pdf-verification-cli

Verify PDF page count and content using command-line tools when Python libraries unavailable

Quality

63%

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 ./benchmarks/gdpval/skills/pdf-verification-cli/SKILL.md

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 content is highly actionable with executable examples and a clear, validated workflow, but it carries redundancy and stays monolithic when some material could live in separate referenced files.

Suggestions

Remove the redundant Common Use Cases table or the Python integration section since both restate commands already demonstrated, improving token efficiency.

Move the Troubleshooting and Python Integration sections into referenced files (e.g. TROUBLESHOOTING.md) to apply progressive disclosure for this >50-line skill.

Tighten code-block comments and the metadata-field list to only what Claude cannot infer about poppler-utils.

Dimension	Reasoning	Score
Conciseness	The body is mostly efficient and assumes Claude's competence, but the Common Use Cases table repeats commands already shown and the Python integration section re-implements the bash workflow, adding tokens that could be trimmed.	2 / 3
Actionability	It provides fully executable bash and Python examples with specific flags and copy-paste-ready snippets, matching the score-3 anchor for concrete, runnable guidance.	3 / 3
Workflow Clarity	The Verification Workflow is a clearly sequenced four-step process with an explicit validation checkpoint in Step 3 (if/else page-count mismatch); the operation is verification rather than destructive, so no feedback-loop cap applies.	3 / 3
Progressive Disclosure	No bundle files exist and sections are well-organized, but the skill is a monolithic >50-line document with inline content (Python integration, troubleshooting) that could be split into referenced files, so it does not reach the score-3 bar.	2 / 3
	Total	10 / 12 Passed

Description

50%

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 clear and honest about its niche but reads as a capability-plus-constraint statement rather than a trigger-optimized declaration. It lacks the natural "Use when..." user-intent phrasing the rubric rewards.

Suggestions

Add an explicit user-intent trigger, e.g. "Use when verifying PDF page count or text content and Python PDF libraries are unavailable."

Expand the action list slightly (e.g. "check page count, extract and search text") to push specificity toward 3.

Include natural trigger terms users would say ("PDF", "page count", "extract text") rather than leading with the Python-unavailable constraint.

Dimension	Reasoning	Score
Specificity	The description names the PDF domain and two concrete actions ("Verify PDF page count and content") but stops short of listing multiple specific actions, matching the score-2 anchor rather than the comprehensive score-3 example.	2 / 3
Completeness	It states what the skill does but the "when" clause is an environment condition (Python unavailable) with no "Use when..." user-intent trigger, so per the guideline completeness is capped at 2.	2 / 3
Trigger Term Quality	It includes "PDF" and "page count" but frames the trigger around the technical condition "when Python libraries unavailable" rather than natural user phrases, missing common variations users would actually say.	2 / 3
Distinctiveness Conflict Risk	The CLI-fallback niche is somewhat specific, but the description could still overlap with a general PDF-handling skill since the distinguishing trigger is environment-based rather than a distinct user intent.	2 / 3
	Total	8 / 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: HKUDS/OpenSpace
Path: benchmarks/gdpval/skills/pdf-verification-cli/SKILL.md
Commit: c5a9c4b

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.