[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M6GE8ESGG03F5ZPWMP5PF8C8":3,"skill-same:01M6GE8ESGG03F5ZPWMP5PF8C8":76},{"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":47,"linkOnly":48,"markdownContent":49,"markdownBody":50,"frontMatter":51,"refName":52,"commitSha":53,"skillDirectory":54,"forksCount":55,"repositoryHtmlUrl":56,"repositoryHomepageUrl":57,"ownerHtmlUrl":58,"ownerBlogUrl":59,"ownerDescription":60,"updatedAt":61,"install":62,"resources":75},"01M6GE8ESGG03F5ZPWMP5PF8C8","code-test",null,"Use only when autopilot-code dispatches implementation verification and evidence recording. Not for top-level user requests or primary capability routing.","dmlguq456\u002Fhearting","dmlguq456","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F41767172?v=4","01M6GDVTSD0T4B6TF7SNHXZHZV","Ui-Hyeop Shin","01M6GDVTXMYH31J9E7M6TZHZEM",9,"MIT","https:\u002F\u002Fgithub.com\u002Fdmlguq456\u002Fhearting\u002Fblob\u002Fmain\u002Fadapters\u002Fcodex\u002Fskills\u002Fcode-test\u002FSKILL.md",[18,23],{"categoryNo":19,"categoryName":20,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000008","测试与质量","SCENARIO","使用场景",{"categoryNo":24,"categoryName":25,"taxonomyType":26,"taxonomyTypeDesc":27},"01JBSEEDCAT000000000000030","开发工程师","PROFESSION","适用职业",[29,30,31,32,33,34,35,36,37,38,39,40,41,42,43,44,45,46],"test","code","code test","implementation verification","when","capability","for","top","requests","recording","autopilot","implementation","evidence","only","use","user","verification","routing","2026-11-10 10:12:30",false,"---\nname: code-test\ndescription: \"Use only when autopilot-code dispatches implementation verification and evidence recording. Not for top-level user requests or primary capability routing.\"\n---\n\n# code-test\n\nThis is a Codex-native Skill projection generated from the portable capability\ncontract. It is adapter-owned output, not a legacy compatibility Skill copy.\n\n## Source\n\n- Portable source: `capabilities\u002Fcode-test.md`\n- Runtime check: `adapters\u002Fcodex\u002Fbin\u002Fpreflight.sh capability-info code-test`\n- Bootstrap: `adapters\u002Fcodex\u002FAGENTS.md`\n\n## Use\n\n1. Read `capabilities\u002Fcode-test.md` for the runtime-neutral contract.\n2. Run `adapters\u002Fcodex\u002Fbin\u002Fpreflight.sh capability-info code-test`.\n3. Obey the reported status:\n   - `instruction-only`: use this Skill as Codex guidance plus explicit preflight guards.\n   - `tool-contract`: report the named `tool_contract`, run any `tool_contract_check`, and obey `runtime_surface` \u002F `fallback` before claiming full support.\n   - `unsupported`: stop or use the reported `fallback`.\n\n## Shape\n\n- Identifier: `code-test`\n- Invocation class: `parent-invoked`\n- Supported modes: `none`\n- Argument shape: `\u003Cplan name, path, or test scope> [--intensity direct|quick|standard|strong|thorough|adversarial]`\n- Portable meaning: Verify implementation results in stages and record evidence.\n\n## Portable Contract\n\n- Invocation semantics: Assess graduated verification after `code-execute` or on demand to verify code correctness. Intensity-derived rigor scales final verification and test-adequacy review; it does not force a separate parallel QA loop by itself. The capability resolves a plan path, changed-file list, or test scope, assesses the applicable test levels, runs only checks whose evidence is missing or invalidated by the change, stops on the first failing new check, and records durable evidence before reporting a verdict. When the verification target includes a report spectrogram, assess the fail-closed figure semantic verifier against its manifest and report. Reuse its result only while the manifest, report, PNG hash, and visual-review evidence still match. Missing exact 48 kHz full-band metadata, range-compatible claims, shared-scale evidence, or a hash-current visual review is a failed level. For a planned