Skip to main content
skill CX Codex

oma-search · first-fluke, research — Claude Code skill: what it does, how to install

oma-search — a skill for Claude Code and Codex that routes queries across external documentation, web search, and remote code. It picks the matching retrieval channel and returns answers backed by citations.

MIT ★ 1,472 updated 2026-11-12

Install into Claude Code · Plugin marketplace All methods and platforms ↓
/plugin marketplace add first-fluke/oh-my-agent
/plugin install oma-research@oh-my-agent
Open on GitHub

What oma-search does

The skill functions inside Claude Code and Codex, dividing external retrieval into four explicit routes: docs, web, code, and fetch. It queries Context7 for library documentation, routes web questions to native, brave, or exa providers, and searches remote code across GitHub or GitLab. Requests dealing purely with local repository files bypass this skill and route directly to local code tools.

Every result carries metadata about the actual provider, source constraints, reading status, and observed version limits. When an explicit web provider fails authentication or hits rate limits, the skill surfaces that failure directly instead of quietly falling back to native search.

Passing the --strict modifier limits acceptance strictly to primary or official material. If no source meets that bar, the skill reports the evidence gap rather than substituting broader unverified pages.

What it helps with

  • locate official library documentation pinned to an exact version
  • search remote GitHub or GitLab repositories for code examples
  • retrieve and inspect content from a specific web address
  • run web research through Brave or Exa with citation tracking

Example prompts for the agent

  • Find API route documentation using the --docs flag
  • Search remote GitLab repositories: oma search code "auth middleware" --host gitlab --language go
  • Read and evaluate the external page at <url> using the fetch route

How to install oma-search

1Plugin marketplace

/plugin marketplace add first-fluke/oh-my-agent
/plugin install oma-research@oh-my-agent

This installs the whole oma-research plugin with all its skills

2Skills CLI (Vercel)

npx skills add first-fluke/oh-my-agent --skill oma-search -a claude-code

3Manually: put the files in place

~/.claude/skills/oma-search/SKILL.md

Copy the whole skill folder; for one project use .claude/skills/oma-search/

Step by step, with commands for each platform: How to install skills in Claude Code: five ways

Questions about oma-search

How do I install oma-search in Claude Code?

Add the repository with /plugin marketplace add first-fluke/oh-my-agent, then run /plugin install oma-research@oh-my-agent.

What does oma-search do?

It acts as a search router that sends queries to documentation engines, web search providers, remote code hosts, or a direct URL reader.

How does oma-search handle the --strict modifier?

It insists on verified official or primary references. When those cannot be confirmed, it returns an evidence gap instead of loosening constraints.

Source text

SKILL.md · MIT
---
name: oma-search
description: Find external documentation, web sources, or remote code with
  citations. Local code navigation uses the configured code tools.
---

# Search Router

## Scheduling

### Goal
Select the search or retrieval channel needed by the request and return sources
with supporting evidence and retrieval limits.

### Intent signature
- Find external documentation, web information, or remote implementation examples.
- Read a known external URL or supply external sources to another skill.

### When to use
Library documentation, web research, remote code search, known-URL reading, and
requests whose external source channel needs selection.

### When NOT to use
- Pure local code exploration -> use configured code intelligence directly under
  `../_shared/core/code-intelligence.md`; do not dispatch this skill.
- Git history/blame -> `oma-scm`; architecture analysis -> `oma-architecture`.

### Expected inputs
Query or known URL; optional route hint (`docs`, `web`, `code`, `fetch`); version,
recency, host, repository and source constraints; optional web-provider override.
Explicit `--docs`, `--code` or `--web` selects the search route. `--gitlab` selects
the remote code host. `--strict` requires suitable primary or official sources
with inspected supporting content; `--wide` includes broader results with their
limitations. These modifiers preserve the request's source constraints.

### Expected outputs
An answer or relevant source list with source URL/file reference, route, actual
provider, source type, content-read status, supporting evidence and material
limitations. Include publication, retrieval and version details when observed.
Do not invent results, dates, sources or certainty.

