CtrlK
BlogDocsLog inGet started
Tessl Logo

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.

63

Quality

75%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

SecuritybySnyk

High

Do not use without reviewing

Fix and improve this skill with Tessl

tessl review fix ./skills/pdf/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

50%

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

This skill is extremely actionable with excellent, executable code examples covering a wide range of PDF operations. However, it is severely undermined by massive verbosity and repetition — key rules (font restrictions, Paragraph wrapping, metadata requirements, mixed-language font handling) are repeated 3-5 times each with full code examples, roughly doubling the document length. The document would benefit enormously from consolidating repeated content and moving detailed implementation examples (cross-references, TOC, table formatting) into referenced files.

Suggestions

Eliminate repetition: The mixed Chinese-English font handling code, table cell Paragraph wrapping rule, font restriction list, and Z.ai metadata requirement each appear multiple times with full examples — consolidate each to a single authoritative location and reference it elsewhere.

Move detailed implementation examples (complete TOC code, cross-reference system, cover page specifications, table formatting examples) into separate reference files and keep only concise summaries with links in SKILL.md.

Restructure the document to lead with a clear end-to-end workflow (create → populate → sanitize → build → add metadata) before diving into specific features, and move the 'Quick Start' section to actually be near the top.

Remove explanatory text that restates why rules exist (e.g., 'Why this is mandatory: Rendering formatting tags...') — Claude can infer rationale from the rule itself.

DimensionReasoningScore

Conciseness

Extremely verbose at ~800+ lines. Massive repetition throughout — the mixed Chinese-English font handling code block appears twice verbatim, the table cell Paragraph wrapping rule is stated 4+ times with full examples each time, font restrictions are repeated in multiple sections, and the metadata/Z.ai branding requirement is hammered at least 5 times. Explains concepts Claude already knows (what TA_JUSTIFY does, why bold tags need Paragraph objects) repeatedly. The 'Character Safety Rule' content is restated in 'Rich Text Formatting' and again in 'Critical Reminders'.

1 / 3

Actionability

Highly actionable with fully executable, copy-paste-ready Python code examples throughout. Specific font paths, exact color hex codes, complete working examples for TOC generation, cross-references, table formatting, and all major operations. Commands are concrete and specific (e.g., `python scripts/sanitize_code.py generate_pdf.py`).

3 / 3

Workflow Clarity

The mandatory post-generation workflow (write file → sanitize → execute) is clearly sequenced with validation. However, the overall document structure is disorganized — 'Core Constraints' mix content generation guidelines with technical implementation details, the 'Quick Start' section appears deep into the document after hundreds of lines of constraints, and 'Critical Reminders' at the end largely duplicate earlier sections. The decision tree for DocTemplate choice is good, but the document lacks a clear top-level workflow for 'how to create a PDF from start to finish' that ties all pieces together.

2 / 3

Progressive Disclosure

References to forms.md and reference.md are well-signaled and appear to be one level deep. However, the SKILL.md itself is monolithic — enormous amounts of detail (complete table formatting examples, full cross-reference implementation, cover page specifications, spacing standards) are inlined rather than split into separate reference files. The content that should be in reference files (e.g., the 100+ line cross-reference example, detailed table styling rules, cover page specs) bloats the main skill file significantly.

2 / 3

Total

8

/

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.

This is a strong skill description that clearly enumerates specific PDF manipulation capabilities and includes an explicit 'when' clause with natural trigger terms. The description is concise yet comprehensive, covering the full range of PDF operations. Minor note: 'GLM' is an unusual reference (possibly project-specific) but doesn't significantly detract from clarity.

DimensionReasoningScore

Specificity

Lists multiple specific concrete actions: 'extracting text and tables', 'creating new PDFs', 'merging/splitting documents', and 'handling forms'. These are clear, actionable capabilities.

3 / 3

Completeness

Clearly answers both 'what' (extracting text/tables, creating PDFs, merging/splitting, handling forms) and 'when' ('When GLM needs to fill in a PDF form or programmatically process, generate, or analyze PDF documents at scale'). Has an explicit trigger clause.

3 / 3

Trigger Term Quality

Includes strong natural keywords users would say: 'PDF', 'text', 'tables', 'merging', 'splitting', 'forms', 'PDF form', 'generate', 'analyze PDF documents'. Good coverage of common variations and use cases.

3 / 3

Distinctiveness Conflict Risk

Clearly scoped to PDF manipulation with distinct triggers like 'PDF form', 'merging/splitting documents', 'PDF documents'. Unlikely to conflict with non-PDF skills due to the specific file format focus.

3 / 3

Total

12

/

12

Passed

Validation

90%

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation10 / 11 Passed

Validation for skill structure

CriteriaDescriptionResult

skill_md_line_count

SKILL.md is long (1534 lines); consider splitting into references/ and linking

Warning

Total

10

/

11

Passed

Repository
jjyaoao/HelloAgents
Reviewed

Table of Contents

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.