QA leg with sealed `done_when` items, its `\u003Cprimary-report>.items.json` is a derived output of that exact primary report. The existing report scope, sub-session fence, state ledger, and continuation carry the sidecar with the primary; no separate path input is needed. Adapters may expose this capability through native commands, skill files, prompt instructions, or explicit wrappers. The adapter must report unsupported runtime mechanics instead of silently treating another runtime's native file format as portable. Put pytest basetemp and tool scratch data under the supplied `runtime_dir` or system temporary storage. Keep test reports and compact evidence in the declared artifact outputs.\n\n\n\n## Projected Portable Details\n\n## Artifact Ownership\n\nArtifact root: `core\u002FCONVENTIONS.md §5.1`.\n\nWhen invoked from a `standard+` `autopilot-code` stage cycle, write verification\nevidence only to the test node's declared outputs and write scope. Return the final verdict to `code-report`, which owns\n`pipeline_summary.md`; the `code-test` stage must not write that report-owned\nartifact. Standalone invocations should create or reuse an appropriate\n`plans\u002F\u003Cdate>_\u003Cslug>\u002F` work-cycle directory and may update their own standalone\nsummary when no `code-report` stage exists.\n\nRequired evidence:\n\n- test target resolution: plan path, changed-file list, or inferred scope;\n- command log or explicit skip\u002Fblock reason for each attempted level;\n- failing level and first actionable error when verification fails;\n- final one-line verdict suitable for handoff to `code-report`.\n\n## Artifact Producer Lifecycle\n\n`code-test` is a `standard+` stage worker: it never issues its own campaign or\ncycle. It receives the owner's open cycle through\n`AGENT_ARTIFACT_CAMPAIGN_ID`\u002F`AGENT_ARTIFACT_CYCLE_ID`\u002F`AGENT_ARTIFACT_PRODUCER_ID`\u002F\n`AGENT_ARTIFACT_CYCLE_DIR`\u002F`AGENT_ARTIFACT_OUTPUT_DIR` (dispatch env\npass-through); the resolver applies the test node's declared outputs and\nwrite scope.\n`artifact_producer.py` owns the open cycle and its output paths; `finalize` and\n`admit-shared` belong to the owner, never to a stage worker. See\n`producer_lifecycle` in `capabilities\u002Ftopologies.json`.\n\n## Role Requirements\n\nUse portable role names from `roles\u002FREADME.md` and `core\u002FCONVENTIONS.md`.\nConcrete model names, subagent frontmatter, and runtime-specific tool lists\nbelong in adapter files.\n\nMinimum role mapping:\n\n- verification: QA role using `roles\u002Funits\u002Fqa\u002Ftest.md`;\n- review: optional QA reviewer for test adequacy when selected by QA\u002Fintensity risk;\n- reporting: editorial\u002Freporting role only for user-facing summary polish, not\n  for changing the test verdict.\n\n## Guard Requirements\n\nAdapters must preserve the portable invariants relevant to this capability:\n\n- resolve artifact root through `utilities\u002Fartifact-root.sh` or equivalent logic;\n- use DB memory paths, not runtime-native memory files.\n\nAdditional test-entry gates:\n\n- run `roles\u002Funits\u002Fqa\u002Ftest.md` semantics or the adapter-native projection of\n  that mode before claiming verification;\n- if the adapter reports a `verification-runner` tool contract, run its\n  contract check or report unavailable;\n- do not modify source files while acting in `code-test`;\n- do not claim independent QA review unless a separate QA role, headless worker,\n  or external reviewer actually ran.\n\n## Portable Procedure\n\n1. Resolve the verification target:\n   - if a plan path is provided, read the plan's verification section and the\n     corresponding checklist\u002Fchanged-file evidence;\n   - if changed files are provided, use them directly;\n   - otherwise infer recent changed files from git state and report the\n     inference.