[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M6BYWGYSPPDDRDSDG5Y09K6B":3,"skill-same:01M6BYWGYSPPDDRDSDG5Y09K6B":92},{"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":44,"commitSha":45,"skillDirectory":46,"forksCount":47,"repositoryHtmlUrl":48,"repositoryHomepageUrl":6,"ownerHtmlUrl":49,"ownerBlogUrl":6,"ownerDescription":50,"updatedAt":51,"install":52,"resources":65},"01M6BYWGYSPPDDRDSDG5Y09K6B","oma-search",null,"Intent-based search router with trust scoring. Routes queries to optimal channels (Context7 docs, native web search, gh\u002Fglab code search, Serena local) and attaches domain trust labels. Use for search, find, lookup, reference, docs, code search, and web research.","mrmarbury\u002FPalmSync4Mac","mrmarbury","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F114311?v=4","01M6BYSN920J8AMQ0W6HGSBH60","Stefan Marbury","01M6BYSNDEACDBNBPNRNCVYAPJ",2,"Apache-2.0","https:\u002F\u002Fgithub.com\u002Fmrmarbury\u002FPalmSync4Mac\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Foma-search\u002FSKILL.md",[],[19,20,21,22,23,24,25,26,27,28,29,30,31,32,33,34,35,36,37,38],"oma search","search","with","channels","use","for","domain","trust","context7","intent","native","router","scoring","local","labels","serena","code","native web search","gh","web search","2026-11-10 10:12:30",false,"---\nname: oma-search\ndescription: Intent-based search router with trust scoring. Routes queries to optimal channels (Context7 docs, native web search, gh\u002Fglab code search, Serena local) and attaches domain trust labels. Use for search, find, lookup, reference, docs, code search, and web research.\n---\n\n# Search Agent - Intent-Based Search Router\n\n## Scheduling\n\n### Goal\nClassify information-seeking requests, route them to the best search channel, attach trust labels, and return source-grounded results.\n\n### Intent signature\n- User asks to search, find, look up, reference docs, inspect official documentation, search GitHub\u002FGitLab code, or gather web research.\n- Another skill needs reusable search infrastructure with trust scoring.\n\n### When to use\n- Finding official library\u002Fframework documentation\n- Web research for tutorials, examples, comparisons, and solutions\n- Searching GitHub\u002FGitLab code for implementation patterns\n- Any query where the search channel is unclear (auto-routing)\n- Other skills needing search infrastructure (shared invocation)\n\n### When NOT to use\n- Local codebase exploration only -> use Serena MCP directly\n- Git history or blame analysis -> use SCM Agent\n- Full architecture research -> use Architecture Agent (may invoke this skill internally)\n\n### Expected inputs\n- Query string, intent hint, or explicit flags such as `--docs`, `--code`, `--web`, `--strict`, `--wide`, `--gitlab`\n- Optional required source type, recency, domain, or trust constraints\n\n### Expected outputs\n- Ranked search results with route, source, trust label, and concise relevance summary\n- Fallback explanation when primary route fails\n- Source links or references suitable for the calling skill\n\n### Dependencies\n- Context7 MCP for docs, runtime-native web search, `gh`\u002F`glab` for code, Serena for local search\n- `resources\u002Fintent-rules.md`, `resources\u002Ftrust-registry.md`, execution protocol, examples, and checklist\n\n### Control-flow features\n- Branches by classified intent, user flags, route success\u002Ffailure, and trust constraints\n- May call web\u002Fdocs\u002Fcode\u002Flocal tools\n- Scores domains at domain level only\n\n## Structural Flow\n\n### Entry\n1. Parse the query and flags.\n2. Classify the search intent.\n3. Select one best route unless ambiguity or flags justify more.\n\n### Scenes\n1. **PREPARE**: Parse query and classify route.