[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M718X2NY7GTNC8ZDSTHB9WXG":3,"skill-same:01M718X2NY7GTNC8ZDSTHB9WXG":66},{"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":45,"commitSha":46,"skillDirectory":47,"forksCount":48,"repositoryHtmlUrl":49,"repositoryHomepageUrl":6,"ownerHtmlUrl":50,"ownerBlogUrl":6,"ownerDescription":6,"updatedAt":51,"install":52,"resources":65},"01M718X2NY7GTNC8ZDSTHB9WXG","gh:work-x",null,"Execute iOS Swift\u002FObjC work with Morph-X blueprint, transform, audit, and memory fingerprinting to reduce template-code repetition risk.","wangrenzhu-ola\u002FGaleHarnessCodingCLI","wangrenzhu-ola","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F113888128?v=4","01M718T5C0YYVP4Z7F4SH1MCHM","王韧竹(Bamboo Wang\u002F雪落)","01M718T5CN5T80VWXEWPK25PDQ",2,"MIT","https:\u002F\u002Fgithub.com\u002Fwangrenzhu-ola\u002FGaleHarnessCodingCLI\u002Fblob\u002Fmain\u002Fplugins\u002Fgaleharness-cli\u002Fskills\u002Fgh-work-x\u002FSKILL.md",[],[19,20,21,22,23,24,25,26,27,28,29,30,31,32,33,34,35,36,37,38],"work","gh:work x","gh","execute","doc","transform","latest","ios","audit","template","fingerprinting","plan","with","code","reduce","Blueprint","use","auto","memory","risk","2026-11-10 10:12:30",false,"---\nname: gh:work-x\ndescription: Execute iOS Swift\u002FObjC work with Morph-X blueprint, transform, audit, and memory fingerprinting to reduce template-code repetition risk.\nargument-hint: \"[Plan doc path or description of iOS work. Blank to auto use latest plan doc]\"\n---\n\n# Work-X Execution Command\n\nExecute work with the normal shipping discipline, plus Morph-X safeguards for iOS Swift\u002FObjC output. This reduces template-code repetition risk; it does not guarantee App Review success and does not replace real product, UI, content, metadata, or feature differentiation.\n\n## Input Document\n\n\u003Cinput_document> #$ARGUMENTS \u003C\u002Finput_document>\n\n## Execution Workflow\n\n### Phase 0: Input Triage\n\nDetermine how to proceed from `\u003Cinput_document>`.\n\n**Plan document:** read it completely in Phase 1 and treat it as a decision artifact.\n\n**Bare prompt:** scan likely files, nearby tests, and local conventions; classify scope:\n\n| Complexity | Signals | Action |\n|-----------|---------|--------|\n| Trivial | 1-2 files, no behavioral change | Setup, apply directly, and run relevant tests if behavior changed |\n| Small \u002F Medium | Clear scope, under ~10 files | Build a task list, then execute |\n| Large | Cross-cutting, architecture, auth\u002Fpayments\u002Fmigrations, 10+ files | Recommend planning\u002Fbrainstorming; if proceeding, build tasks carefully |\n\n\u003C!-- HKT-PATCH:gale-task-start -->\n### Phase 0.1: Task Lifecycle Start\n\nRun:\n\n```bash\ngale-task log skill_started --skill gh:work-x --title \"${ARGUMENTS:-work-x}\" 2>\u002Fdev\u002Fnull || true\n```\n\nIf `gale-task` is unavailable, skip silently. This must never block execution.\n\u003C!-- \u002FHKT-PATCH:gale-task-start -->\n\n\u003C!-- HKT-PATCH:phase-0.6 -->\n### Phase 0.6: HKTMemory Retrieve\n\nBefore choosing a blueprint, retrieve related implementation context and historical Morph-X fingerprints:\n\n```bash\nmemory_root=\"$(gale-memory resolve-root 2>\u002Fdev\u002Fnull || true)\"\n[ -n \"$memory_root\" ] && export HKT_MEMORY_DIR=\"$memory_root\"\nhkt-memory retrieve \\\n  --query \"\u003Ctask summary, iOS components, Swift\u002FObjC files, prior blueprint or strategy tags>\" \\\n  --layer all --limit 10 --min-similarity 0.35 \\\n  --vector-weight 0.7 --bm25-weight 0.3\n```\n\nUse results only as context: extract constraints, avoided patterns, and prior blueprint\u002Fstrategy fingerprints. Do not copy historical code shape. If no results or any command error occurs, proceed silently without blocking.