\n2. Assess the applicable levels from `roles\u002Funits\u002Fqa\u002Ftest.md`: syntax, import,\n   smoke, functional, integration, and behavioral runtime observation for\n   user-facing surfaces. These levels classify evidence; they do not require a\n   restart at syntax when valid evidence already covers a level. Use existing\n   execution, review, test, and CI artifacts when their source, scope, inputs,\n   dependencies, and run conditions still apply. Identify the changed delta,\n   any known failure, and any required unverified dimension.\n   If changed outputs include a spectrogram report, assess the fail-closed\n   figure semantic verifier against its manifest and report, reusing its result\n   only when the evidence remains current.\n3. Run only selected checks whose evidence is missing or invalidated, in level\n   order, and stop at the first failure. Preserve known unresolved failures;\n   after a fix, rerun the check affected by that fix. A handoff or a historical\n   PASS marker alone neither invalidates command evidence nor satisfies the\n   current test gate.\n4. Record commands, outputs or excerpts, skips, blockers, and the first\n   actionable failure in `test_logs\u002F`.\n5. Emit the final verdict as a handoff to `code-report`; in a `standard+` stage\n   cycle, `code-report` alone updates `pipeline_summary.md`. When no\n   `code-report` stage exists, a standalone invocation may update its own\n   standalone work-cycle summary.\n6. Return a concise report path plus verdict to the caller.\n\n## Shared Procedure References\n\nRead the complete portable procedure files listed here when they apply; this logical read-set is shared across Claude, Codex, and OpenCode.\n\n- `capabilities\u002Fcode-test\u002Freferences\u002Fprocedure.md`\n\n## Workflow Evidence\n\n- Before capability grounding\u002Fspec-changing work: `adapters\u002Fcodex\u002Fbin\u002Fpreflight.sh route code-test [cwd] [session-id]`\n- For workflow state: `adapters\u002Fcodex\u002Fbin\u002Fpreflight.sh status [cwd] [session-id]` and `adapters\u002Fcodex\u002Fbin\u002Fpreflight.sh prompt-signal [cwd] [session-id]`\n\nDo not use legacy compatibility Skill files or non-native adapter Skill files\nas Codex-native source. Those files are compatibility\u002Freference surfaces only.\n","# code-test\n\nThis is a Codex-native Skill projection generated from the portable capability\ncontract. It is adapter-owned output, not a legacy compatibility Skill copy.\n\n## Source\n\n- Portable source: `capabilities\u002Fcode-test.md`\n- Runtime check: `adapters\u002Fcodex\u002Fbin\u002Fpreflight.sh capability-info code-test`\n- Bootstrap: `adapters\u002Fcodex\u002FAGENTS.md`\n\n## Use\n\n1. Read `capabilities\u002Fcode-test.md` for the runtime-neutral contract.\n2. Run `adapters\u002Fcodex\u002Fbin\u002Fpreflight.sh capability-info code-test`.\n3. Obey the reported status:\n   - `instruction-only`: use this Skill as Codex guidance plus explicit preflight guards.\n   - `tool-contract`: report the named `tool_contract`, run any `tool_contract_check`, and obey `runtime_surface` \u002F `fallback` before claiming full support.\n   - `unsupported`: stop or use the reported `fallback`.\n\n## Shape\n\n- Identifier: `code-test`\n- Invocation class: `parent-invoked`\n- Supported modes: `none`\n- Argument shape: `\u003Cplan name, path, or test scope> [--intensity direct|quick|standard|strong|thorough|adversarial]`\n- Portable meaning: Verify implementation results in stages and record evidence.