pdf

Use this skill whenever the user wants to do anything with PDF files. This includes reading or extracting text/tables from PDFs, combining or merging multiple PDFs into one, splitting PDFs apart, rotating pages, adding watermarks, creating new PDFs, filling PDF forms, encrypting/decrypting PDFs, extracting images, and OCR on scanned PDFs to make them searchable. If the user mentions a .pdf file or asks to produce one, use this skill.

Quality

76%

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 ./configs/microservice/bff-service/configs/agent-skills/wanwu/pdf/SKILL.md

Quality

Content

53%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 content is actionable and rich with executable examples across the common PDF tasks, but it is verbose with repeated material and inlines reference-grade content that belongs in the separate files it points to — which do not actually exist in the bundle. Batch and destructive operations also lack validation checkpoints.

Suggestions

Create the referenced REFERENCE.md, FORMS.md, and BEST_PRACTICES.md files (or remove the dead links) and move the inlined Chinese-font deep-dive and per-library API reference into them so SKILL.md stays a lean overview.

Add explicit validation/verification checkpoints to batch and destructive workflows (e.g., after merge/split, verify page counts with PdfReader; after encrypt, confirm the file opens with the password).

De-duplicate the content: the drawString-vs-Paragraph warning and the 'no font files needed' note each appear multiple times — keep one authoritative copy and fix the TTF example that registers a .ttc file as a TTFont.

Dimension	Reasoning	Score
Conciseness	The body is mostly useful code but contains repeated padding ('no font files needed' appears 4+ times, the drawString-vs-Paragraph warning appears twice) and a promotional 'Why CIDFont is Better' section with six emoji bullets that could be tightened, fitting anchor 3 rather than 4.	3 / 5
Actionability	Concrete, mostly copy-paste-ready code and CLI commands cover all common tasks (merge, split, extract text/tables, create, OCR, watermark, encrypt), with only minor gaps such as a TTF example registering a .ttc file the doc itself says errors, and an inconsistent sys.path setup for the markdown_to_pdf import.	4 / 5
Workflow Clarity	Tasks are presented as isolated snippets without sequenced multi-step workflows, and batch/destructive operations (merge, split, encrypt) lack any validation or verification checkpoints; per the rubric cap such skills cannot score above 3.	3 / 5
Progressive Disclosure	The body references REFERENCE.md, FORMS.md, and BEST_PRACTICES.md, but none of these files exist in the bundle (dead references), while large reference-style content such as the ~115-line Chinese-font deep-dive and library API examples are inlined rather than split out, matching anchor 2.	2 / 5
	Total	12 / 20 Passed

Description

100%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.

This is an exemplary description that clearly states both what the skill does (a comprehensive enumerated list of PDF operations) and when to use it (explicit trigger phrases including the .pdf extension). It is specific, distinct, and uses the standard imperative trigger voice matching the good examples.

Dimension	Reasoning	Score
Specificity	Lists many concrete actions ('reading or extracting text/tables', 'merging multiple PDFs', 'splitting PDFs apart', 'rotating pages', 'adding watermarks', 'filling PDF forms', 'encrypting/decrypting', 'extracting images', 'OCR on scanned PDFs'), giving comprehensive coverage that matches the anchor-5 example.	5 / 5
Completeness	Explicitly answers 'what' via the enumerated action list and 'when' via concrete trigger phrases ('Use this skill whenever the user wants to do anything with PDF files', 'If the user mentions a .pdf file or asks to produce one, use this skill'), matching the anchor-5 example almost exactly.	5 / 5
Trigger Term Quality	Covers natural terms and synonyms including 'PDF files', 'PDFs', the '.pdf file' extension, and 'forms', plus common action verbs users actually say (merge, split, fill, extract, OCR), satisfying the anchor-5 criterion of comprehensive coverage with synonyms and file extensions.	5 / 5
Distinctiveness Conflict Risk	The skill is squarely PDF-niche with an explicit '.pdf file' extension trigger and PDF-specific actions, giving a clear niche with minimal conflict risk as described by the anchor-5 example.	5 / 5
	Total	20 / 20 Passed

Validation

87%

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 — 14 / 16 Passed

Validation for skill structure

Criteria	Description	Result
skill_md_line_count	SKILL.md is long (613 lines); consider splitting into references/ and linking	Warning
relative_links	Relative link issues: 1 missing	Warning

	Total	14 / 16 Passed

Repository: UnicomAI/wanwu
Path: configs/microservice/bff-service/configs/agent-skills/wanwu/pdf/SKILL.md
Commit: 030c20b

Reviewed: 1 day 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.