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.

Quality

86%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Low

Low-risk findings worth noting

Quality

Content

73%Weight 40%Scale 1-5

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

The body is well-structured with executable commands, clear routing logic, and explicit validation/recovery checkpoints. Its main weakness is redundancy — the core workflow is restated several times — and references to a resources/ bundle that is not actually present.

Suggestions

Collapse the Scenes, Default Workflow, Actions, and Structural Flow sections into a single canonical pipeline to remove the repeated restatements of the same five steps.

Dedupe the 'flags override classifier' rule so it appears once (e.g., in Transitions) rather than in Transitions, Guardrails, and Routes.

Provide a concrete invocation example for the docs and web routes (not just 'runtime's available tools') to make every route copy-paste-ready, or confirm the referenced resources/*.md files exist and are reachable.

Dimension	Reasoning	Score
Conciseness	Per-section content is efficient, but the same five-step search process is restated across Scenes, Default Workflow, Actions, and Structural Flow, and the 'flags override classifier' rule is repeated in Transitions, Guardrails, and Routes — noticeable redundancy rather than just minor trimmable over-explanation.	3 / 5
Actionability	Provides concrete executable commands (`oma search code`, `oma search trust`, `oma search fetch`) with flags and a routes table specifying tools and fallbacks; the docs/web routes lean on 'runtime's available tools' without an exact invocation, a minor gap keeping it below fully copy-paste-ready.	4 / 5
Workflow Clarity	The process is clearly sequenced (Entry/Scenes/Transitions/Exit plus Parse/Route/Collect/Score/Present) with an explicit VERIFY checkpoint, trust-scoring validation, fallback feedback loops (docs->web->fetch), and a submission checklist reference.	5 / 5
Progressive Disclosure	A clear one-level-deep References section points to execution-protocol, examples, intent-rules, trust-registry, checklist, and error-playbook files, but inlined guardrails/routes/actions/scenes could live in those files and the referenced resources/ files are not present in the bundle, leaving minor organization gaps.	4 / 5
	Total	16 / 20 Passed

Description

100%Weight 40%Scale 1-5

Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.

A strong description: third-person voice, concrete capabilities, explicit trigger phrases, and a clearly distinct niche. It answers both what the skill does and when to use it without fluff or over-claims.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions — routing queries, attaching trust labels, and enumerating four specific channels (Context7 docs, native web search, gh/glab code, Serena local) — matching the comprehensive-coverage anchor.	5 / 5
Completeness	Explicitly answers both what (routes queries to channels and attaches domain trust labels) and when (concrete 'Use for...' trigger phrases), matching the anchor for clearly answering both.	5 / 5
Trigger Term Quality	The 'Use for search, find, lookup, reference, docs, code search, and web research' clause provides comprehensive natural keywords with synonyms (search/find/lookup) that users would actually say.	5 / 5
Distinctiveness Conflict Risk	The intent-based search-router niche with named channels and trust scoring is a clear, distinct trigger set with minimal overlap risk against other skills.	5 / 5
	Total	20 / 20 Passed

Validation

100%

Warnings & errors only

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository: first-fluke/oh-my-agent
Path: .agents/skills/oma-search/SKILL.md
Commit: 032c988

Reviewed: 2 days ago

Table of Contents

Discovery Implementation Validation

Is this your skill?

If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.