Oma Search | Skills Pool
Oma Search Intent-based search router with trust scoring. Routes queries to optimal channels (Context7 docs, native web search, gh/glab code search, Serena local) and attaches domain trust labels. Use for search, find, lookup, reference, docs, code search, and web research.
first-fluke 667 estrellas 16 abr 2026 Ocupación Categorías Herramientas de Dominio y DNS Contenido de la habilidad
Search Agent - Intent-Based Search Router
When to use
Finding official library/framework documentation
Web research for tutorials, examples, comparisons, and solutions
Searching GitHub/GitLab code for implementation patterns
Any query where the search channel is unclear (auto-routing)
Other skills needing search infrastructure (shared invocation)
When NOT to use
Local codebase exploration only -> use Serena MCP directly
Git history or blame analysis -> use SCM Agent
Full architecture research -> use Architecture Agent (may invoke this skill internally)
Core Rules
Classify intent before searching : every query goes through IntentClassifier firstOne query, one best route : avoid redundant multi-route unless intent is ambiguous
Instalación rápida
Oma Search npx skillvault add first-fluke/first-fluke-oh-my-agent-agents-skills-oma-search-skill-md
estrellas 667
Actualizado 16 abr 2026
Ocupación
Trust score every result : all non-local results get domain trust labels from the registry
Flags override classifier : user-provided flags (--docs, --code, --web, --strict, --wide, --gitlab) always take precedence
Fail forward : if primary route fails, fall back gracefully (docs->web, web->insane-search phases)
No additional MCP required : Context7 for docs, runtime native for web, CLI for code, Serena for local
Vendor-agnostic web search : use whatever the current runtime provides (WebSearch, Google, Bing)
Domain-level trust only : do not attempt sub-path or page-level scoring
Routes Route Primary Tool Fallback Trigger docsContext7 MCP (resolve-library-id → query-docs) web routeOfficial docs, API reference webRuntime native search insane-search 4-Phase Tutorials, examples, solutions codegh search code / glab api— Implementation patterns, repos localSerena MCP (delegate) — Current project files, symbols
Default Workflow
Parse — Extract query, detect flags, classify intentRoute — Dispatch to the appropriate search channel(s)Collect — Gather results from dispatched routesScore — Attach trust labels to each result domainPresent — Format and rank results for the user
Invocation
Standalone /oma-search "React Server Components streaming"
/oma-search --docs "Next.js middleware"
/oma-search --code "PKCE implementation"
/oma-search --strict "JWT refresh token rotation"
Shared Infrastructure (from other skills) Other skills reference oma-search by specifying intent and query:
State intent: docs | web | code | local
Pass query string
Use Trust Score in results to weigh source reliability
How to Execute Follow resources/execution-protocol.md step by step.
See resources/examples.md for input/output examples.
Use resources/intent-rules.md for intent classification reference.
Use resources/trust-registry.md for domain trust scoring reference.
Before submitting, run resources/checklist.md.
Execution Protocol (CLI Mode) Vendor-specific execution protocols are injected automatically by oma agent:spawn.
Source files live under ../_shared/runtime/execution-protocols/{vendor}.md.
References
Execution steps: resources/execution-protocol.md
Intent classification: resources/intent-rules.md
Trust registry: resources/trust-registry.md
Examples: resources/examples.md
Checklist: resources/checklist.md
Error recovery: resources/error-playbook.md
Context loading: ../_shared/core/context-loading.md
Context budget: ../_shared/core/context-budget.md
Lessons learned: ../_shared/core/lessons-learned.md
02
When to use