oma-scholar

Scholarly research companion using Knows sidecar spec (.knows.yaml). Generates, validates, reviews, queries, and compares structured research-paper sidecars, and fetches them from knows.academy. Use for academic literature search, survey synthesis, paper authoring assistance, and peer review with token-efficient claim/evidence/relation access.

Quality

88%

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

77%

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

The body is highly actionable with executable CLI commands, a clear validated workflow, and useful guardrails, but it carries an unnecessary abstract process meta-framework and references bundle files that are absent from the package.

Suggestions

Remove or trim the abstract Scheduling/Scenes and Logical Operations meta-framework (SSL primitives, Resource scope tables) to recover token budget — Claude does not need this conceptual scaffolding to run the concrete commands.

Either include the referenced resources/*.md files (execution-protocol, sidecar-spec, api-endpoints, etc.) in the bundle or drop the references, since the empty references/ directory means the disclosure points to nothing loadable.

Consider moving the 18 detailed Guardrails into resources/sidecar-spec.md and keeping a short checklist inline, so SKILL.md reads as an overview pointing one level deep rather than embedding the full spec.

Dimension	Reasoning	Score
Conciseness	The substantive sections (Guardrails, CLI examples, Troubleshooting) are dense and useful, but the Scheduling/Scenes and Logical Operations meta-framework with abstract 'SSL primitive' and 'Resource scope' tables is conceptual scaffolding Claude does not need and adds token weight.	2 / 3
Actionability	Provides copy-paste-ready, executable commands ('oma scholar search', 'oma scholar lint --fail-on-warning', raw curl endpoints), a concrete Modes table with triggers and outputs, and specific troubleshooting fixes.	3 / 3
Workflow Clarity	Clear sequenced workflow (PREPARE→ACQUIRE→REASON→ACT→VERIFY→FINALIZE) with an explicit validation checkpoint ('run oma scholar lint after Generate'), strict/lenient modes, and a failure-and-recovery section forming a validate→fix→retry feedback loop.	3 / 3
Progressive Disclosure	The References section signals one-level-deep resources well, but the referenced resources/*.md files are not present in the bundle (references/, scripts/, assets/ are empty), so the disclosed detail cannot be loaded, and the 18 inline Guardrails could partly live in sidecar-spec.md.	2 / 3
	Total	10 / 12 Passed

Description

100%

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, third-person description that names concrete actions and provides an explicit 'Use for' trigger clause covering both what and when. It is clearly distinct from sibling skills like oma-search or oma-pdf.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions ('Generates, validates, reviews, queries, and compares' sidecars; 'fetches them from knows.academy') rather than vague language, matching the score-3 anchor.	3 / 3
Completeness	Explicitly answers what ('Generates, validates, reviews, queries, and compares structured research-paper sidecars') and when ('Use for academic literature search, survey synthesis, paper authoring assistance, and peer review').	3 / 3
Trigger Term Quality	Includes natural user-facing terms ('academic literature search, survey synthesis, paper authoring assistance, peer review') plus spec identifiers ('.knows.yaml', 'knows.academy') that users would plausibly say.	3 / 3
Distinctiveness Conflict Risk	Clear niche built around the Knows `.knows.yaml` spec and knows.academy, with triggers unlikely to overlap with generic search or PDF skills.	3 / 3
	Total	12 / 12 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-scholar/SKILL.md
Commit: 3021301

Reviewed: about 24 hours 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.