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.
79
75%
Does it follow best practices?
Impact
Pending
No eval scenarios have been run
Risky
Do not use without reviewing
Optimize this skill with Tessl
npx tessl skill review --optimize ./skills/pdf/SKILL.mdQuality
Discovery
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 capabilities and includes an explicit 'when' clause with natural trigger terms. The description is concise yet comprehensive, covering both the breadth of PDF operations and the conditions under which the skill should be selected. Minor note: 'GLM' in the trigger clause is an unusual reference (possibly a project-specific term), but it doesn't significantly detract from the description's quality.
| Dimension | Reasoning | Score |
|---|---|---|
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, 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', 'extract text', 'tables', 'merge', 'split', 'forms', 'fill in a 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', and 'PDF documents'. Unlikely to conflict with other skills due to the specific file format focus. | 3 / 3 |
Total | 12 / 12 Passed |
Implementation
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 highly actionable with excellent executable code examples covering PDF creation, manipulation, and formatting with ReportLab. However, it is severely undermined by extreme verbosity and repetition — the same rules about font registration, Paragraph wrapping, forbidden Unicode characters, and metadata are restated 3-4 times each. The document would benefit enormously from deduplication and splitting detailed formatting specifications into separate reference files.
Suggestions
Eliminate the massive repetition: font handling rules, Paragraph wrapping requirements, forbidden character rules, and metadata instructions each appear 3-4 times. State each rule once in a canonical location and reference it elsewhere.
Move detailed specifications (cover page styles, table formatting rules, cross-reference implementation, TOC template) into separate reference files, keeping only concise summaries and links in the main SKILL.md.
Remove explanations of basic concepts Claude already knows (e.g., how to use pypdf for merging/splitting, basic canvas operations) and focus the main document on the project-specific constraints and patterns that are unique to this environment.
Consolidate the mandatory workflow into a single, clearly numbered sequence at the top of the document rather than scattering pieces of it (sanitization, metadata addition) across multiple sections.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | Extremely verbose at ~800+ lines with massive repetition. The same rules (font registration, Paragraph wrapping, forbidden characters, metadata branding, mixed Chinese-English font handling) are repeated 3-4 times each throughout the document. The 'Critical Reminders' section near the end largely duplicates earlier sections verbatim. Much content explains things Claude already knows (how to use pypdf, basic Python patterns). | 1 / 3 |
Actionability | The skill provides fully executable, copy-paste ready code examples throughout — font registration templates, complete table examples, TOC implementation, cross-reference systems, command-line tools with exact syntax. Code includes specific file paths, exact color hex values, and concrete parameter values. | 3 / 3 |
Workflow Clarity | The mandatory post-generation workflow (write to file → sanitize → execute → add metadata) is clearly sequenced with explicit steps. However, the overall document structure is disorganized — constraints, guidelines, layout rules, and reminders are scattered across multiple sections without a clear sequential flow. The sanitization and metadata steps are repeated in multiple places, creating confusion about the canonical workflow. | 2 / 3 |
Progressive Disclosure | References to forms.md and reference.md are well-signaled at the end. However, the main SKILL.md is monolithic — enormous amounts of detailed formatting rules, complete code examples for TOC/cross-references, and extensive table styling specifications are all inline rather than split into separate reference files. The cover page specs, table formatting rules, and cross-reference implementation could easily be in separate files. | 2 / 3 |
Total | 8 / 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.
Validation — 10 / 11 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 | 10 / 11 Passed | |
- Repository
- jjyaoao/HelloAgents
- Commit
07048a9
- 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.