\n2. **ACT**: Dispatch to docs, web, code, or local search.\n3. **ACQUIRE**: Collect search results and source metadata.\n4. **VERIFY**: Apply trust scoring and route-specific quality checks.\n5. **FINALIZE**: Present ranked results or fallback status.\n\n### Transitions\n- If `--docs`, `--code`, `--web`, `--strict`, `--wide`, or `--gitlab` is provided, flags override classifier.\n- If docs route fails, fall back to web.\n- If web search needs fetch escalation, use `oma search fetch` strategies.\n- If query is purely local, use Serena MCP instead of web.\n\n### Failure and recovery\n- If primary route fails, fall forward to the next appropriate route.\n- If trust score is weak, label it instead of hiding uncertainty.\n- If no reliable results exist, report that and suggest a narrower query.\n\n### Exit\n- Success: results are routed, trust-scored, and source-grounded.\n- Partial success: route failures or trust limitations are explicit.\n\n## Logical Operations\n\n### Actions\n| Action | SSL primitive | Evidence |\n|--------|---------------|----------|\n| Parse query and flags | `READ` | User request |\n| Classify intent | `SELECT` | Intent rules |\n| Dispatch search route | `CALL_TOOL` | Docs, web, code, local tools |\n| Collect results | `READ` | Search outputs |\n| Score trust | `VALIDATE` | Trust registry |\n| Rank and format | `INFER` | Relevance and trust |\n| Report results | `NOTIFY` | Final answer |\n\n### Tools and instruments\n- Context7 docs tools\n- Runtime-native web search\n- `oma search` CLI primitives: `fetch`, `code`, `trust`, `api`, `api:search`, `meta`, `rss`, `rss:google`, `media`, `archive`, `doctor`\n- Serena MCP for local project search\n\n### Canonical command path\n```bash\noma search code \"\u003Cquery>\" [--host gitlab] [--language \u003Clang>] [--repo \u003Cowner\u002Frepo>]\noma search trust \u003Cdomain>\noma search fetch \u003Curl>\n```\n\nFor docs and web routes, use the runtime's available official-docs or web-search tools after classifying intent; do not duplicate routes unless the intent is ambiguous.\n\n### Resource scope\n| Scope | Resource target |\n|-------|-----------------|\n| `NETWORK` | Web\u002Fdocs\u002Fsource-code search targets |\n| `CODEBASE` | Local files when local search is selected |\n| `PROCESS` | `gh`, `glab`, and CLI search commands |\n| `MEMORY` | Query classification, trust labels, selected results |\n\n### Preconditions\n- Query and route constraints are clear enough to classify.\n- Required search tools are available or fallback is possible.\n\n### Effects and side effects\n- Performs external searches or local code searches.\n- Produces ranked references that may influence downstream implementation or research.\n\n### Guardrails\n1. **Classify intent before searching**: every query goes through IntentClassifier first\n2. **One query, one best route**: avoid redundant multi-route unless intent is ambiguous\n3. **Trust score every result**: all non-local results get domain trust labels via `oma search trust \u003Cdomain>` (single source: `cli\u002Fcommands\u002Fsearch\u002Ftrust.ts`)\n4. **Flags override classifier**: user-provided flags (`--docs`, `--code`, `--web`, `--strict`, `--wide`, `--gitlab`) always take precedence\n5. **Fail forward**: if primary route fails, fall back gracefully (docs->web, web->`oma search fetch` strategies)\n6. **No additional MCP required**: Context7 for docs, runtime native for web, CLI for code, Serena for local\n7. **Vendor-agnostic web search**: use whatever the current runtime provides (WebSearch, Google, Bing)\n8. **Domain-level trust only**: do not attempt sub-path or page-level scoring\n\n### Routes\n\n| Route | Primary Tool | Fallback | Trigger |\n|-------|-------------|----------|---------|\n| `docs` | Context7 MCP (`resolve-library-id` → `query-docs`) | `web` route | Official docs, API reference |\n| `web` | Runtime native search | `oma search fetch` (api\u002Fprobe\u002Fimpersonate\u002Fbrowser) | Tutorials, examples, solutions |\n| `code` | `oma search code` (wraps `gh` \u002F `glab`) | (none) | Implementation patterns, repos |\n| `local` | Serena MCP (delegate) | (none) | Current project files, symbols |\n\n### Default Workflow\n1. **Parse**: Extract query, detect flags, classify intent\n2. **Route**: Dispatch to the appropriate search channel(s)\n3. **Collect**: Gather results from dispatched routes\n4. **Score**: Attach trust labels to each result domain\n5. **Present**: Format and rank results for the user\n\n### Invocation\n\n#### Standalone\n```\n\u002Foma-search \"React Server Components streaming\"\n\u002Foma-search --docs \"Next.js middleware\"\n\u002Foma-search --code \"PKCE implementation\"\n\u002Foma-search --strict \"JWT refresh token rotation\"\n```\n\n#### Shared Infrastructure (from other skills)\nOther skills reference oma-search by specifying intent and query:\n1. State intent: `docs` | `web` | `code` | `local`\n2. Pass query string\n3. Use Trust Score in results to weigh source reliability\n\n## References\nFollow `resources\u002Fexecution-protocol.md` step by step.\nSee `resources\u002Fexamples.md` for input\u002Foutput examples.\nUse `resources\u002Fintent-rules.md` for intent classification reference.\nUse `resources\u002Ftrust-registry.md` for domain trust scoring reference.\nBefore submitting, run `resources\u002Fchecklist.md`.\nVendor-specific execution protocols are injected automatically by `oma agent spawn`.\nSource files live under `..\u002F_shared\u002Fruntime\u002Fexecution-protocols\u002F{vendor}.md`.\n- Execution steps: `resources\u002Fexecution-protocol.md`\n- Intent classification: `resources\u002Fintent-rules.md`\n- Trust registry: `resources\u002Ftrust-registry.md`\n- Examples: `resources\u002Fexamples.md`\n- Checklist: `resources\u002Fchecklist.md`\n- Error recovery: `resources\u002Ferror-playbook.md`\n- Context loading: `..\u002F_shared\u002Fcore\u002Fcontext-loading.md`\n- Context budget: `..\u002F_shared\u002Fcore\u002Fcontext-budget.md`\n- Lessons learned: `..\u002F_shared\u002Fcore\u002Flessons-learned.md`\n","# Search Agent - Intent-Based Search Router\n\n## Scheduling\n\n### Goal\nClassify information-seeking requests, route them to the best search channel, attach trust labels, and return source-grounded results.\n\n### Intent signature\n- User asks to search, find, look up, reference docs, inspect official documentation, search GitHub\u002FGitLab code, or gather web research.\n- Another skill needs reusable search infrastructure with trust scoring.\n\n### When to use\n- Finding official library\u002Fframework documentation\n- Web research for tutorials, examples, comparisons, and solutions\n- Searching GitHub\u002FGitLab code for implementation patterns\n- Any query where the search channel is unclear (auto-routing)\n- Other skills needing search infrastructure (shared invocation)\n\n### When NOT to use\n- Local codebase exploration only -> use Serena MCP directly\n- Git history or blame analysis -> use SCM Agent\n- Full architecture research -> use Architecture Agent (may invoke this skill internally)\n\n### Expected inputs\n- Query string, intent hint, or explicit flags such as `--docs`, `--code`, `--web`, `--strict`, `--wide`, `--gitlab`\n- Optional required source type, recency, domain, or trust constraints\n\n### Expected outputs\n- Ranked search results with route, source, trust label, and concise relevance summary\n- Fallback explanation when primary route fails\n- Source links or references suitable for the calling skill\n\n### Dependencies\n- Context7 MCP for docs, runtime-native web search, `gh`\u002F`glab` for code, Serena for local search\n- `resources\u002Fintent-rules.md`, `resources\u002Ftrust-registry.md`, execution protocol, examples, and checklist\n\n### Control-flow features\n- Branches by classified intent, user flags, route success\u002Ffailure, and trust constraints\n- May call web\u002Fdocs\u002Fcode\u002Flocal tools\n- Scores domains at domain level only\n\n## Structural Flow\n\n### Entry\n1. Parse the query and flags.