\n\n## Portable Contract\n\n- Invocation semantics: Assess graduated verification after `code-execute` or on demand to verify code correctness. Intensity-derived rigor scales final verification and test-adequacy review; it does not force a separate parallel QA loop by itself. The capability resolves a plan path, changed-file list, or test scope, assesses the applicable test levels, runs only checks whose evidence is missing or invalidated by the change, stops on the first failing new check, and records durable evidence before reporting a verdict. When the verification target includes a report spectrogram, assess the fail-closed figure semantic verifier against its manifest and report. Reuse its result only while the manifest, report, PNG hash, and visual-review evidence still match. Missing exact 48 kHz full-band metadata, range-compatible claims, shared-scale evidence, or a hash-current visual review is a failed level. For a planned QA leg with sealed `done_when` items, its `\u003Cprimary-report>.items.json` is a derived output of that exact primary report. The existing report scope, sub-session fence, state ledger, and continuation carry the sidecar with the primary; no separate path input is needed. Adapters may expose this capability through native commands, skill files, prompt instructions, or explicit wrappers. The adapter must report unsupported runtime mechanics instead of silently treating another runtime's native file format as portable. Put pytest basetemp and tool scratch data under the supplied `runtime_dir` or system temporary storage. Keep test reports and compact evidence in the declared artifact outputs.\n\n\n\n## Projected Portable Details\n\n## Artifact Ownership\n\nArtifact root: `core\u002FCONVENTIONS.md §5.1`.\n\nWhen invoked from a `standard+` `autopilot-code` stage cycle, write verification\nevidence only to the test node's declared outputs and write scope. Return the final verdict to `code-report`, which owns\n`pipeline_summary.md`; the `code-test` stage must not write that report-owned\nartifact. Standalone invocations should create or reuse an appropriate\n`plans\u002F\u003Cdate>_\u003Cslug>\u002F` work-cycle directory and may update their own standalone\nsummary when no `code-report` stage exists.\n\nRequired evidence:\n\n- test target resolution: plan path, changed-file list, or inferred scope;\n- command log or explicit skip\u002Fblock reason for each attempted level;\n- failing level and first actionable error when verification fails;\n- final one-line verdict suitable for handoff to `code-report`.\n\n## Artifact Producer Lifecycle\n\n`code-test` is a `standard+` stage worker: it never issues its own campaign or\ncycle. It receives the owner's open cycle through\n`AGENT_ARTIFACT_CAMPAIGN_ID`\u002F`AGENT_ARTIFACT_CYCLE_ID`\u002F`AGENT_ARTIFACT_PRODUCER_ID`\u002F\n`AGENT_ARTIFACT_CYCLE_DIR`\u002F`AGENT_ARTIFACT_OUTPUT_DIR` (dispatch env\npass-through); the resolver applies the test node's declared outputs and\nwrite scope.\n`artifact_producer.py` owns the open cycle and its output paths; `finalize` and\n`admit-shared` belong to the owner, never to a stage worker. See\n`producer_lifecycle` in `capabilities\u002Ftopologies.json`.\n\n## Role Requirements\n\nUse portable role names from `roles\u002FREADME.md` and `core\u002FCONVENTIONS.md`.\nConcrete model names, subagent frontmatter, and runtime-specific tool lists\nbelong in adapter files.\n\nMinimum role mapping:\n\n- verification: QA role using `roles\u002Funits\u002Fqa\u002Ftest.md`;\n- review: optional QA reviewer for test adequacy when selected by QA\u002Fintensity risk;\n- reporting: editorial\u002Freporting role only for user-facing summary polish, not\n  for changing the test verdict.\n\n## Guard Requirements\n\nAdapters must preserve the portable invariants relevant to this capability:\n\n- resolve artifact root through `utilities\u002Fartifact-root.sh` or equivalent logic;\n- use DB memory paths, not runtime-native memory files.\n\nAdditional test-entry gates:\n\n- run `roles\u002Funits\u002Fqa\u002Ftest.md` semantics or the adapter-native projection of\n  that mode before claiming verification;\n- if the adapter reports a `verification-runner` tool contract, run its\n  contract check or report unavailable;\n- do not modify source files while acting in `code-test`;\n- do not claim independent QA review unless a separate QA role, headless worker,\n  or external reviewer actually ran.