\n\u003C!-- \u002FHKT-PATCH:phase-0.6 -->\n\n\u003C!-- HKT-PATCH:phase-0.6b -->\n### Phase 0.6b: HKTMemory Session Search\n\nQuery related work sessions:\n\n```bash\nmemory_root=\"$(gale-memory resolve-root 2>\u002Fdev\u002Fnull || true)\"\n[ -n \"$memory_root\" ] && export HKT_MEMORY_DIR=\"$memory_root\"\nhkt-memory session-search \\\n  --query \"gh:work-x \u003Ctask title or iOS feature summary>\" \\\n  --limit 5\n```\n\nUse returned sessions as supplementary context for blueprint selection. If unavailable, continue silently; session search is non-blocking.\n\u003C!-- \u002FHKT-PATCH:phase-0.6b -->\n\n### Phase 1: Quick Start\n\n1. **Read Plan and Clarify** when a plan\u002Fspec path was provided.\n   - Read the full document, including requirements, scope boundaries, implementation units, files, test scenarios, verification, and deferred unknowns.\n   - Ask only when ambiguity blocks correct execution.\n   - Get user approval to proceed when the source workflow requires it.\n\n2. **Setup Environment**\n   - Check the current branch and default branch.\n   - If already on a meaningful feature branch, continue unless the user asks otherwise.\n   - If on the default branch, create a feature branch or worktree unless the user explicitly confirms working on the default branch.\n   - Respect workspace safety: do not overwrite uncommitted user work.\n\n3. **Create Task List**\n   - Derive tasks from implementation units, dependencies, file ownership, tests, and verification.\n   - Preserve plan U-IDs in task names.\n   - Include quality checks and relevant tests.\n\n4. **Choose Execution Strategy**\n   - Use inline execution for small work or interactive tasks.\n   - Use serial subagents for dependent multi-unit work.\n   - Use parallel subagents only after checking file ownership overlap; do not stage, commit, or run the full suite inside parallel workers.\n\n### Phase 1.5: Morph-X Blueprint Constraints\n\nBefore writing or changing Swift\u002FObjC code:\n\n1. Load `.morph-config.yaml` from the target iOS project root if present. If missing, use in-memory defaults and record `config_source: default`.\n2. Build a blueprint prompt block from: project seed, feature intent, retrieved historical fingerprints, blacklisted pattern tags, existing architecture, and local test\u002Fbuild constraints.\n3. Select a blueprint that differs from recently used strategy fingerprints across:\n   - state management\n   - module boundaries\n   - file splitting\n   - protocol or abstraction boundaries\n   - error handling\n   - data-flow organization\n4. Write the constraints into the task notes before implementation. The constraints should guide original structure; they must not request cosmetic churn or semantic changes.\n5. If config, CLI, or memory retrieval is unavailable, continue with a manual blueprint summary and mark Morph-X as degraded, not failed.\n\n### Phase 2: Execute\n\nFor each task:\n\n1. Mark it in progress.\n2. Read relevant files and local patterns.\n3. Find adjacent tests before editing.\n4. Implement with existing conventions and the Phase 1.5 blueprint constraints.\n5. Run a System-Wide Test Check: if shared contracts or user-facing behavior changed, choose a relevant broader test target; otherwise run focused tests.\n6. Assess quality before moving on: behavior covered, edge cases considered, no unrelated refactors, no user work overwritten.\n\n### Phase 3: Morph-X Apply and Similarity Audit\n\nAfter Swift\u002FObjC code is produced and before final summary:\n\n1. Apply safe transformation when the CLI is available:\n   ```bash\n   gale-harness morph --apply --config .morph-config.yaml --report .morph-report.json\n   ```\n   The transform must be semantics-preserving. If the command, SwiftSyntax, or ObjC adapter is unavailable, skip the transform, record the reason, and continue to audit fallback.