oma-academic-writing

Academic writing capability for publication-grade English prose. Drafts, revises, and audits essays, reports, analysis sections, executive summaries, conclusions, and literature reviews while enforcing sentence-structure variation, high-frequency academic verbs, calibrated hedging, and anti-AI stylistic compliance. USE for academic writing, essay polish, paragraph rewrite, prose revision against any rubric tier (HD/D/C, A/B/C, top-band/mid-band, etc.), anti-AI audit, reverse outlining, claim-evidence mapping, and rubric enforcement on assignments.

Quality

81%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Passed

No findings from the security scan

Quality

Content

73%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 academic-writing skill with strong workflow clarity and validation loops. Its main weaknesses are workflow restatement across sections and resource files referenced but not bundled.

Suggestions

Consolidate the workflow into a single canonical sequence; the Scenes, Canonical workflow path, and Actions table currently restate the same steps three times.

Bundle the referenced resources/*.md files (anti-ai-checklist, sentence-structure-reference, academic-verb-tiers, hedging-guide) so the one-level-deep references resolve, or inline the minimal needed content.

Add one short before/after prose revision example so the revise-mode output format is concrete rather than only described.

Dimension	Reasoning	Score
Conciseness	Mostly efficient and free of concepts Claude already knows, but the same workflow is restated three times (Scenes PREPARE/ACQUIRE/ACT/VERIFY/FINALIZE, the Canonical workflow path, and the Actions table), adding noticeable redundancy that could be tightened.	3 / 5
Actionability	Highly concrete guidance for an instruction skill — explicit banned-verb list, sentence-length ranges (8-15/16-25/26-40), em-dash and semicolon quotas, a 3-column Claim-Evidence Map, and a failure/recovery table — with only minor gaps such as no worked before/after prose example.	4 / 5
Workflow Clarity	Clear multi-step sequence (Entry, Scenes, Exit) with explicit validation checkpoints (VERIFY against anti-AI checklist), an iterative audit feedback loop, and a guardrail checklist plus recovery table for error handling.	5 / 5
Progressive Disclosure	Well-signaled one-level-deep references in a dedicated References section (resources/*.md and shared core files), with substantial protocol detail inlined in SKILL.md; however the referenced resource files are not present in the bundle, so navigation cannot be fully verified.	4 / 5
	Total	16 / 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, third-person description that clearly states both capability and use triggers with comprehensive, concrete actions. Minor room to improve distinctiveness and add a few more synonyms.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions ("Drafts, revises, and audits essays, reports, analysis sections, executive summaries, conclusions, and literature reviews") plus four enforcement mechanisms, giving comprehensive coverage of the capability.	5 / 5
Completeness	Explicitly answers both what ("Drafts, revises, and audits...") and when ("USE for academic writing, essay polish..."), with concrete trigger phrases for each use case.	5 / 5
Trigger Term Quality	Good coverage of natural phrases users would say ("essay polish", "paragraph rewrite", "anti-AI audit", "reverse outlining", "claim-evidence mapping"), though a few common synonyms like "proofreading" or "editing" are absent.	4 / 5
Distinctiveness Conflict Risk	Academic writing is a clear, narrow niche with distinct triggers, but the description alone does not disambiguate from adjacent skills (translation, scholar, pm) which are only separated in the body's "When NOT to use" section.	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: .agents/skills/oma-academic-writing/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.