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

87%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 well-structured and highly actionable, with executable commands, a sequenced PREPARE->FINALIZE workflow, explicit validation in VERIFY, and a failure-and-recovery table with feedback loops. Conciseness is strong but slightly weighed down by SSL-primitive scaffolding and inline command variants; progressive disclosure is good with a clear References section, though the referenced bundle files are not present to fully verify.

Suggestions

Trim the 'Logical Operations' scaffolding (SSL primitive / Evidence columns and Resource-scope table) — these add ceremony without guiding execution, since the actionable content already lives in the Scenes, Transitions, and command path.

Move the hybrid/OCR command variants out of the body into the referenced execution-protocol.md (as guardrail 5 already prescribes) so the canonical path shows only the standard case inline.

Add a quick one-line trigger/key-point summary near the top so the core conversion recipe is reachable without scanning the full Structural Flow.

Dimension	Reasoning	Score
Conciseness	The body is efficient and assumes Claude's competence — it skips explaining what a PDF is and leads with concrete tooling and commands — but sections like the Scheduling/Intent-signature scaffolding and the SSL-primitive/Evidence columns add ceremony that could be trimmed, keeping it just below a 5.	4 / 5
Actionability	Provides copy-paste-ready, executable commands in the 'Canonical command path' (e.g. `uvx opendataloader-pdf "{input_path}" --format markdown --output-dir "{output_dir}"`) plus a concrete hybrid/OCR invocation covering the common cases.	5 / 5
Workflow Clarity	The Scenes flow (PREPARE -> ACQUIRE -> ACT -> VERIFY -> FINALIZE) gives a clear sequence, the VERIFY step plus Transitions and the Failure-and-recovery table provide explicit validation checkpoints and feedback loops (retry with tagged structure, hybrid mode, page-range splitting), and the Exit criteria define success/partial/failure outcomes.	5 / 5
Progressive Disclosure	A clear References section signals one-level-deep pointers (execution-protocol.md, pdf-config.yaml, shared core docs) and guardrail 5 explicitly keeps detailed command sequences in resources rather than inlining them; however the referenced bundle files are not present to verify, and a few inline command variants plus the Actions/Resource-scope tables could live in those external files, so it sits at 4 rather than 5.	4 / 5
	Total	18 / 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.

The description is specific, complete, and distinctive: it names concrete extraction actions and gives explicit 'Use for...' trigger guidance tied to the PDF-to-Markdown niche. The only minor gap is trigger-term breadth (missing '.pdf'/'PDFs' synonyms), which keeps trigger_term_quality at 4 rather than 5.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions — 'Extracts text, tables, headings, lists, and images with correct reading order' and 'Convert PDF files to Markdown' — giving comprehensive coverage of the tool's capabilities, matching the score-5 anchor.	5 / 5
Completeness	Explicitly states what it does (convert/extract text, tables, headings, lists, images) and when to use it ('Use for PDF parsing, PDF to Markdown conversion, document extraction, and AI-ready data preparation'), satisfying both halves with concrete trigger phrases.	5 / 5
Trigger Term Quality	Includes natural user phrases like 'PDF parsing', 'PDF to Markdown conversion', 'document extraction', but omits common synonyms/extensions such as '.pdf', 'PDFs', or 'read this PDF', so a few natural terms are missing rather than comprehensively covered.	4 / 5
Distinctiveness Conflict Risk	The narrow PDF-to-Markdown niche with opendataloader-pdf-specific triggers and explicit 'AI-ready data preparation' framing makes it clearly distinct from general document skills and unlikely to trigger for the wrong skill.	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: benchmarks/runs/oma/.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.