### Dependencies
Context7 for documentation; the configured `providers.web` (`native`, `brave` or
`exa`) for web discovery; `oma search code`/`gh`/`glab` for remote code; runtime
retrieval tools or `oma search fetch` for known URLs. `oma search providers`
reports registration, selection and credential metadata; `oma doctor` checks
credential presence without verifying validity or API reachability.

## Structural Flow

### Routes
| Route | Execution | Scope |
|---|---|---|
| `docs` | Context7 library resolution and queries; official-site discovery when needed | Official documentation within requested version constraints |
| `web` | Selected web provider: runtime tools for `native`, CLI adapter for `brave` or `exa` | Discover URLs relevant to a query |
| `code` | `oma search code` through the selected code host | Remote implementation matches within host/repository constraints |
| `fetch` | Available URL reader/browser or `oma search fetch <url>` | Read a URL already supplied or discovered |

### Failure and recovery
- Missing/empty documentation lookup: use official-site discovery while retaining
  the documentation route's version and source limits.
- Selected web provider unavailable, unauthenticated or rate-limited: report its
  failure. Do not silently replace an explicit provider choice with native search.
- Search returns no candidate URLs: refine within the original constraints or
  report no result. URL retrieval cannot replace missing search results.
- A known URL cannot be read: use the retrieval-specific recovery reference and
  preserve access/authentication errors and archive provenance.
- No source meets `--strict`: report the source or evidence gap. A broader result
  set does not automatically satisfy the strict request.

### Exit
Return supported results and disclose failed routes, unread sources, stale or
archived content, and version limits. A provider name or domain label does not
verify an individual claim.

## Logical Operations

### Canonical workflow path
1. Resolve the requested outcome and constraints. Hand pure local-code requests
   directly to configured code intelligence. For external work, select one primary
   route; use `resources/intent-rules.md` only when selection is unclear.
   Record the route and web provider with subject `search.route-selection` per
   `../_shared/runtime/route-selection.md` (explicit flag or the outcome that
   decided it). Record an added route the same way when the evidence gap needs it.
2. Execute that route using `resources/execution-protocol.md`. Resolve the web
   provider from configuration or the request override. Add another route only
   when the remaining evidence gap needs it; do not fan out by default.
3. Read the relevant content needed to support the answer. Retain URLs and
   inspection status, deduplicate results, and apply source/version constraints.
   Use `resources/trust-registry.md` for provenance rules or an explicitly needed
   optional domain diagnostic; no numeric lookup is required for ordinary results.
4. Rank by relevance and source suitability for the question. Return the requested
   answer or sources with evidence, the actual route/provider and material limits.

### CLI entry points
```bash
oma search providers
oma search web "<query>" [--provider <id>] [--limit <n>]
oma search code "<query>" [--host gitlab] [--language <lang>] [--repo <owner/repo>]
oma search fetch <url>
oma search trust <domain>
```
Use `api`, `rss`, `meta`, `media`, `archive` or `doctor` only when the selected
operation needs that primitive. `trust` remains an optional domain diagnostic.

### Guardrails
- Preserve explicit route, provider, source, host, version and date constraints.
- Keep query discovery separate from reading an existing URL.
- Treat search snippets and excerpts as limited evidence; identify unread sources.
- Do not manufacture trust scores or promote Context7/GitHub results to claim-level
  verification based on their provider or hosting domain.
- Do not repeat successful routes, search local project files via the web, install
  a provider or track a repository automatically.

### Resource scope and effects
Search may contact external services and spawn configured provider or code-host
processes. Retrieval may launch an available browser. Query constraints and
provenance are session context; persistent caches belong in generated state, not
skill definitions. Local source navigation belongs to the configured code tools.