\n2. Classify the search intent.\n3. Select one best route unless ambiguity or flags justify more.\n\n### Scenes\n1. **PREPARE**: Parse query and classify route.\n2. **ACT**: Dispatch to docs, web, code, or local search.\n3. **ACQUIRE**: Collect search results and source metadata.\n4. **VERIFY**: Apply trust scoring and route-specific quality checks.\n5. **FINALIZE**: Present ranked results or fallback status.\n\n### Transitions\n- If `--docs`, `--code`, `--web`, `--strict`, `--wide`, or `--gitlab` is provided, flags override classifier.\n- If docs route fails, fall back to web.\n- If web search needs fetch escalation, use `oma search fetch` strategies.\n- If query is purely local, use Serena MCP instead of web.\n\n### Failure and recovery\n- If primary route fails, fall forward to the next appropriate route.\n- If trust score is weak, label it instead of hiding uncertainty.\n- If no reliable results exist, report that and suggest a narrower query.\n\n### Exit\n- Success: results are routed, trust-scored, and source-grounded.\n- Partial success: route failures or trust limitations are explicit.\n\n## Logical Operations\n\n### Actions\n| Action | SSL primitive | Evidence |\n|--------|---------------|----------|\n| Parse query and flags | `READ` | User request |\n| Classify intent | `SELECT` | Intent rules |\n| Dispatch search route | `CALL_TOOL` | Docs, web, code, local tools |\n| Collect results | `READ` | Search outputs |\n| Score trust | `VALIDATE` | Trust registry |\n| Rank and format | `INFER` | Relevance and trust |\n| Report results | `NOTIFY` | Final answer |\n\n### Tools and instruments\n- Context7 docs tools\n- Runtime-native web search\n- `oma search` CLI primitives: `fetch`, `code`, `trust`, `api`, `api:search`, `meta`, `rss`, `rss:google`, `media`, `archive`, `doctor`\n- Serena MCP for local project search\n\n### Canonical command path\n```bash\noma search code \"\u003Cquery>\" [--host gitlab] [--language \u003Clang>] [--repo \u003Cowner\u002Frepo>]\noma search trust \u003Cdomain>\noma search fetch \u003Curl>\n```\n\nFor docs and web routes, use the runtime's available official-docs or web-search tools after classifying intent; do not duplicate routes unless the intent is ambiguous.\n\n### Resource scope\n| Scope | Resource target |\n|-------|-----------------|\n| `NETWORK` | Web\u002Fdocs\u002Fsource-code search targets |\n| `CODEBASE` | Local files when local search is selected |\n| `PROCESS` | `gh`, `glab`, and CLI search commands |\n| `MEMORY` | Query classification, trust labels, selected results |\n\n### Preconditions\n- Query and route constraints are clear enough to classify.\n- Required search tools are available or fallback is possible.\n\n### Effects and side effects\n- Performs external searches or local code searches.\n- Produces ranked references that may influence downstream implementation or research.