pdf

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

3.69x

Quality

75%

Does it follow best practices?

Impact

85%

3.69x

Average score across 3 eval scenarios

Securityby

High

Do not use without reviewing

Fix and improve this skill with Tessl

tessl review fix ./plugins/all-skills/skills/pdf/SKILL.md

The canonical home for this skill is pdf in anthropics/skills

Quality

Content

65%

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

A well-organized, actionable reference with executable code throughout and clear task-to-tool mapping. Its weaknesses are missing validation feedback loops for risky operations and an incomplete bundle (reference.md and forms.md are referenced but not present).

Suggestions

Add validation/verification steps to destructive or batch operations (e.g. re-open encrypted output to confirm, run scripts/check_bounding_boxes.py after defining fields.json) to raise workflow clarity.

Either include the referenced reference.md and forms.md in the bundle or remove the pointers, since the body repeatedly directs the reader to files that are not present.

Deduplicate the 'Quick Start' extract-text example against the pdfplumber section and trim obvious code comments to improve token efficiency.

Dimension	Reasoning	Score
Conciseness	The guide is largely lean and assumes Claude's competence, but the 'Quick Start' extract-text block duplicates the pdfplumber section and several code comments state the obvious (e.g. 'Rotate 90 degrees clockwise'); not level 3 because some tokens could be trimmed, not level 1 because it avoids explanatory fluff.	2 / 3
Actionability	Every section provides fully executable, copy-paste-ready code or commands (pypdf, pdfplumber, reportlab, qpdf, pytesseract) plus a 'Quick Reference' table mapping tasks to tools; matches the 'fully executable, copy-paste ready' anchor.	3 / 3
Workflow Clarity	Tasks are presented as discrete single-step recipes but lack validation checkpoints, and destructive/batch operations (encrypt, merge, form-fill via scripts) have no verify step; per the rubric, missing feedback loops for such operations caps this at 2 rather than 3.	2 / 3
Progressive Disclosure	The body signals one-level-deep references (reference.md, forms.md) and routes form filling to a separate file, but those referenced files are absent from the bundle while undocumented form-handling scripts exist in scripts/, so navigation is incomplete; not level 1 because structure and signaling exist, not level 3 because the referenced files are missing.	2 / 3
	Total	9 / 12 Passed

Description

85%

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 description that states concrete capabilities and pairs them with an explicit use-when trigger in third person. The only gap is breadth of natural trigger terms (no 'PDFs' or '.pdf').

Suggestions

Add common trigger variations such as 'PDFs' and '.pdf' alongside 'PDF documents' to broaden natural-keyword coverage.

Consider adding 'extracting data' or 'document processing' as natural phrasings users may say.

Dimension	Reasoning	Score
Specificity	It lists multiple concrete actions — 'extracting text and tables, creating new PDFs, merging/splitting documents, and handling forms' — matching the 'lists multiple specific concrete actions' anchor; it is not level 2 because coverage is comprehensive rather than partial.	3 / 3
Completeness	It explicitly answers both 'what' (concrete actions) and 'when' via 'When Claude needs to fill in a PDF form or programmatically process, generate, or analyze PDF documents at scale'; the explicit trigger clause meets the level-3 bar and exceeds the level-2 'when implied' anchor.	3 / 3
Trigger Term Quality	Relevant keywords appear ('PDF', 'forms', 'PDF documents') but common user variations such as 'PDFs' and '.pdf' are missing; it is not level 3 because coverage of natural terms is incomplete, yet not level 1 because the terms present are genuine user language.	2 / 3
Distinctiveness Conflict Risk	'Comprehensive PDF manipulation toolkit' with PDF/form-specific triggers carves a clear niche unlikely to overlap other skills; it is not level 2 because the triggers are distinct rather than only 'somewhat specific'.	3 / 3
	Total	11 / 12 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
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	15 / 16 Passed

Repository: davepoon/buildwithclaude
Path: plugins/all-skills/skills/pdf/SKILL.md
Commit: b79ed72

Reviewed: about 5 hours 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.