## References
- Route selection: `resources/intent-rules.md` (unclear external request)
- Execution: `resources/execution-protocol.md` (selected route only)
- Provenance and optional domain diagnostics: `resources/trust-registry.md` (source/evidence interpretation)
- Recovery: `resources/error-playbook.md` (route failure)
- Result checks: `resources/checklist.md` (applicable source and evidence checks)
- Examples: `resources/examples.md` (unfamiliar input or boundary)
- Local-code handoff: `../_shared/core/code-intelligence.md` (local requests)

© First Fluke · MIT · first-fluke/oh-my-agent

Similar skills

All skills for Agent setup: memory, context, orchestration →

oma-search by other authors comes first.

oma-search First Fluke The oma-search skill picks a search channel for docs, web research, code, or local project files, then labels external sources by domain trust. Use it when the right place to search is unclear. CX Codex +1 ★ 1,472repo stars github-search parcadei A skill for Claude Code, Codex, Cursor, GitHub Copilot, and Gemini CLI that queries GitHub code, repositories, issues, and pull requests through MCP. It accepts a search type and a query string with full GitHub Search syntax. CX Codex +1 746installs search-docs imagekit-developer Teaches the agent how to build effective queries for the search_docs tool and pick the right ImageKit documentation sources. CX Codex +1 511installs docs-search adobe docs-search searches aem.live docs, ranks pages by relevance, and pulls full articles with code samples. Use it when a regular web search gives you nothing on Edge Delivery Services. CX Codex +1 1,700installs Vascue Public Knowledge Search vascue-io Vascue Public Knowledge Search enables AI assistants to retrieve verified excerpts from public Vascue technical guides, pricing pages, and Cliniko workflow documentation. CX Codex +1 exa-search affaan-m exa-search is a Claude Code skill that searches the web, code examples, company information, and professional profiles through Exa. The agent activates it for lookup requests or background research. CX Codex +1 6,300installs youtube-search ZeroPointRepo youtube-search — a Claude Code skill that searches YouTube videos, channels and playlists through TranscriptAPI, then pulls transcripts for what it finds. Kick it off when research needs video sources, not just written ones. CX Codex +1 1,100installs

From the same set69

The whole set →
oma-skill-creation oma-skill-creation is a Claude Code skill for building and refining OMA skills in SSL-lite format for Claude Code and Codex. It runs during authoring, routing reviews, and contract validation. CX Codex +1 ★ 1,472repo stars oma-mobile oma-mobile — a mobile-focused skill: it builds screens and widgets in Flutter or React Native, wires camera, GPS, push and offline handling, then runs the checks. CX Codex +1 ★ 1,472repo stars oma-debug oma-debug — a skill for Claude Code and Codex isolates bugs, writes targeted fixes, and creates regression tests. Runs when tests fail, services crash, or code suffers from race conditions. CX Codex +1 ★ 1,472repo stars oma-qa The oma-qa skill for Claude Code and Codex reviews changes for security, performance, accessibility, and correctness. It checks a diff, runs relevant tools, and reports reproducible findings with fixes. CX Codex +1 ★ 1,472repo stars oma-pm oma-pm is a Claude Code skill that turns product requirements into a prioritized task plan with dependencies and acceptance criteria. It prepares the plan before work is handed to specialist agents. CX Codex +1 ★ 1,472repo stars oma-brainstorm oma-brainstorm — a skill for exploring intent, constraints, and alternative approaches before planning or coding. Use it when you have an idea but the path forward is unclear. CX Codex +1 ★ 1,472repo stars oma-pm oma-pm — a skill for Claude Code and Codex decomposes product requirements into scoped tasks with dependencies and acceptance criteria. Generates plan artifacts for specialist agents and orchestrators. CX Codex +1 ★ 1,472repo stars oma-design oma-design resolves a project's design direction and maintains DESIGN.md as the visual contract. Picks an external design skill — Interface Design, Taste, or Impeccable — for the task at hand. CX Codex +1 ★ 1,472repo stars

Project sponsors

Companies that keep this analytics open