\n\n2. Audit similarity:\n   ```bash\n   gale-harness audit --similarity --config .morph-config.yaml --report .morph-audit.json\n   ```\n   Include AST\u002Fstructure fingerprint, token n-gram, statement Jaccard, and control-flow approximation results when available. Missing baselines or tools are non-blocking and should be reported as degraded signals.\n\n3. Handle thresholds:\n   - Default behavior is warn, not block.\n   - If `.morph-config.yaml` configures a blocking threshold and the audit exceeds it, stop before finalizing code and ask the user how to proceed.\n   - Never claim the audit proves App Review compliance.\n\n4. Run focused compile\u002Ftest verification appropriate to the changed iOS project when available. If no Xcode or Swift test target is runnable, state the gap.\n\n\u003C!-- HKT-PATCH:phase-4.5 -->\n### Phase 4.5: HKTMemory Store\n\nAfter implementation and Morph-X audit, store a concise memory record:\n\n```bash\nmemory_root=\"$(gale-memory resolve-root 2>\u002Fdev\u002Fnull || true)\"\n[ -n \"$memory_root\" ] && export HKT_MEMORY_DIR=\"$memory_root\"\nhkt-memory store \\\n  --content \"\u003Csummary with repo-relative files, blueprint constraints, strategy fingerprint, audit status, degraded fallback notes>\" \\\n  --title \"\u003Cwork-x title>\" \\\n  --topic \"work-x morph blueprint strategy fingerprint\" \\\n  --layer all\n```\n\nStore only summaries, tags, and fingerprints; do not store full source code. On error, note it as non-blocking and do not fail the workflow.\n\u003C!-- \u002FHKT-PATCH:phase-4.5 -->\n\n### Phase 5: Close\n\nReturn:\n\n```text\n## Work-X Summary\n**Completed**: [what changed]\n**Blueprint**: [constraints and strategy fingerprint]\n**Morph Apply**: [report path or degraded reason]\n**Similarity Audit**: [report path, threshold result, blocking\u002Fwarning decision]\n**Tests**: [commands run and results]\n**Compliance Boundary**: Reduces template-code repetition risk; does not guarantee App Review success.\n```\n\n\u003C!-- HKT-PATCH:gale-task-end -->\nRun `gale-task log skill_completed 2>\u002Fdev\u002Fnull || true`. If unavailable, skip silently.\n\u003C!-- \u002FHKT-PATCH:gale-task-end -->\n","# Work-X Execution Command\n\nExecute work with the normal shipping discipline, plus Morph-X safeguards for iOS Swift\u002FObjC output. This reduces template-code repetition risk; it does not guarantee App Review success and does not replace real product, UI, content, metadata, or feature differentiation.\n\n## Input Document\n\n\u003Cinput_document> #$ARGUMENTS \u003C\u002Finput_document>\n\n## Execution Workflow\n\n### Phase 0: Input Triage\n\nDetermine how to proceed from `\u003Cinput_document>`.\n\n**Plan document:** read it completely in Phase 1 and treat it as a decision artifact.\n\n**Bare prompt:** scan likely files, nearby tests, and local conventions; classify scope:\n\n| Complexity | Signals | Action |\n|-----------|---------|--------|\n| Trivial | 1-2 files, no behavioral change | Setup, apply directly, and run relevant tests if behavior changed |\n| Small \u002F Medium | Clear scope, under ~10 files | Build a task list, then execute |\n| Large | Cross-cutting, architecture, auth\u002Fpayments\u002Fmigrations, 10+ files | Recommend planning\u002Fbrainstorming; if proceeding, build tasks carefully |\n\n\u003C!-- HKT-PATCH:gale-task-start -->\n### Phase 0.1: Task Lifecycle Start\n\nRun:\n\n```bash\ngale-task log skill_started --skill gh:work-x --title \"${ARGUMENTS:-work-x}\" 2>\u002Fdev\u002Fnull || true\n```\n\nIf `gale-task` is unavailable, skip silently. This must never block execution.\n\u003C!-- \u002FHKT-PATCH:gale-task-start -->\n\n\u003C!