pdf

Comprehensive PDF manipulation toolkit for extracting text and tables, creating new PDFs, merging/splitting documents, and handling forms. When GLM needs to fill in a PDF form or programmatically process, generate, or analyze PDF documents at scale.

Quality

78%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

High

Do not use without reviewing

Fix and improve this skill with Tessl

tessl review fix ./skills/pdf/SKILL.md

Quality

Content

63%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.

Highly actionable with concrete executable examples and a sound generation workflow, but undermined by severe repetition/verbosity and progressive-disclosure defects: referenced files are missing and the body is a monolithic wall that should be split.

Suggestions

De-duplicate the repeated font-registration and mixed CJK/English font-handling code blocks (each appears verbatim twice) and consolidate the 'wrap table cells in Paragraph' rule to a single authoritative statement.

Create the referenced reference.md and forms.md files and move the large inline TOC, cross-reference, and detailed font/table-formatting reference material into them so SKILL.md becomes a lean overview with one-level-deep links.

Trim the pervasive ALL-CAPS emphasis ('NON-NEGOTIABLE', 'CRITICAL', 'ABSOLUTE MANDATORY') to reduce padding without losing the key constraints.

Dimension	Reasoning	Score
Conciseness	The 1500-line body is noticeably verbose with heavily repeated sections — the mixed CJK/English font-handling block and font-registration code each appear nearly verbatim twice, and the 'table cells must be Paragraph' rule is restated 4+ times amid pervasive ALL-CAPS padding ('NON-NEGOTIABLE', 'CRITICAL').	2 / 5
Actionability	Fully executable, copy-paste-ready code for merge/split, text+table extraction, reportlab creation, tables, auto-TOC, cross-references, OCR, watermark, and password protection, plus specific qpdf/pdftotext commands and concrete font paths and color hex values.	5 / 5
Workflow Clarity	The generation workflow is clearly sequenced with a validation checkpoint (write .py -> sanitize_code.py -> execute; build -> add_zai_metadata -> report), but the overall document is fragmented across scattered constraint/font/table sections rather than one coherent end-to-end flow.	4 / 5
Progressive Disclosure	References to reference.md and forms.md are explicitly signaled but those files do not exist in the bundle, and large blocks that belong in separate files (full TOC/cross-ref implementations, font-config tables) are inlined into the monolithic SKILL.md.	3 / 5
	Total	14 / 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 clearly states both capabilities and use-conditions. Its only gap is slightly limited trigger-term variation (no '.pdf' extension or broader synonyms).

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions — 'extracting text and tables, creating new PDFs, merging/splitting documents, and handling forms' — giving comprehensive coverage, matching the score-5 anchor.	5 / 5
Completeness	Explicitly answers what ('Comprehensive PDF manipulation toolkit for...') and when ('When GLM needs to fill in a PDF form or programmatically process, generate, or analyze PDF documents at scale') with concrete trigger phrases.	5 / 5
Trigger Term Quality	Good keyword coverage ('PDF', 'PDF form', 'PDF documents', 'forms') but misses the '.pdf' file extension and common synonyms, so it sits just below the comprehensive score-5 anchor.	4 / 5
Distinctiveness Conflict Risk	Clear PDF-only niche with distinct triggers (forms, generation, at-scale processing); minimal overlap risk with other skills.	5 / 5
	Total	19 / 20 Passed

Validation

93%

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 — 15 / 16 Passed

Validation for skill structure

Criteria	Description	Result
skill_md_line_count	SKILL.md is long (1534 lines); consider splitting into references/ and linking	Warning

	Total	15 / 16 Passed

Repository: jjyaoao/HelloAgents
Path: skills/pdf/SKILL.md
Commit: 93e77ea

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.