a\n  verdict on the definition comes from `\u002Faudit-subagent` run in an agent session separate from\n  the one that authored it.\n- ALWAYS: write to the invocation checkout. Reach a user-scope destination outside it —\n  creating, editing, or deleting — only after the operator confirms the exact absolute\n  destination; one approval covers one write.\n- NEVER: widen an approved checkout-scope write to user scope on the judgment that the\n  configured agent suits other projects.\n\n\u003C\u002Fconstraints>\n\n\u003Cintake>\n\nSelect the route from the task message:\n\n| Task message carries                                                                                   | Route                    |\n| ------------------------------------------------------------------------------------------------------ | ------------------------ |\n| A target path or role only                                                                             | `\u003Cworkflow>`             |\n| A target followed by a sealed run file and the instruction to attend to every rule the run names       | `\u003Crepair_from_run_file>` |\n| A target followed by the command line and complete output of a deterministic command that failed on it | `\u003Crepair_from_command>`  |\n\n\u003C\u002Fintake>\n\n\u003Cworkflow>\n\n1. Require `$configuration_target`. When it is empty, return a `blocked` result naming the\n   missing configuration path or role. Read the requested target and its governing requirements. Identify the role's\n   owning skill, exact configured name, destination, selected profile, and result.\n   Return a `blocked` result naming the missing input when a product decision or a required\n   input is absent. When the definition already holds the requested result, return an\n   `unchanged` result naming the committed head and the path that holds it, and edit nothing.\n2. Apply `\u002Fsubagent-standards` to placement, capabilities, profiles, isolation,\n   invocation, and evidence. Read the relevant references from the index below.\n3. For a skill-backed role, author a thin wrapper that invokes the owning skill\n   and relays its result. Keep task-specific behavior in that skill.\n4. For a marketplace source, declare `profile: standard`, `profile: strong`,\n   `profile: executor`, or `profile: fast` according to the governing selection. Let the product build\n   emit the complete native configuration. For a product-owned native definition,\n   use the selected complete configuration supplied by the loaded standards and examples.\n5. Use skill `instructions:author-skill`. Update the calling skill through it so its\n   explicit launch names the configured role and supplies only the target.\n6. Run the product's author command, then apply `\u002Fsubagent-standards` `\u003Cconfiguration_subject>`\n   to identify the authored input and exact emitted definitions, or the directly authored\n   native definition.\n7. Check the finished definition against every row of the `\u002Fsubagent-standards` and\n   `\u002Fagent-prompt-standards` rule catalogs, each row at the surface its stating section\n   names — template syntax and profile selection at the authored input, native fields,\n   permissions, and complete profile values in each emitted definition. Repair each\n   violation at its authored source and repeat steps 6 and 7 until no row is violated.\n8. Run the focused deterministic checks, then preserve the exact definition through the\n   product's normal checkpoint workflow. A later edit repeats steps 6 to 8, so the\n   returned definition is the state those checks passed on.\n9. Return the configuration path, the configured role, the emitted definitions, and the\n   verification still outstanding under `\u002Fsubagent-standards`: an `\u002Faudit-subagent` run in\n   a separate agent session, and native loading with one minimal isolated execution of the\n   emitted definition.\n\nThis skill launches no configuration it authors.