-- HKT-PATCH:phase-0.6 -->\n### Phase 0.6: HKTMemory Retrieve\n\nBefore choosing a blueprint, retrieve related implementation context and historical Morph-X fingerprints:\n\n```bash\nmemory_root=\"$(gale-memory resolve-root 2>\u002Fdev\u002Fnull || true)\"\n[ -n \"$memory_root\" ] && export HKT_MEMORY_DIR=\"$memory_root\"\nhkt-memory retrieve \\\n  --query \"\u003Ctask summary, iOS components, Swift\u002FObjC files, prior blueprint or strategy tags>\" \\\n  --layer all --limit 10 --min-similarity 0.35 \\\n  --vector-weight 0.7 --bm25-weight 0.3\n```\n\nUse results only as context: extract constraints, avoided patterns, and prior blueprint\u002Fstrategy fingerprints. Do not copy historical code shape. If no results or any command error occurs, proceed silently without blocking.\n\u003C!-- \u002FHKT-PATCH:phase-0.6 -->\n\n\u003C!-- HKT-PATCH:phase-0.6b -->\n### Phase 0.6b: HKTMemory Session Search\n\nQuery related work sessions:\n\n```bash\nmemory_root=\"$(gale-memory resolve-root 2>\u002Fdev\u002Fnull || true)\"\n[ -n \"$memory_root\" ] && export HKT_MEMORY_DIR=\"$memory_root\"\nhkt-memory session-search \\\n  --query \"gh:work-x \u003Ctask title or iOS feature summary>\" \\\n  --limit 5\n```\n\nUse returned sessions as supplementary context for blueprint selection. If unavailable, continue silently; session search is non-blocking.\n\u003C!-- \u002FHKT-PATCH:phase-0.6b -->\n\n### Phase 1: Quick Start\n\n1. **Read Plan and Clarify** when a plan\u002Fspec path was provided.\n   - Read the full document, including requirements, scope boundaries, implementation units, files, test scenarios, verification, and deferred unknowns.\n   - Ask only when ambiguity blocks correct execution.\n   - Get user approval to proceed when the source workflow requires it.\n\n2. **Setup Environment**\n   - Check the current branch and default branch.\n   - If already on a meaningful feature branch, continue unless the user asks otherwise.\n   - If on the default branch, create a feature branch or worktree unless the user explicitly confirms working on the default branch.\n   - Respect workspace safety: do not overwrite uncommitted user work.\n\n3. **Create Task List**\n   - Derive tasks from implementation units, dependencies, file ownership, tests, and verification.\n   - Preserve plan U-IDs in task names.\n   - Include quality checks and relevant tests.\n\n4. **Choose Execution Strategy**\n   - Use inline execution for small work or interactive tasks.\n   - Use serial subagents for dependent multi-unit work.\n   - Use parallel subagents only after checking file ownership overlap; do not stage, commit, or run the full suite inside parallel workers.\n\n### Phase 1.5: Morph-X Blueprint Constraints\n\nBefore writing or changing Swift\u002FObjC code:\n\n1. Load `.morph-config.yaml` from the target iOS project root if present. If missing, use in-memory defaults and record `config_source: default`.\n2. Build a blueprint prompt block from: project seed, feature intent, retrieved historical fingerprints, blacklisted pattern tags, existing architecture, and local test\u002Fbuild constraints.\n3. Select a blueprint that differs from recently used strategy fingerprints across:\n   - state management\n   - module boundaries\n   - file splitting\n   - protocol or abstraction boundaries\n   - error handling\n   - data-flow organization\n4. Write the constraints into the task notes before implementation. The constraints should guide original structure; they must not request cosmetic churn or semantic changes.\n5. If config, CLI, or memory retrieval is unavailable, continue with a manual blueprint summary and mark Morph-X as degraded, not failed.\n\n### Phase 2: Execute\n\nFor each task:\n\n1. Mark it in progress.\n2. Read relevant files and local patterns.