\n\n## Portable Procedure\n\n1. Resolve the verification target:\n   - if a plan path is provided, read the plan's verification section and the\n     corresponding checklist\u002Fchanged-file evidence;\n   - if changed files are provided, use them directly;\n   - otherwise infer recent changed files from git state and report the\n     inference.\n2. Assess the applicable levels from `roles\u002Funits\u002Fqa\u002Ftest.md`: syntax, import,\n   smoke, functional, integration, and behavioral runtime observation for\n   user-facing surfaces. These levels classify evidence; they do not require a\n   restart at syntax when valid evidence already covers a level. Use existing\n   execution, review, test, and CI artifacts when their source, scope, inputs,\n   dependencies, and run conditions still apply. Identify the changed delta,\n   any known failure, and any required unverified dimension.\n   If changed outputs include a spectrogram report, assess the fail-closed\n   figure semantic verifier against its manifest and report, reusing its result\n   only when the evidence remains current.\n3. Run only selected checks whose evidence is missing or invalidated, in level\n   order, and stop at the first failure. Preserve known unresolved failures;\n   after a fix, rerun the check affected by that fix. A handoff or a historical\n   PASS marker alone neither invalidates command evidence nor satisfies the\n   current test gate.\n4. Record commands, outputs or excerpts, skips, blockers, and the first\n   actionable failure in `test_logs\u002F`.\n5. Emit the final verdict as a handoff to `code-report`; in a `standard+` stage\n   cycle, `code-report` alone updates `pipeline_summary.md`. When no\n   `code-report` stage exists, a standalone invocation may update its own\n   standalone work-cycle summary.\n6. Return a concise report path plus verdict to the caller.\n\n## Shared Procedure References\n\nRead the complete portable procedure files listed here when they apply; this logical read-set is shared across Claude, Codex, and OpenCode.\n\n- `capabilities\u002Fcode-test\u002Freferences\u002Fprocedure.md`\n\n## Workflow Evidence\n\n- Before capability grounding\u002Fspec-changing work: `adapters\u002Fcodex\u002Fbin\u002Fpreflight.sh route code-test [cwd] [session-id]`\n- For workflow state: `adapters\u002Fcodex\u002Fbin\u002Fpreflight.sh status [cwd] [session-id]` and `adapters\u002Fcodex\u002Fbin\u002Fpreflight.sh prompt-signal [cwd] [session-id]`\n\nDo not use legacy compatibility Skill files or non-native adapter Skill files\nas Codex-native source. Those files are compatibility\u002Freference surfaces only.\n",{"name":5,"description":7},"main","9efc5374fe7ef449cbc2a9a051324da895084956","adapters\u002Fcodex\u002Fskills\u002Fcode-test",2,"https:\u002F\u002Fgithub.com\u002Fdmlguq456\u002Fhearting","https:\u002F\u002Fdmlguq456.github.io\u002Fhearting\u002F","https:\u002F\u002Fgithub.com\u002Fdmlguq456","https:\u002F\u002Fdmlguq456.github.io\u002F","interested in speech processing","2026-11-11 09:45:36",{"source":8,"skillName":5,"commands":63,"prompt":73,"zipAvailable":74},[64,67,70],{"tool":65,"command":66},"npx","npx skills add dmlguq456\u002Fhearting --skill code-test",{"tool":68,"command":69},"bunx","bunx skills add dmlguq456\u002Fhearting --skill code-test",{"tool":71,"command":72},"pnpm","pnpm dlx skills add dmlguq456\u002Fhearting --skill code-test","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Fdmlguq456\u002Fhearting\u002Fblob\u002Fmain\u002Fadapters\u002Fcodex\u002Fskills\u002Fcode-test\u002FSKILL.md",true,[],[77,97,114,126,138,161],{"skillNo":78,"name":79,"nameZh":6,"description":80,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":81,"categories":82,"keywords":84,"publishedAt":47},"01M6GEES21KY8PDHWM2KSFT24A","code-refine","Use only when autopilot-code dispatches plan