\n\n\u003C\u002Fworkflow>\n\n\u003Crepair_from_run_file>\n\nRead every finding to repair, by its `\u003Cunit>:\u003Crule-id>` key, from the run file alone, and read\nthe definition to repair from the unit the run records for it. Ignore any summary, remedy, or\nclass name in the task message. Attend to every rule the run names and sweep each named class\nacross the whole target. Then follow the `\u003Crepair>` steps.\n\n\u003C\u002Frepair_from_run_file>\n\n\u003Crepair_from_command>\n\nRepair the defect the command's output names at its authored source, never in an emitted\ndefinition. Then follow the `\u003Crepair>` steps.\n\n\u003C\u002Frepair_from_command>\n\n\u003Crepair>\n\n1. Repair each finding across every instance the cited clause covers, and change nothing the\n   clause does not require.\n2. Before returning, list every same-class site and every dependency the repair changed — a\n   renamed field, a changed profile, a changed result contract — and resolve each, in the\n   authored input and in each emitted definition.\n3. Run workflow steps 6 to 8 on the repaired definition.\n4. Return the repaired definition with, for each repair, the clause applied and the check that\n   shows the class closed, plus the outstanding verification the workflow names. Return a\n   `blocked` result naming the missing input when the run file or the command output is absent.\n\n\u003C\u002Frepair>\n\n\u003Creference>\n\nRead only the references relevant to the role's actual work:\n\n- [subagents.md](${CLAUDE_SKILL_DIR}\u002Freferences\u002Fsubagents.md): native definitions,\n  complete profile examples, capability selection, and skill-backed wrappers.\n- [write-subagent-prompts.md](${CLAUDE_SKILL_DIR}\u002Freferences\u002Fwrite-subagent-prompts.md):\n  converting a role requirement into a focused prompt and result contract.\n- [evaluation-and-testing.md](${CLAUDE_SKILL_DIR}\u002Freferences\u002Fevaluation-and-testing.md):\n  evidence design, native loading, and retained invocation results.\n- [error-handling-and-recovery.md](${CLAUDE_SKILL_DIR}\u002Freferences\u002Ferror-handling-and-recovery.md):\n  diagnosing failure boundaries and returning actionable evidence.\n- [context-management.md](${CLAUDE_SKILL_DIR}\u002Freferences\u002Fcontext-management.md):\n  independent target discovery and bounded context for long work.\n- [orchestration-patterns.md](${CLAUDE_SKILL_DIR}\u002Freferences\u002Forchestration-patterns.md):\n  explicit dependencies between skill-requested calls.\n- [debugging-agents.md](${CLAUDE_SKILL_DIR}\u002Freferences\u002Fdebugging-agents.md):\n  inspecting native observations without changing the attempted launch.\n\n\u003C\u002Freference>\n\n\u003Cfailure_modes>\n\n**Claude retained independent configuration fields.**\n\nClaude's examples selected a model separately from its reasoning controls and omitted\ncontrols the harness requires. A model chosen apart from its profile drifts from the\nconfiguration owner, and a hand-assembled block leaves out whatever that owner adds.\nDeclare one central profile and use its complete native configuration as one unit.\n\n**Claude prescribed a retired tool contract in invocation advice.**\n\nClaude's handoff prescribed return fields and lifecycle tools an earlier tool version\nexposed. The advice was copied from earlier guidance instead of read from the current\nnative tool schema. Use the invocation mechanics of the root harness instruction file\n`\u002Fsubagent-standards` `\u003Cinvocation>` names and the current native schema, and report the\nactual result.\n\n\u003C\u002Ffailure_modes>\n\n\u003Csuccess_criteria>\n\n- The definition implements the governing role and the complete selected native profile.\n- The finished definition violates no rule in the `\u002Fsubagent-standards` or\n  `\u002Fagent-prompt-standards` rule catalog and is returned with no audit dispatched or awaited.\n- The calling skill's launch instruction names the exact configured role and supplies only the target.\n- The product's author command and focused deterministic checks exit zero on the returned\n  definition, and every emitted definition the result names exists at its path.\n- The result names the configuration path, the configured role, each emitted definition, the\n  pending `\u002Faudit-subagent` run, and the pending native loading and minimal isolated execution.