\n3. Find adjacent tests before editing.\n4. Implement with existing conventions and the Phase 1.5 blueprint constraints.\n5. Run a System-Wide Test Check: if shared contracts or user-facing behavior changed, choose a relevant broader test target; otherwise run focused tests.\n6. Assess quality before moving on: behavior covered, edge cases considered, no unrelated refactors, no user work overwritten.\n\n### Phase 3: Morph-X Apply and Similarity Audit\n\nAfter Swift\u002FObjC code is produced and before final summary:\n\n1. Apply safe transformation when the CLI is available:\n   ```bash\n   gale-harness morph --apply --config .morph-config.yaml --report .morph-report.json\n   ```\n   The transform must be semantics-preserving. If the command, SwiftSyntax, or ObjC adapter is unavailable, skip the transform, record the reason, and continue to audit fallback.\n\n2. Audit similarity:\n   ```bash\n   gale-harness audit --similarity --config .morph-config.yaml --report .morph-audit.json\n   ```\n   Include AST\u002Fstructure fingerprint, token n-gram, statement Jaccard, and control-flow approximation results when available. Missing baselines or tools are non-blocking and should be reported as degraded signals.\n\n3. Handle thresholds:\n   - Default behavior is warn, not block.\n   - If `.morph-config.yaml` configures a blocking threshold and the audit exceeds it, stop before finalizing code and ask the user how to proceed.\n   - Never claim the audit proves App Review compliance.\n\n4. Run focused compile\u002Ftest verification appropriate to the changed iOS project when available. If no Xcode or Swift test target is runnable, state the gap.\n\n\u003C!-- HKT-PATCH:phase-4.5 -->\n### Phase 4.5: HKTMemory Store\n\nAfter implementation and Morph-X audit, store a concise memory record:\n\n```bash\nmemory_root=\"$(gale-memory resolve-root 2>\u002Fdev\u002Fnull || true)\"\n[ -n \"$memory_root\" ] && export HKT_MEMORY_DIR=\"$memory_root\"\nhkt-memory store \\\n  --content \"\u003Csummary with repo-relative files, blueprint constraints, strategy fingerprint, audit status, degraded fallback notes>\" \\\n  --title \"\u003Cwork-x title>\" \\\n  --topic \"work-x morph blueprint strategy fingerprint\" \\\n  --layer all\n```\n\nStore only summaries, tags, and fingerprints; do not store full source code. On error, note it as non-blocking and do not fail the workflow.\n\u003C!-- \u002FHKT-PATCH:phase-4.5 -->\n\n### Phase 5: Close\n\nReturn:\n\n```text\n## Work-X Summary\n**Completed**: [what changed]\n**Blueprint**: [constraints and strategy fingerprint]\n**Morph Apply**: [report path or degraded reason]\n**Similarity Audit**: [report path, threshold result, blocking\u002Fwarning decision]\n**Tests**: [commands run and results]\n**Compliance Boundary**: Reduces template-code repetition risk; does not guarantee App Review success.\n```\n\n\u003C!-- HKT-PATCH:gale-task-end -->\nRun `gale-task log skill_completed 2>\u002Fdev\u002Fnull || true`. If unavailable, skip silently.\n\u003C!-- \u002FHKT-PATCH:gale-task-end -->\n",{"name":5,"description":7,"argument-hint":44},"[Plan doc path or description of iOS work. Blank to auto use latest plan doc]","main","adde77e5116dc3a65ca3385f7d19d086cd10a74c","plugins\u002Fgaleharness-cli\u002Fskills\u002Fgh-work-x",1,"https:\u002F\u002Fgithub.com\u002Fwangrenzhu-ola\u002FGaleHarnessCodingCLI","https:\u002F\u002Fgithub.com\u002Fwangrenzhu-ola","2026-06-13 09:21:37",{"source":8,"skillName":5,"commands":53,"prompt":63,"zipAvailable":64},[54,57,60],{"tool":55,"command":56},"npx","npx skills add wangrenzhu-ola\u002FGaleHarnessCodingCLI --skill \"gh:work-x\"",{"tool":58,"command":59},"bunx","bunx skills add wangrenzhu-ola\u002FGaleHarnessCodingCLI --skill \"gh:work-x\"",{"tool":61,"command":62},"pnpm","pnpm