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

94%

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

88%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 a strong, mostly lean overview with copy-paste-ready commands, a clear multi-step workflow with validation checkpoints and recovery loops, and well-signaled references to detail files. It loses a point on conciseness (some padding in guardrails/fallback prose) and progressive disclosure (referenced bundle files are not present to verify).

Suggestions

Tighten the Guardrails section and Provider Fallback prose — trim token-ratio asides and consolidate redundant notes to lift conciseness toward the top anchor.

Ensure the referenced resource files (resources/execution-protocol.md, resources/sidecar-spec.md, etc.) actually exist in a bundle directory so progressive disclosure can be fully verified and scored at 5.

Consider moving the verbose troubleshooting table into a referenced troubleshooting resource, keeping only the most frequent errors inline in SKILL.md.

Dimension	Reasoning	Score
Conciseness	Mostly lean and actionable with tables, command blocks, and guardrails that earn their place, but the Guardrails list (18 items) and Provider Fallback prose contain some explanatory padding (e.g. '~700 tokens for claims-only vs ~10K for full PDF') that could be trimmed.	4 / 5
Actionability	Fully executable copy-paste-ready commands across Search/Resolve/Get/Lint with flags and concrete examples, plus a troubleshooting table mapping real error strings to fixes, covering the common cases.	5 / 5
Workflow Clarity	Multi-step processes are clearly sequenced (PREPARE→ACQUIRE→REASON→ACT→VERIFY→FINALIZE) with explicit validation checkpoints ('Validate before sharing', 'run lint before sharing') and recovery loops (retry/OpenAlex fallback, fix-and-revalidate on lint failure).	5 / 5
Progressive Disclosure	SKILL.md is a well-organized overview pointing to clearly signaled one-level-deep resources (execution-protocol, sidecar-spec, api-endpoints, etc.) listed in a References section; however the bundle directories (references/scripts/assets) are absent, so referenced paths cannot be verified as real files, a minor organization gap versus the top anchor.	4 / 5
	Total	18 / 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.

The description is exemplary: it concisely states a comprehensive set of concrete capabilities, gives explicit trigger guidance with natural phrasing, and carves out a distinctive niche with minimal conflict risk. It uses proper third-person voice and earns the top anchor on every dimension.

Dimension	Reasoning	Score
Specificity	Lists multiple specific concrete actions — 'Generates, validates, reviews, queries, and compares structured research-paper sidecars, and fetches them from knows.academy' — giving comprehensive coverage of capabilities.	5 / 5
Completeness	Explicitly answers both 'what' (generates/validates/reviews/queries/compares/fetches sidecars) and 'when' ('Use for academic literature search, survey synthesis, paper authoring assistance, and peer review'), satisfying the top anchor.	5 / 5
Trigger Term Quality	Comprehensive coverage of natural terms users would say — 'academic literature search', 'survey synthesis', 'paper authoring assistance', 'peer review', plus technical artifacts like '.knows.yaml' and 'knows.academy'.	5 / 5
Distinctiveness Conflict Risk	Clear niche around Knows .knows.yaml scholarly sidecars with distinctive triggers (knows.academy, OpenAlex, claims/evidence/relations) that minimize conflict with general search or PDF 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: benchmarks/runs/oma/.agents/skills/oma-scholar/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.