oma-scholar

Search academic literature and generate, validate, or compare Knows paper sidecars. Use for claim/evidence analysis and literature synthesis.

Quality

78%

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-scholar/SKILL.md

Quality

Content

81%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 an actionable, well-sequenced operations guide with excellent executable commands, error-recovery loops, and a clean reference split. Its weakness is token efficiency: duplicated CLI examples, abstract scheduling scaffolding, and inlined time-sensitive statistics that could be consolidated or pushed to reference files.

Suggestions

Deduplicate the CLI examples: merge "Canonical command path" into the "Quick Reference" section to cut repeated search/resolve/get/lint blocks.

Trim the Scheduling/Scenes/Transitions scaffolding (e.g., the SSL-primitive table) to the operational content, or move it to the execution-protocol reference.

Move volatile statistics and version-sensitive details (47% dangling-ref rate, 15-sample measurement, 2026-only indexing caveat) into a reference file so the core SKILL.md stays stable.

Dimension	Reasoning	Score
Conciseness	The body is dense with non-obvious domain knowledge (guardrails, lint error-to-fix mappings, fallback cascade), but the "Scheduling"/"Scenes"/"Transitions" scaffolding is ceremonial, the CLI commands are repeated in both "Canonical command path" and "Quick Reference", and time-sensitive figures (v0.9.0, 2026-only indexing, 47% dangling-ref stat) are inlined rather than isolated — matching the mostly-efficient-but-could-be-tightened anchor.	3 / 5
Actionability	Guidance is fully executable: copy-paste `oma scholar search\|resolve\|get\|lint` invocations with flags, raw curl endpoints, exact lint error strings paired with fixes, and concrete examples covering the common generate/validate/fetch cases — matching the copy-paste-ready anchor.	5 / 5
Workflow Clarity	The PREPARE→ACQUIRE→REASON→ACT→VERIFY→FINALIZE sequence includes an explicit validation stage, "run lint before sharing" checkpoints, a --fail-on-warning CI mode, and a failure-and-recovery section covering API timeouts, YAML parse fixes, and fallback sources — clear sequence with explicit validation and feedback loops.	5 / 5
Progressive Disclosure	A clearly labeled References section points to one-level-deep, purpose-tagged files (execution protocol, spec, API endpoints, checklist), keeping the overview lean. Minor gaps: the referenced `resources/` files are not present in the bundle to verify, and cross-skill paths (`../_shared/core/...`, `../../rules/...`) reach outside it, so structure is good but not fully clean.	4 / 5
	Total	17 / 20 Passed

Description

75%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 specific, third-person, and follows the what/when pattern with a distinct Knows-sidecar niche. Its main weakness is incomplete coverage: only four of six modes are named and the when-clause misses natural triggers like peer review and the .knows.yaml extension.

Suggestions

Mention the review and analyze capabilities (e.g., "produce peer reviews as sidecars") so the description covers all main modes.

Add natural trigger phrases users would say, such as "research paper", "peer review", or the ".knows.yaml" file extension, to the when-clause.

Dimension	Reasoning	Score
Specificity	"Search academic literature and generate, validate, or compare Knows paper sidecars" lists several concrete actions on a named artifact type, matching the anchor for several specific actions with minor gaps; it omits the analyze/review/fetch modes the body documents, so it is not comprehensive (5).	4 / 5
Completeness	It answers both "what" (search, generate, validate, compare Knows sidecars) and "when" ("Use for claim/evidence analysis and literature synthesis") in third person, but the when-clause covers only two of the six modes and lacks trigger phrases for searching or peer review, so it falls short of the explicit comprehensive-trigger anchor.	4 / 5
Trigger Term Quality	Natural terms like "academic literature", "paper sidecars", "claim/evidence analysis", and "literature synthesis" give good keyword coverage, but common variations such as "peer review", "research paper", and the ".knows.yaml" extension are missing, placing it just below the comprehensive-synonym anchor.	4 / 5
Distinctiveness Conflict Risk	"Knows paper sidecars" carves a clear niche with distinct triggers, but the opening "Search academic literature" and "literature synthesis" invite minor overlap with general academic-search skills, matching the mostly-distinct anchor rather than minimal-conflict.	4 / 5
	Total	16 / 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-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.