New: 97,000+ skills indexed from GitHub repos with 100+ stars · every skill safety-checkedBrowse top skillsTop skills
Esc to closeBrowse all skills
Submit a skillBrowse skills
Submit a skillBrowse skills

Agent skill

Document Generation

by bionic-gpt in bionic-gpt/bionic-gpt

Create polished printable documents and PDFs, including forms, checklists, reports, briefs, comparisons, worksheets, task lists, and other operational documents.

Apache-2.0Auto-check passedDocuments & Office

Install Document Generation

skills CLI
$ npx skills add bionic-gpt/bionic-gpt --skill document-generation -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install bionic-gpt/bionic-gpt document-generation --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/bionic-gpt/bionic-gpt.git skills-src && mkdir -p .claude/skills && cp -r skills-src/crates/builtin-skills/skills/document-generation .claude/skills/document-generation && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Facts

Skill name
document-generation
GitHub stars
2.4k
Token cost
~1.1k tokens
SKILL.md length
541 words
Files
4 (incl. references)
Skills in repo
21
Repo updated
First seen
Licence
Apache-2.0

At a glance

Create polished printable documents and PDFs, including forms, checklists, reports, briefs, comparisons, worksheets, task lists, and other operational documents.

  • Works in 7 steps: Read all source material and identify → Choose a layout based on how the… → Start from the closest known-good… → …
  • Tasks that involve Task breakdown
  • SKILL.md covers Workflow, References, Design Principles and Source Fidelity, plus 4 more sections
  • Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md

What it does

Document Generation is an agent skill from bionic-gpt/bionic-gpt. Create polished printable documents and PDFs, including forms, checklists, reports, briefs, comparisons, worksheets, task lists, and other operational documents. Use Typst and compile to PDF.

Its SKILL.md is about 1.1k tokens, which your agent loads only when the skill is triggered. The skill folder holds 4 other files, including reference files.

It sits in Documents & Office, covering Task breakdown, PDF and Educational content. The repository describes itself as: Bionic is sovereign Agentic AI for the enterprise — Runs on-premise and can securely work with your sensitive data and systems. The licence is Apache-2.0.

When your agent uses it

  • