oma-pdf

Convert PDF files to Markdown using opendataloader-pdf. Extracts text, tables, headings, lists, and images with correct reading order. Use for PDF parsing, PDF to Markdown conversion, document extraction, and AI-ready data preparation.

Quality

88%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Critical

Do not install without reviewing

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 concrete commands and a well-sequenced, validated workflow including recovery loops. Its main weaknesses are verbose abstract framing that could be trimmed and four referenced detail files that do not actually exist in the bundle.

Suggestions

Trim the abstract meta-structure (SSL primitive column, Scenes taxonomy, Resource scope table) in favor of leaner operational guidance to improve token efficiency.

Create the referenced bundle files (resources/execution-protocol.md, config/pdf-config.yaml, ../_shared/core/context-loading.md, ../_shared/core/quality-principles.md) or remove the dangling references so progressive disclosure is real rather than promised.

Move the full command-variant detail the Guardrails hint at into execution-protocol.md and keep only the canonical path inline, reinforcing the one-level-deep reference structure.

Dimension	Reasoning	Score
Conciseness	The body is information-dense and avoids explaining concepts Claude already knows, but it carries heavy abstract scaffolding ('SSL primitive', 'Scenes: PREPARE/ACQUIRE/ACT/VERIFY/FINALIZE', 'Resource scope') that pads length without adding executable value, fitting the mostly-efficient-but-could-be-tightened anchor.	2 / 3
Actionability	Provides fully executable commands with real flags and placeholders, e.g. 'uvx opendataloader-pdf "{input_path}" --format markdown --output-dir "{output_dir}"' and the hybrid OCR sequence, matching the copy-paste-ready score-3 anchor.	3 / 3
Workflow Clarity	A clear Entry-to-Exit sequence with an explicit VERIFY checkpoint and a failure/recovery table that encodes feedback loops (garbled -> retry tagged structure -> retry hybrid), satisfying the explicit-validation-and-recovery anchor.	3 / 3
Progressive Disclosure	References are clearly signaled and one level deep ('resources/execution-protocol.md', 'config/pdf-config.yaml'), but none of the referenced files exist in the bundle — no references/, scripts/, assets/, resources/, or config/ directories are present — so the navigation promise is unfulfilled and the structure is only partly realized.	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.

The description is specific, third-person, and explicit about both capabilities and trigger conditions, hitting the top anchor on every dimension. It is concise without padding and clearly scoped to PDF conversion.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions — 'Convert PDF files to Markdown', 'Extracts text, tables, headings, lists, and images with correct reading order' — matching the score-3 anchor of several specific concrete actions.	3 / 3
Completeness	Answers both 'what' (convert/extract content) and 'when' via an explicit 'Use for PDF parsing, PDF to Markdown conversion, document extraction...' trigger clause, satisfying the score-3 anchor.	3 / 3
Trigger Term Quality	Includes natural user phrasing such as 'PDF parsing', 'PDF to Markdown conversion', and 'document extraction', giving good coverage of terms a user would actually say.	3 / 3
Distinctiveness Conflict Risk	Occupies a clear PDF-to-Markdown niche with distinct triggers and is unlikely to fire for other document types, matching the score-3 clear-niche anchor.	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-pdf/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.