\n\n### Guardrails\n1. **Classify intent before searching**: every query goes through IntentClassifier first\n2. **One query, one best route**: avoid redundant multi-route unless intent is ambiguous\n3. **Trust score every result**: all non-local results get domain trust labels via `oma search trust \u003Cdomain>` (single source: `cli\u002Fcommands\u002Fsearch\u002Ftrust.ts`)\n4. **Flags override classifier**: user-provided flags (`--docs`, `--code`, `--web`, `--strict`, `--wide`, `--gitlab`) always take precedence\n5. **Fail forward**: if primary route fails, fall back gracefully (docs->web, web->`oma search fetch` strategies)\n6. **No additional MCP required**: Context7 for docs, runtime native for web, CLI for code, Serena for local\n7. **Vendor-agnostic web search**: use whatever the current runtime provides (WebSearch, Google, Bing)\n8. **Domain-level trust only**: do not attempt sub-path or page-level scoring\n\n### Routes\n\n| Route | Primary Tool | Fallback | Trigger |\n|-------|-------------|----------|---------|\n| `docs` | Context7 MCP (`resolve-library-id` → `query-docs`) | `web` route | Official docs, API reference |\n| `web` | Runtime native search | `oma search fetch` (api\u002Fprobe\u002Fimpersonate\u002Fbrowser) | Tutorials, examples, solutions |\n| `code` | `oma search code` (wraps `gh` \u002F `glab`) | (none) | Implementation patterns, repos |\n| `local` | Serena MCP (delegate) | (none) | Current project files, symbols |\n\n### Default Workflow\n1. **Parse**: Extract query, detect flags, classify intent\n2. **Route**: Dispatch to the appropriate search channel(s)\n3. **Collect**: Gather results from dispatched routes\n4. **Score**: Attach trust labels to each result domain\n5. **Present**: Format and rank results for the user\n\n### Invocation\n\n#### Standalone\n```\n\u002Foma-search \"React Server Components streaming\"\n\u002Foma-search --docs \"Next.js middleware\"\n\u002Foma-search --code \"PKCE implementation\"\n\u002Foma-search --strict \"JWT refresh token rotation\"\n```\n\n#### Shared Infrastructure (from other skills)\nOther skills reference oma-search by specifying intent and query:\n1. State intent: `docs` | `web` | `code` | `local`\n2. Pass query string\n3. Use Trust Score in results to weigh source reliability\n\n## References\nFollow `resources\u002Fexecution-protocol.md` step by step.\nSee `resources\u002Fexamples.md` for input\u002Foutput examples.\nUse `resources\u002Fintent-rules.md` for intent classification reference.\nUse `resources\u002Ftrust-registry.md` for domain trust scoring reference.\nBefore submitting, run `resources\u002Fchecklist.md`.\nVendor-specific execution protocols are injected automatically by `oma agent spawn`.\nSource files live under `..\u002F_shared\u002Fruntime\u002Fexecution-protocols\u002F{vendor}.md`.\n- Execution steps: `resources\u002Fexecution-protocol.md`\n- Intent classification: `resources\u002Fintent-rules.md`\n- Trust registry: `resources\u002Ftrust-registry.md`\n- Examples: `resources\u002Fexamples.md`\n- Checklist: `resources\u002Fchecklist.md`\n- Error recovery: `resources\u002Ferror-playbook.md`\n- Context loading: `..\u002F_shared\u002Fcore\u002Fcontext-loading.md`\n- Context budget: `..\u002F_shared\u002Fcore\u002Fcontext-budget.md`\n- Lessons learned: `..\u002F_shared\u002Fcore\u002Flessons-learned.md`\n",{"name":5,"description":7},"main","6725f57d555e82c2be2d17e092ad1291b20f56f0",".agents\u002Fskills\u002Foma-search",0,"https:\u002F\u002Fgithub.com\u002Fmrmarbury\u002FPalmSync4Mac","https:\u002F\u002Fgithub.com\u002Fmrmarbury","FreeBSD admin, Elixir & Erlang Dev, Rubyist, Skateboarder, Musician","2026-11-07 06:23:43",{"source":8,"skillName":5,"commands":53,"prompt":63,"zipAvailable":64},[54,57,60],{"tool":55,"command":56},"npx","npx skills add mrmarbury\u002FPalmSync4Mac --skill oma-search",{"tool":58,"command":59},"bunx","bunx skills add mrmarbury\u002FPalmSync4Mac --skill oma-search",{"tool":61,"command":62},"pnpm","pnpm dlx skills add mrmarbury\u002FPalmSync4Mac --skill