Best Claude Skills for Documents (2026)

Most "best skills" lists are copied README summaries. This one isn't: we installed all 156 documents skills in our catalog, ran each against a baseline and scored four criteria. 68 passed cleanly, average score 8.8/10. The one to start with: TR Dizin.

Ranked by SkillProof Score · how we score

  1. 1

    TR Dizin

    Stdlib-only CLI for the open TR Dizin (Turkish national academic index) JSON API — search, filters, PDF-to-text

    From our test: Ran the real live API end to end — search, field-scoped advanced search, author lookup, the documented ':' -in-query error (exact message and exit code 2), and a full PDF-to-markdown extraction of a…

    Tested · Works ★ 10.0/10 by saidsurucu

  2. 2

    Patent Writing Chinese

    Generates CNIPA-style Chinese patent .docx files with real OMML equations and B&W block diagrams.

    From our test: Actually ran the bundled example end-to-end (pip install python-docx/lxml/matplotlib, executed examples/example_patent.py) and diffed the resulting docx XML against a plain python-docx baseline…

    Tested · Works ★ 10.0/10 by StellaQIU27

  3. 3

    DOCX — Word Documents

    Create and edit real Word documents — headings, tables, tracked changes.

    From our test: Produced a 14-page report with a table of contents, numbered headings, styled tables and a letterhead. Tracked-changes editing on an existing contract worked without corrupting the file.

    Tested · Works ★ 9.6/10 by Anthropic

  4. 4

    Shipping Artifacts

    Defines the doc set that makes an AI-built app reviewable before it ships.

    From our test: For a Next.js + Supabase + Stripe app it produced a structured doc set with per-step deny cases and a permissions matrix instead of a flat README, and its own docs admit test docs need a separate…

    Tested · Works ★ 9.6/10 by phuryn

  5. 5

    Generate Requirement Drafts

    Drafts EARS-format Simulink requirements as .slreqx or validated YAML with traceability.

    From our test: Ran the mini-task live: generated a 3-requirement CruiseControl_requirements.yaml following the skill's EARS + draft-marking + provenance rules and it parsed clean with a real `yaml.safe_load` check…

    Tested · Works ★ 9.6/10 by matlab

  6. 6

    PDF Proof

    Finds a value in a PDF, verifies it's the right occurrence, and outputs a highlighted screenshot proof page.

    From our test: Built a test invoice PDF with the same dollar amount appearing twice — once as the real total, once inside an unrelated instruction sentence — and the bundled script correctly found both, let me pick…

    Tested · Works ★ 9.6/10 by metedata

  7. 7

    PRISMA Systematic Literature Review

    Walks a user through a PRISMA 2020 systematic review and outputs a journal-format .docx

    From our test: Ran a PRISMA flow-diagram mini-task end to end: the skill correctly picked Template A, flagged a missing 'reports not retrieved' count instead of guessing at it, and produced both a table version and…

    Tested · Works ★ 9.6/10 by keemanxp

  8. 8

    Quality Checking

    Cross-checks generated API docs against a route manifest and source middleware

    From our test: Fed it a doc file with a missing endpoint, two missing auth markers, and a malformed JSON example — it caught all four by cross-referencing the route manifest, where a generic 'review these docs'…

    Works with setup ★ 9.6/10 by huangjia2019

  9. 9

    Specifying MBD Algorithms

    Structured system/architecture/implementation/test spec templates for Simulink algorithms

    From our test: Ran a real baseline-vs-skill spec comparison for a moving-average accelerometer filter: the skill version added quantitative acceptance criteria, a units/sign-convention interface table, and explicit…

    Tested · Works ★ 9.6/10 by matlab

  10. 10

    DOCX Template Translator

    Converts LaTeX/PDF/Markdown into a .docx that actually follows an institutional Word template — TOC, numbering, citations included.

    From our test: Its 'Common Pitfalls' section reads like a postmortem, not marketing copy — it names the exact bug ('references render as [47]-[79] because the counter shares numId with headings') and the exact…

    Works with setup ★ 9.6/10 by zouchenzhen

How this ranking works

Each skill gets a fresh install in Claude Code, three trigger phrasings, and the same task run with and without it. Scores: installation (5), trigger reliability (5), output vs baseline (10), documentation honesty (5) — normalized to a 10-point SkillProof Score. Full rubric on the methodology page. Queue-verdict skills sit at the bottom until testing completes.

New here? Start with how to install Claude skills — or grab the whole setup in one command with a curated pack ($10).

On a different AI tool? These tested instructions adapt: see our conversion guides for Cursor rules, Copilot instructions, Windsurf and Custom GPTs.