dlx skills add wangrenzhu-ola\u002FGaleHarnessCodingCLI --skill \"gh:work-x\"","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Fwangrenzhu-ola\u002FGaleHarnessCodingCLI\u002Fblob\u002Fmain\u002Fplugins\u002Fgaleharness-cli\u002Fskills\u002Fgh-work-x\u002FSKILL.md",true,[],[67,82,94,105,113,121],{"skillNo":68,"name":69,"nameZh":6,"description":70,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":71,"categories":72,"keywords":78,"publishedAt":39},"01M718XZ8QAQPM8BS5K9M2YQTJ","skill-one","Sample skill","https:\u002F\u002Fgithub.com\u002Fwangrenzhu-ola\u002FGaleHarnessCodingCLI\u002Fblob\u002Fmain\u002Ftests\u002Ffixtures\u002Fsample-plugin\u002Fskills\u002Fskill-one\u002FSKILL.md",[73],{"categoryNo":74,"categoryName":75,"taxonomyType":76,"taxonomyTypeDesc":77},"01JBSEEDCAT000000000000023","Skill与智能体开发","SCENARIO","使用场景",[79,80,81],"skill one","sample skill","sample",{"skillNo":83,"name":84,"nameZh":6,"description":85,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":86,"categories":87,"keywords":89,"publishedAt":39},"01M718XYEEENP5G592XVQ6MGVR","disabled-skill","A skill with model invocation disabled","https:\u002F\u002Fgithub.com\u002Fwangrenzhu-ola\u002FGaleHarnessCodingCLI\u002Fblob\u002Fmain\u002Ftests\u002Ffixtures\u002Fsample-plugin\u002Fskills\u002Fdisabled-skill\u002FSKILL.md",[88],{"categoryNo":74,"categoryName":75,"taxonomyType":76,"taxonomyTypeDesc":77},[90,31,91,92,93],"disabled skill","with model","true","model",{"skillNo":95,"name":96,"nameZh":6,"description":97,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":98,"categories":99,"keywords":101,"publishedAt":39},"01M718XXNH8T61H0EJE0BHE593","claude-only-skill","A skill restricted to Claude Code only","https:\u002F\u002Fgithub.com\u002Fwangrenzhu-ola\u002FGaleHarnessCodingCLI\u002Fblob\u002Fmain\u002Ftests\u002Ffixtures\u002Fsample-plugin\u002Fskills\u002Fclaude-only-skill\u002FSKILL.md",[100],{"categoryNo":74,"categoryName":75,"taxonomyType":76,"taxonomyTypeDesc":77},[102,103,104,32],"only","claude only skill","claude only",{"skillNo":106,"name":107,"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":108,"categories":109,"keywords":110,"publishedAt":39},"01M718XWMPEPBWHC05JNGKSEF0","default-skill","https:\u002F\u002Fgithub.com\u002Fwangrenzhu-ola\u002FGaleHarnessCodingCLI\u002Fblob\u002Fmain\u002Ftests\u002Ffixtures\u002Fcustom-paths\u002Fskills\u002Fdefault-skill\u002FSKILL.md",[],[111,112],"default skill","default",{"skillNo":114,"name":115,"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":116,"categories":117,"keywords":118,"publishedAt":39},"01M718XVZXW8CXYBNQZPJPNB6B","custom-skill","https:\u002F\u002Fgithub.com\u002Fwangrenzhu-ola\u002FGaleHarnessCodingCLI\u002Fblob\u002Fmain\u002Ftests\u002Ffixtures\u002Fcustom-paths\u002Fcustom-skills\u002Fcustom-skill\u002FSKILL.md",[],[119,120],"custom","custom skill",{"skillNo":122,"name":123,"nameZh":6,"description":124,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":125,"categories":126,"keywords":130,"publishedAt":39},"01M718XT6P96FVR69X0EEKK2N6","test-xcode","Build and test iOS apps on simulator using XcodeBuildMCP. Use after making iOS code changes, before creating a PR, or when verifying app behavior and checking for crashes on simulator.","https:\u002F\u002Fgithub.com\u002Fwangrenzhu-ola\u002FGaleHarnessCodingCLI\u002Fblob\u002Fmain\u002Fplugins\u002Fgaleharness-cli\u002Fskills\u002Ftest-xcode\u002FSKILL.md",[127],{"categoryNo":128,"categoryName":129,"taxonomyType":76,"taxonomyTypeDesc":77},"01JBSEEDCAT000000000000008","测试与质量",[131,132,133,134,135,136,137,138,112,92,139,35,140,141,32,142,143,26,144,145],"test","xcode","test xcode","apps","app","build and test","pr","for","xcodebuildmcp","scheme","when","changes","build","name","behavior"]