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

80%

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-scholar/SKILL.md

Quality

Content

71%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.

Highly actionable content with concrete CLI commands, validation modes, and a strong troubleshooting table. Weaknesses are token spend on abstract scheduling scaffolding, inlined spec minutiae that belong in the referenced sidecar-spec file, and referenced bundle files that are not present.

Suggestions

Trim or remove the Logical Operations table mapping actions to SSL primitives (SELECT/READ/REQUEST/INFER) and compress the Scenes/Intent-signature scaffolding — the Modes table and Transitions already convey the same control flow in fewer tokens.

Move the detailed spec-field rules from Guardrails (items 4–12) into resources/sidecar-spec.md and keep only the top 3–4 highest-risk rules inline, since that file is already referenced for spec rules.

Move the time-sensitive coverage statement ("only 2026 papers, ~50K") into resources/upstream-spec-cache.md or a status section that is explicitly marked as subject to change, and ensure the referenced resources/*.md files actually ship in the skill bundle.

Dimension	Reasoning	Score
Conciseness	The SSL-primitive action table ("SELECT"/"READ"/"REQUEST"/"INFER") and the Scenes/Intent-signature scaffolding are abstract ceremony that add tokens without executable value, and "currently indexes only 2026 papers (~50K)" is time-sensitive without a deprecated/old-patterns section. Most of the body is otherwise tight, so not below the midpoint.	3 / 5
Actionability	Fully copy-paste-ready commands cover the common cases: "oma scholar search --year-min 2024", partial fetch via "--section statements", lint with "--lenient"/"--fail-on-warning", raw curl endpoints, and a troubleshooting table mapping exact error strings to fixes.	5 / 5
Workflow Clarity	Entry→Scenes(VERIFY)→Transitions→Failure-and-recovery→Exit gives a clear sequence with explicit validation ("run lint before sharing", strict/lenient/CI modes) and error→fix→retry loops, but per-mode execution steps are delegated to resources/execution-protocol.md, which is not present in the bundle, leaving a minor gap.	4 / 5
Progressive Disclosure	The 18-item Guardrails list inlines detailed spec rules (coverage enums, provenance.actor shape, ID formats) that duplicate the referenced resources/sidecar-spec.md, and none of the referenced resources/ files exist in the evaluated bundle. The References section itself is clearly listed and one level deep, so structure is present but content that should be separate is inline.	3 / 5
	Total	15 / 20 Passed

Description

88%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 multi-action capability list, an explicit "Use for..." trigger clause, and distinctive Knows-specific anchoring. The only gaps are a few missing natural trigger synonyms and slight breadth in the "when" triggers.

Dimension	Reasoning	Score
Specificity	Lists six concrete actions — "Generates, validates, reviews, queries, and compares structured research-paper sidecars, and fetches them from knows.academy" — giving comprehensive, non-generic coverage of the skill's capabilities.	5 / 5
Completeness	Explicitly answers both: the "what" via the enumerated generate/validate/review/query/compare/fetch actions, and the "when" via the concrete "Use for academic literature search, survey synthesis, paper authoring assistance, and peer review" trigger clause.	5 / 5
Trigger Term Quality	Good natural keyword coverage ("academic literature search", "survey synthesis", "peer review", "paper authoring", ".knows.yaml"), but misses common variations users would say such as "find papers", "literature review", or "summarize a paper".	4 / 5
Distinctiveness Conflict Risk	Knows, .knows.yaml, and knows.academy anchor a distinct niche, but broad trigger phrases like "peer review" and "survey synthesis" create minor overlap risk with generic search or review 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-scholar/SKILL.md
Commit: ce19702

Reviewed: 4 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.