oma-search","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Fmrmarbury\u002FPalmSync4Mac\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Foma-search\u002FSKILL.md",true,[66,72,76,80,84,88],{"path":67,"resourceType":68,"resourceTypeDesc":69,"sizeBytes":70,"sourceHtmlUrl":71},"resources\u002Fchecklist.md","REFERENCE","参考文档",1653,"https:\u002F\u002Fgithub.com\u002Fmrmarbury\u002FPalmSync4Mac\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Foma-search\u002Fresources\u002Fchecklist.md",{"path":73,"resourceType":68,"resourceTypeDesc":69,"sizeBytes":74,"sourceHtmlUrl":75},"resources\u002Ferror-playbook.md",5247,"https:\u002F\u002Fgithub.com\u002Fmrmarbury\u002FPalmSync4Mac\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Foma-search\u002Fresources\u002Ferror-playbook.md",{"path":77,"resourceType":68,"resourceTypeDesc":69,"sizeBytes":78,"sourceHtmlUrl":79},"resources\u002Fexamples.md",4329,"https:\u002F\u002Fgithub.com\u002Fmrmarbury\u002FPalmSync4Mac\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Foma-search\u002Fresources\u002Fexamples.md",{"path":81,"resourceType":68,"resourceTypeDesc":69,"sizeBytes":82,"sourceHtmlUrl":83},"resources\u002Fexecution-protocol.md",4588,"https:\u002F\u002Fgithub.com\u002Fmrmarbury\u002FPalmSync4Mac\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Foma-search\u002Fresources\u002Fexecution-protocol.md",{"path":85,"resourceType":68,"resourceTypeDesc":69,"sizeBytes":86,"sourceHtmlUrl":87},"resources\u002Fintent-rules.md",2773,"https:\u002F\u002Fgithub.com\u002Fmrmarbury\u002FPalmSync4Mac\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Foma-search\u002Fresources\u002Fintent-rules.md",{"path":89,"resourceType":68,"resourceTypeDesc":69,"sizeBytes":90,"sourceHtmlUrl":91},"resources\u002Ftrust-registry.md",5045,"https:\u002F\u002Fgithub.com\u002Fmrmarbury\u002FPalmSync4Mac\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Foma-search\u002Fresources\u002Ftrust-registry.md",[93,118,148,173,200,229],{"skillNo":94,"name":95,"nameZh":6,"description":96,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":97,"categories":98,"keywords":99,"publishedAt":39},"01M6WJZMN4HV76T0Y2PYDAAD7Q","oma-translator","Context-aware translation that preserves tone, style, and natural word order. Use when translating UI strings, documentation, marketing copy, or any multilingual content. Infers register, domain, and style from the source text and surrounding codebase context.","https:\u002F\u002Fgithub.com\u002Fmrmarbury\u002FPalmSync4Mac\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Foma-translation\u002FSKILL.md",[],[100,101,102,103,104,105,106,107,23,108,109,25,110,111,112,113,114,115,116,117],"translator","oma translator","documentation","ui","marketing","Word","text","context","multilingual","translation","tone","style","register","copy","strings","source","codebase","when",{"skillNo":119,"name":120,"nameZh":6,"description":121,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":122,"categories":123,"keywords":129,"publishedAt":39},"01M6WJZ5W60XSDDE72AW5E85GT","oma-skill-creator","Create or update OMA skills in the SSL-lite human-readable format. Use when adding a new `.agents\u002Fskills\u002F{skill-name}\u002FSKILL.md`, converting an existing skill to the standardized Scheduling \u002F Structural Flow \u002F Logical Operations \u002F References structure, or validating whether a skill has enough routing, execution, resource, and safety detail.","https:\u002F\u002Fgithub.com\u002Fmrmarbury\u002FPalmSync4Mac\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Foma-skill-creation\u002FSKILL.md",[124],{"categoryNo":125,"categoryName":126,"taxonomyType":127,"taxonomyTypeDesc":128},"01JBSEEDCAT000000000000023","Skill与智能体开发","SCENARIO","使用场景",[130,131,132,133,134,135,136,137,138,139,23,140,141,142,143,144,145,146,147,117],"skill creator","oma skill creator","creator","create","update","routing","ssl","flow","execution","Safety","scheduling","references","existing