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

79%

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

Fix and improve this skill with Tessl

tessl review fix ./benchmarks/runs/oma/.agents/skills/oma-search/SKILL.md

Quality

Content

68%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 content is well-structured with clear routing tables, a sequenced scene-based workflow, and excellent progressive disclosure pointing to one-level-deep resources. Its main weakness is redundancy: routing, flags, and trust-scoring guidance is restated across multiple sections, inflating token usage without adding information.

Suggestions

Consolidate the route/flag/trust-scoring material that is repeated across Scheduling, Structural Flow, Logical Operations, Routes, and Default Workflow into a single authoritative section to reduce token cost.

Add concrete, executable examples for the docs and web routes (e.g., the Context7 resolve-library-id -> query-docs call sequence) rather than deferring to 'use the runtime's available tools'.

Specify the VERIFY checkpoint as a concrete validation step (e.g., the exact trust-score threshold or check command) instead of describing it abstractly.

Dimension	Reasoning	Score
Conciseness	Mostly efficient tables and lists, but the body repeats the same routing/flag/trust information across Scheduling, Structural Flow, Logical Operations, Routes, and Default Workflow sections, adding notable redundancy.	3 / 5
Actionability	Provides concrete executable commands for the code route (gh search code, glab api) and a clear default workflow, but docs/web routes rely on 'use the runtime's available tools' rather than executable specifics.	4 / 5
Workflow Clarity	Clear sequenced workflow (PREPARE/ACT/ACQUIRE/VERIFY/FINALIZE) with explicit failure/fallback transitions and a trust-scoring verification step, though checkpoints are described abstractly rather than as concrete validation commands.	4 / 5
Progressive Disclosure	Body is an overview that clearly signals one-level-deep references (resources/execution-protocol.md, intent-rules.md, trust-registry.md, examples.md, checklist.md, error-playbook.md), with detail appropriately split out and easy to navigate.	5 / 5
	Total	16 / 20 Passed

Description

90%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.

The description is strong: it concisely states what the skill does, names specific channels and trust labeling, and provides a rich set of natural trigger terms with an explicit 'Use for' clause. Minor overlap risk with general research skills keeps distinctiveness just below 5.

Dimension	Reasoning	Score
Specificity	Names concrete actions ('Routes queries to optimal channels', 'attaches domain trust labels') and enumerates four specific channels, though routing/labeling could be more granular.	4 / 5
Completeness	Explicitly answers both 'what' (intent-based search router with trust scoring) and 'when' via a clear 'Use for...' clause with concrete trigger phrases.	5 / 5
Trigger Term Quality	Comprehensive natural trigger list including synonyms and tool-specific variants: 'search, find, lookup, reference, docs, code search, and web research'.	5 / 5
Distinctiveness Conflict Risk	Clear niche (multi-channel search routing with trust labels) is fairly distinct, but broad search triggers could overlap marginally with general research or local-search skills.	4 / 5
	Total	18 / 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: benchmarks/runs/oma/.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.