pdf-official

Use this skill whenever a PDF file is being produced, opened, transformed, filled, or read. That includes: extracting text or tables from an existing PDF; combining, carving, rotating, cropping, or watermarking pages; composing a fresh PDF (report, invoice, certificate); filling AcroForm fields or overlaying text onto a non-fillable scanned form; encrypting or unlocking a PDF; running OCR over a scanned document; rendering pages to PNG/JPEG for visual analysis. Trigger on mentions of 'PDF', a filename ending in .pdf, requests like 'turn this into a PDF report', or references to AcroForm / form fields.

Quality

91%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Low

Low-risk findings worth noting

Quality

Content

92%

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

A well-structured, lean, actionable overview with a clear probe→validate workflow. The single material defect is that the four sub-guide markdown files it routes to are absent from the bundle, breaking the progressive-disclosure navigation the skill is built around.

Suggestions

Ship the missing sub-guides (extract.md, transform.md, compose.md, interactive.md) referenced by the routing table, or inline their essential content so the overview is not a dead end.

If the sub-guides are intentionally omitted from this bundle, remove or gate the routing links so the body does not point to non-existent files.

Consider noting in SKILL.md that validation details live in each sub-guide's Validation section only once those sections actually exist, to keep the promised feedback loops real.

Dimension	Reasoning	Score
Conciseness	The body is lean and assumes Claude's competence — routing tables, an exit-code legend, and a gotchas list carry information density with no padding about what a PDF is or how libraries work, matching the score-3 anchor where every token earns its place.	3 / 3
Actionability	It gives fully executable, copy-paste-ready commands ('scripts/survey.py path/to/file.pdf --pretty', 'python3 -m pip install ...', 'qpdf --password=… --decrypt', 'qpdf --encrypt … 256 --') plus a library-selection table naming specific functions like 'pypdf.update_page_form_field_values', matching the score-3 anchor.	3 / 3
Workflow Clarity	A clear sequence is stated ('probe → plan → extract or compose → validate') with explicit validation signals — exit code 3 means validation failure, sanity_check.py reports findings, and each path starts with a probe — matching the score-3 anchor for a clear sequence with explicit validation steps.	3 / 3
Progressive Disclosure	The overview is well-designed with one-level-deep, clearly signaled references in a routing table, but the four referenced sub-guides (extract.md, transform.md, compose.md, interactive.md) do not exist in the bundle — only scripts/ (whose referenced scripts all exist) — so navigation to the detailed material is broken, which caps this at the score-2 anchor rather than 3.	2 / 3
	Total	11 / 12 Passed

Description

90%

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, comprehensive description with excellent trigger coverage and explicit when/what guidance. Its only weakness is voice: it leads with the imperative 'Use this skill whenever...' instead of a third-person capability statement, which the rubric penalizes on specificity.

Suggestions

Rewrite the opening in third person (e.g., 'Produces, opens, transforms, fills, and reads PDF files') and keep 'Use this skill whenever...' as a trailing trigger clause, mirroring the rubric's good examples.

Optionally lead with a one-line capability summary before the 'That includes:' list so the what/when split reads as third-person capability + explicit trigger.

Dimension	Reasoning	Score
Specificity	The description lists many concrete actions ('extracting text or tables', 'combining, carving, rotating, cropping, or watermarking pages', 'composing a fresh PDF', 'filling AcroForm fields', 'encrypting or unlocking', 'running OCR', 'rendering pages to PNG/JPEG') matching the score-3 anchor, but it leads with the imperative/second-person 'Use this skill whenever' rather than a third-person capability statement, so the rubric's voice penalty reduces this by one level.	2 / 3
Completeness	It explicitly answers both what ('That includes: extracting text or tables... composing a fresh PDF...') and when ('Use this skill whenever a PDF file is being produced, opened, transformed, filled, or read' plus 'Trigger on mentions of...'), matching the score-3 anchor with explicit triggers.	3 / 3
Trigger Term Quality	It covers natural terms users would say — 'PDF', 'a filename ending in .pdf', 'turn this into a PDF report', 'AcroForm / form fields', 'scanned document' — matching the score-3 anchor for good coverage of natural keywords.	3 / 3
Distinctiveness Conflict Risk	The niche is clearly PDF-specific with distinct triggers (AcroForm, .pdf filenames, OCR) unlikely to fire for unrelated skills, matching the score-3 anchor for a clear niche with distinct triggers.	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
relative_links	Relative link issues: 10 missing	Warning

	Total	15 / 16 Passed

Repository: XiaomiMiMo/MiMo-Code
Path: packages/opencode/src/skill/builtin/.bundle/pdf-official/SKILL.md
Commit: ff87d47

Reviewed: about 9 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.