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

85%

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%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, highly actionable skill body with a clear sequenced workflow and validation/recovery loops. Its main weaknesses are redundant restatements of the hybrid command and a referenced execution-protocol.md that is not shipped with the bundle.

Suggestions

Deduplicate the hybrid invocation: state the `uvx --from "opendataloader-pdf[hybrid]" opendataloader-pdf-hybrid` command once (e.g., in the Canonical command path) and reference it from Dependencies/Failure/Actions instead of repeating it verbatim.

Ship the referenced `resources/execution-protocol.md` (or inline the on-request flags like `--sanitize`, `--table-method cluster`, `--detect-strikethrough`) so progressive-disclosure navigation does not lead to a missing file.

Collapse the repeated large-file / `--to-stdout` / distinct-output-directory guidance into a single location instead of restating it in both Transitions and the Failure table.

Dimension	Reasoning	Score
Conciseness	Mostly efficient and assumes competence (no PDF or library primers), but the hybrid invocation command is restated verbatim across Dependencies, the Actions table, and the Canonical command path, and basename/--to-stdout guidance repeats across Transitions and the Failure table.	3 / 5
Actionability	Provides copy-paste-ready executable commands for the text-layer probe, standard conversion, mdformat normalization, and the hybrid OCR server + convert flow, covering the common cases with concrete flags.	5 / 5
Workflow Clarity	Clear Entry -> Scenes (PREPARE/ACQUIRE/ACT/VERIFY/FINALIZE) -> Transitions -> Failure/recovery -> Exit sequence with an explicit VERIFY validation checkpoint and retry/escalation feedback loops for garbled output, missing tables, and OCR cases.	5 / 5
Progressive Disclosure	Overview-style body with one-level-deep references to resources/execution-protocol.md and shared core docs, but that referenced file (and the referenced config files) are not present in the bundle, so navigation leads to a missing file.	3 / 5
	Total	16 / 20 Passed

Description

92%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, specific description that names concrete extraction actions and gives explicit use-for trigger guidance. Adding the .pdf extension and more user-natural phrases would round out the trigger coverage.

Dimension	Reasoning	Score
Specificity	Lists multiple specific concrete extraction actions ("Extracts text, tables, headings, lists, and images") plus the core conversion, giving comprehensive coverage of the extraction surface.	5 / 5
Completeness	Explicitly answers both what ("Convert PDF files to Markdown... Extracts text, tables, headings, lists, and images") and when ("Use for PDF parsing, PDF to Markdown conversion, document extraction") with concrete trigger phrases.	5 / 5
Trigger Term Quality	Good natural-term coverage ("PDF parsing, PDF to Markdown conversion, document extraction") but omits the .pdf extension and common variants like "read this PDF", and "AI-ready data preparation" is more aspirational than a phrase users say.	4 / 5
Distinctiveness Conflict Risk	Scoped to a clear niche (PDF-to-Markdown conversion via opendataloader-pdf) with distinct triggers, giving minimal overlap risk with other document skills.	5 / 5
	Total	19 / 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-pdf/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.