skill","structure","human","structural","detail","Existing",{"skillNo":149,"name":150,"nameZh":6,"description":151,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":152,"categories":153,"keywords":155,"publishedAt":39},"01M6WJYHKKTDG9RT9A6ZWCT29A","oma-orchestrator","Automated multi-agent orchestrator that spawns CLI subagents in parallel, coordinates via MCP Memory, and monitors progress. Use for orchestration, parallel execution, and automated multi-agent workflows.","https:\u002F\u002Fgithub.com\u002Fmrmarbury\u002FPalmSync4Mac\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Foma-orchestration\u002FSKILL.md",[154],{"categoryNo":125,"categoryName":126,"taxonomyType":127,"taxonomyTypeDesc":128},[156,157,158,159,160,161,162,138,163,164,165,23,166,167,168,169,170,171,172,24],"oma orchestrator","orchestrator","MCP","cli","memory","orchestration","workflows","multi-agent","parallel","subagents","agent orchestrator","parallel execution","coordinates","agent workflows","progress","via","multi",{"skillNo":174,"name":175,"nameZh":6,"description":176,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":177,"categories":178,"keywords":182,"publishedAt":39},"01M6WJXXDQ99RCQ3S4GW5D42Q4","oma-explainer","Turn a code change (diff, PR, branch, commit range) into a rich, self-contained interactive HTML explainer with Background \u002F Intuition \u002F Code \u002F Quiz sections. Use for explain, walkthrough, code-change explanation, diff\u002FPR\u002Fbranch explainer requests — 설명서, 해설, コード解説, 代码讲解. Produces a single offline-capable HTML file with diagrams, callouts, and an accessible quiz.","https:\u002F\u002Fgithub.com\u002Fmrmarbury\u002FPalmSync4Mac\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Foma-explanation\u002FSKILL.md",[179],{"categoryNo":180,"categoryName":181,"taxonomyType":127,"taxonomyTypeDesc":128},"01JBSEEDCAT000000000000009","前端开发",[183,184,185,186,187,35,188,189,190,191,192,23,193,194,195,196,197,24,198,199],"explainer","oma explainer","change","commit","pr","offline","file","walkthrough","branch","interactive","html","diff","diagrams","self","quiz","rich","single",{"skillNo":201,"name":202,"nameZh":6,"description":203,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":204,"categories":205,"keywords":209,"publishedAt":39},"01M6WJWQC0CTFQWQKQ2EZYXVGJ","oma-academic-writer","Academic writing specialist for publication-grade English prose. Drafts, revises, and audits essays, reports, analysis sections, executive summaries, conclusions, and literature reviews while enforcing sentence-structure variation, high-frequency academic verbs, calibrated hedging, and anti-AI stylistic compliance. USE for academic writing, essay polish, paragraph rewrite, prose revision against any rubric tier (HD\u002FD\u002FC, A\u002FB\u002FC, top-band\u002Fmid-band, etc.), anti-AI audit, reverse outlining, claim-evidence mapping, and rubric enforcement on assignments.","https:\u002F\u002Fgithub.com\u002Fmrmarbury\u002FPalmSync4Mac\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Foma-academic-writing\u002FSKILL.md",[206],{"categoryNo":207,"categoryName":208,"taxonomyType":127,"taxonomyTypeDesc":128},"01JBSEEDCAT000000000000018","写作与文案",[210,211,212,213,214,215,216,217,218,219,220,143,221,222,223,224,225,226,227,228],"oma academic writer","writer","Academic","academic writer","writing","audit","analysis","polish","reports","ai audit","claim","Anti-AI","english","literature","essays","essay","reviews","drafts","top",{"skillNo":230,"name":231,"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":232,"categories":233,"keywords":234,"publishedAt":39},"01M6BYY6K38NQSE2BXHWM0ZGRC","work","https:\u002F\u002Fgithub.com\u002Fmrmarbury\u002FPalmSync4Mac\u002Fblob\u002Fmain\u002F.opencode\u002Fskills\u002Fwork\u002FSKILL.md",[],[231]]