\n- A repair returns, for each finding, the clause applied and the check that shows the class\n  closed, with every same-class site and changed dependency resolved.\n- A definition that already holds the requested result returns `unchanged`; an absent input\n  or composed skill returns `blocked`.\n- No configuration load or execution approval is claimed before its actual result exists.\n\n\u003C\u002Fsuccess_criteria>\n",{"name":5,"arguments":44,"description":7,"allowed-tools":45,"argument-hint":46},"configuration_target","Read, Glob, Write, Edit, Bash, {{! tool('use_skill') !}}","\u003Cconfiguration-path-or-role> [repair-input]","main","978d51c51d68c99cffb2ba48f7cad9d2f07e5738","src\u002Fplugins\u002Finstructions\u002Fskills\u002Fauthor-subagent","https:\u002F\u002Fgithub.com\u002Foutcomeeng\u002Fplugins","https:\u002F\u002Fgithub.com\u002Foutcomeeng","https:\u002F\u002Foutcome.engineering","Spec-driven development for AI-assisted engineering","2026-11-12 11:34:11",{"source":8,"skillName":5,"commands":56,"prompt":66,"zipAvailable":67},[57,60,63],{"tool":58,"command":59},"npx","npx skills add outcomeeng\u002Fplugins --skill author-subagent",{"tool":61,"command":62},"bunx","bunx skills add outcomeeng\u002Fplugins --skill author-subagent",{"tool":64,"command":65},"pnpm","pnpm dlx skills add outcomeeng\u002Fplugins --skill author-subagent","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Foutcomeeng\u002Fplugins\u002Fblob\u002Fmain\u002Fsrc\u002Fplugins\u002Finstructions\u002Fskills\u002Fauthor-subagent\u002FSKILL.md",true,[69,75,79,83,87,91,95],{"path":70,"resourceType":71,"resourceTypeDesc":72,"sizeBytes":73,"sourceHtmlUrl":74},"references\u002Fcontext-management.md","REFERENCE","参考文档",1586,"https:\u002F\u002Fgithub.com\u002Foutcomeeng\u002Fplugins\u002Fblob\u002Fmain\u002Fsrc\u002Fplugins\u002Finstructions\u002Fskills\u002Fauthor-subagent\u002Freferences\u002Fcontext-management.md",{"path":76,"resourceType":71,"resourceTypeDesc":72,"sizeBytes":77,"sourceHtmlUrl":78},"references\u002Fdebugging-agents.md",1421,"https:\u002F\u002Fgithub.com\u002Foutcomeeng\u002Fplugins\u002Fblob\u002Fmain\u002Fsrc\u002Fplugins\u002Finstructions\u002Fskills\u002Fauthor-subagent\u002Freferences\u002Fdebugging-agents.md",{"path":80,"resourceType":71,"resourceTypeDesc":72,"sizeBytes":81,"sourceHtmlUrl":82},"references\u002Ferror-handling-and-recovery.md",1948,"https:\u002F\u002Fgithub.com\u002Foutcomeeng\u002Fplugins\u002Fblob\u002Fmain\u002Fsrc\u002Fplugins\u002Finstructions\u002Fskills\u002Fauthor-subagent\u002Freferences\u002Ferror-handling-and-recovery.md",{"path":84,"resourceType":71,"resourceTypeDesc":72,"sizeBytes":85,"sourceHtmlUrl":86},"references\u002Fevaluation-and-testing.md",1975,"https:\u002F\u002Fgithub.com\u002Foutcomeeng\u002Fplugins\u002Fblob\u002Fmain\u002Fsrc\u002Fplugins\u002Finstructions\u002Fskills\u002Fauthor-subagent\u002Freferences\u002Fevaluation-and-testing.md",{"path":88,"resourceType":71,"resourceTypeDesc":72,"sizeBytes":89,"sourceHtmlUrl":90},"references\u002Forchestration-patterns.md",1818,"https:\u002F\u002Fgithub.com\u002Foutcomeeng\u002Fplugins\u002Fblob\u002Fmain\u002Fsrc\u002Fplugins\u002Finstructions\u002Fskills\u002Fauthor-subagent\u002Freferences\u002Forchestration-patterns.md",{"path":92,"resourceType":71,"resourceTypeDesc":72,"sizeBytes":93,"sourceHtmlUrl":94},"references\u002Fsubagents.md",3019,"https:\u002F\u002Fgithub.com\u002Foutcomeeng\u002Fplugins\u002Fblob\u002Fmain\u002Fsrc\u002Fplugins\u002Finstructions\u002Fskills\u002Fauthor-subagent\u002Freferences\u002Fsubagents.md",{"path":96,"resourceType":71,"resourceTypeDesc":72,"sizeBytes":97,"sourceHtmlUrl":98},"references\u002Fwrite-subagent-prompts.md",1649,"https:\u002F\u002Fgithub.com\u002Foutcomeeng\u002Fplugins\u002Fblob\u002Fmain\u002Fsrc\u002Fplugins\u002Finstructions\u002Fskills\u002Fauthor-subagent\u002Freferences\u002Fwrite-subagent-prompts.md",[100,106,139,155,171,184],{"skillNo":101,"name":102,"nameZh":6,"description":6,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":103,"categories":104,"keywords":105,"publishedAt":39},"01M71G25RZTPQG9KJ00JCHC1F7","plugin","https:\u002F\u002Fgithub.com\u002Foutcomeeng\u002Fplugins\u002Fblob\u002Fmain\u002Fsrc\u002Ftemplates\u002Fplugin\u002FSKILL.md",[],[102],{"skillNo":107,"name":108,"nameZh":6,"description":109,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":110,"categories":111,"keywords":122,"publishedAt":39},"01M71G23DCX3SV60H63HBBKQ6J","sanitize-powerpoint","ALWAYS