revision after user notes, plan-check feedback, or verification failure. Not for top-level user requests or primary capability routing.","https:\u002F\u002Fgithub.com\u002Fdmlguq456\u002Fhearting\u002Fblob\u002Fmain\u002Fskills\u002Fcode-refine\u002FSKILL.md",[83],{"categoryNo":24,"categoryName":25,"taxonomyType":26,"taxonomyTypeDesc":27},[30,85,86,87,88,89,45,46,90,91,36,37,92,93,94,95,39,96,42,43],"code refine","refine","feedback","direct","plan","notes","check","revision","quick","intensity","name","revise",{"skillNo":98,"name":99,"nameZh":6,"description":100,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":101,"categories":102,"keywords":104,"publishedAt":47},"01M6GE1MV7AYPMED4DCXR0V7JH","code-execute","Use only when autopilot-code dispatches the implementation stage for an approved plan. Not for top-level user requests or primary capability routing.","https:\u002F\u002Fgithub.com\u002Fdmlguq456\u002Fhearting\u002Fblob\u002Fmain\u002Fadapters\u002Fclaude\u002Fskills\u002Fcode-execute\u002FSKILL.md",[103],{"categoryNo":24,"categoryName":25,"taxonomyType":26,"taxonomyTypeDesc":27},[105,106,30,107,36,37,108,95,39,109,40,110,42,43,44,111,89,112,46,113],"code execute","execute","stage","step by step","record","log","delegate","execution","development",{"skillNo":115,"name":116,"nameZh":6,"description":117,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":118,"categories":119,"keywords":120,"publishedAt":47},"01M6GEG4QX5NCAFD0T1WMZYYM4","claude-aware","Demonstrate a skill source with inactive runtime-specific metadata.","https:\u002F\u002Fgithub.com\u002Fdmlguq456\u002Fhearting\u002Fblob\u002Fmain\u002Ftools\u002Finstall\u002Ffixtures\u002Fextensions\u002Fruntime-specific\u002Fskill\u002FSKILL.md",[],[121,122,123,124,125],"claude aware","source","with","runtime","metadata",{"skillNo":127,"name":128,"nameZh":6,"description":129,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":130,"categories":131,"keywords":132,"publishedAt":47},"01M6GEG1D04DY5SAP5Y8F5BVXA","portable-review","Review a change using portable, instruction-only guidance.","https:\u002F\u002Fgithub.com\u002Fdmlguq456\u002Fhearting\u002Fblob\u002Fmain\u002Ftools\u002Finstall\u002Ffixtures\u002Fextensions\u002Finstruction-only\u002Fskill\u002FSKILL.md",[],[133,134,135,136,42,137],"review","portable review","portable","guidance","change",{"skillNo":139,"name":140,"nameZh":6,"description":141,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":142,"categories":143,"keywords":144,"publishedAt":47},"01M6GEFY4K6ATTDHFW45KJMNSG","session-tidy","Use when context fills, before compact, on handoff to another session, after a large task, or on request. Not for primary routing or memory writes.","https:\u002F\u002Fgithub.com\u002Fdmlguq456\u002Fhearting\u002Fblob\u002Fmain\u002Fskills\u002Fsession-tidy\u002FSKILL.md",[],[145,146,147,46,148,149,150,151,152,33,153,154,35,155,156,157,158,43,159,160],"tidy","session tidy","session","support","memory","handoff","ops","window","request","model","card","clear","compact","task","context","write",{"skillNo":162,"name":163,"nameZh":6,"description":164,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":165,"categories":166,"keywords":170,"publishedAt":47},"01M6GEFTBXE1JFXCQ686PQZ1RV","draft-strategy","Use only when autopilot-draft dispatches document strategy and evidence-plan creation. Not for top-level user requests or primary capability routing.","https:\u002F\u002Fgithub.com\u002Fdmlguq456\u002Fhearting\u002Fblob\u002Fmain\u002Fskills\u002Fdraft-strategy\u002FSKILL.md",[167],{"categoryNo":168,"categoryName":169,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000002","文档处理",[171,172,173,33,34,93,174,36,175,176,177,178,94,179,180,42,181,182,41,43,183,88,89,46,184,133,158],"draft strategy","strategy","draft","mode","output","presentation","proposal","paths","creation","artifact","writing","document","plan creation","create"]