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

75%

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 ./.agents/skills/oma-search/SKILL.md

Quality

Content

67%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.

A well-structured, actionable skill body with concrete commands and a clear scene-based workflow, weakened by redundant restatements of the same pipeline and references to resource files that are not present in the bundle.

Suggestions

Collapse the Scenes, Default Workflow, and Actions sections into a single canonical flow to remove triple restatement of the parse/route/collect/score/present pipeline.

Add an explicit validate->fix->retry feedback loop in the VERIFY/FINALIZE scenes (e.g. re-route on low trust or empty results) rather than only describing fall-forward.

Create the referenced resource files (resources/execution-protocol.md, intent-rules.md, trust-registry.md, examples.md, checklist.md, error-playbook.md) or remove the dangling references so navigation targets exist.

Dimension	Reasoning	Score
Conciseness	The body restates the same pipeline three times (Scenes, Default Workflow, and the Actions table all cover parse/route/collect/score/present), adding redundant tokens without new information; it does avoid explaining concepts Claude already knows.	3 / 5
Actionability	Provides concrete executable commands ('oma search code "<query>" [--host gitlab]', 'oma search trust <domain>', 'oma search fetch <url>'), a routes table with primary tools and fallbacks, and invocation examples, with only minor gaps around docs/web tool invocation specifics.	4 / 5
Workflow Clarity	Clear sequenced flow via Entry, the PREPARE/ACT/ACQUIRE/VERIFY/FINALIZE scenes, and explicit transitions/failure-recovery; the VERIFY scene is a checkpoint, though the validate->fix->retry loop is only weakly explicit.	4 / 5
Progressive Disclosure	References are clearly signaled and one level deep (execution-protocol, intent-rules, trust-registry, examples, checklist, error-playbook), but no bundle files actually exist and the SKILL.md inlines several tables/guardrails that could live in those references.	4 / 5
	Total	15 / 20 Passed

Description

83%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, concrete description that explicitly covers both capability and trigger conditions with specific channels and trust scoring. Minor gains are possible by adding a few more trigger synonyms and sharpening the action list.

Dimension	Reasoning	Score
Specificity	Names concrete actions ('Routes queries to optimal channels', 'attaches domain trust labels') and enumerates specific channels (Context7 docs, native web search, gh/glab, Serena), but the action set is essentially two operations plus channel listing rather than comprehensive coverage.	4 / 5
Completeness	Clearly states what it does (intent-based routing with trust scoring across named channels) and explicitly answers when with concrete trigger phrases via the 'Use for...' clause.	5 / 5
Trigger Term Quality	'Use for search, find, lookup, reference, docs, code search, and web research' gives good natural keyword coverage, though a few synonyms (e.g. 'documentation', 'look up') and variant phrasings are missing.	4 / 5
Distinctiveness Conflict Risk	The intent-routing-plus-trust-scoring niche is mostly distinct, but the broad search/find/lookup trigger set carries minor overlap risk with other general search or research skills.	4 / 5
	Total	17 / 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: 7721120

Reviewed: 5 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.