invoke this skill when sanitizing, cleaning up, auditing, or aligning a PowerPoint (.pptx) deck — slide-master and layout structure, layout type attributes, stray fonts, non-theme colors, or layout naming. NEVER hand-edit pptx XML without this skill.","https:\u002F\u002Fgithub.com\u002Foutcomeeng\u002Fplugins\u002Fblob\u002Fmain\u002Fsrc\u002Fplugins\u002Fwork\u002Fskills\u002Fsanitize-powerpoint\u002FSKILL.md",[112,117],{"categoryNo":113,"categoryName":114,"taxonomyType":115,"taxonomyTypeDesc":116},"01JBSEEDCAT000000000000003","演示文稿","SCENARIO","使用场景",{"categoryNo":118,"categoryName":119,"taxonomyType":120,"taxonomyTypeDesc":121},"01JBSEEDCAT000000000000034","行政与办公人员","PROFESSION","适用职业",[123,124,125,126,127,128,129,35,130,131,132,133,134,135,136,30,137,138,27,25],"sanitize powerpoint","powerpoint","sanitize","fonts","type","cleaning","structure","attributes","theme","pptx","naming","layout","deck","up","xml","master",{"skillNo":140,"name":141,"nameZh":6,"description":142,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":143,"categories":144,"keywords":145,"publishedAt":39},"01M71G21PQKBCDECHGVYSKPJW5","draw-excalidraw","ALWAYS invoke this skill when creating Excalidraw diagrams, visualizing workflows, architectures, or concepts. NEVER generate Excalidraw JSON without this skill.","https:\u002F\u002Fgithub.com\u002Foutcomeeng\u002Fplugins\u002Fblob\u002Fmain\u002Fsrc\u002Fplugins\u002Fwork\u002Fskills\u002Fdraw-excalidraw\u002FSKILL.md",[],[146,147,148,149,150,35,27,151,152,25,153,154],"draw excalidraw","excalidraw","draw","diagrams","architectures","generate","workflows","concepts","json",{"skillNo":156,"name":157,"nameZh":6,"description":158,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":159,"categories":160,"keywords":164,"publishedAt":39},"01M71G1ZMNGFD37RZYM620XM2C","typescript-test-standards","TypeScript test standards enforced across all skills. Loaded by other skills, not invoked directly.","https:\u002F\u002Fgithub.com\u002Foutcomeeng\u002Fplugins\u002Fblob\u002Fmain\u002Fsrc\u002Fplugins\u002Ftypescript\u002Fskills\u002Ftypescript-test-standards\u002FSKILL.md",[161],{"categoryNo":162,"categoryName":163,"taxonomyType":115,"taxonomyTypeDesc":116},"01JBSEEDCAT000000000000008","测试与质量",[165,166,167,168,169,33,170],"typescript","typescript test standards","test","standards","false","across",{"skillNo":172,"name":173,"nameZh":6,"description":174,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":175,"categories":176,"keywords":180,"publishedAt":39},"01M71G1XBH0X1VCTR7269MDGSY","typescript-code-standards","TypeScript code standards enforced across all skills. Loaded by other skills, not invoked directly.","https:\u002F\u002Fgithub.com\u002Foutcomeeng\u002Fplugins\u002Fblob\u002Fmain\u002Fsrc\u002Fplugins\u002Ftypescript\u002Fskills\u002Ftypescript-code-standards\u002FSKILL.md",[177],{"categoryNo":178,"categoryName":179,"taxonomyType":120,"taxonomyTypeDesc":121},"01JBSEEDCAT000000000000030","开发工程师",[165,181,182,183,168,169,33,170],"code","typescript code standards","code standards",{"skillNo":185,"name":186,"nameZh":6,"description":187,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":188,"categories":189,"keywords":190,"publishedAt":39},"01M71G1TQ3VN45SJ75DFMJDB9W","typescript-architecture-standards","TypeScript ADR conventions enforced across architect and auditor skills. Loaded by other skills, not invoked directly.","https:\u002F\u002Fgithub.com\u002Foutcomeeng\u002Fplugins\u002Fblob\u002Fmain\u002Fsrc\u002Fplugins\u002Ftypescript\u002Fskills\u002Ftypescript-architecture-standards\u002FSKILL.md",[],[191,168,192,193,165,194,195,170,33,196,169,197],"architecture standards","typescript architecture standards","architecture","adr","architect","auditor","conventions"]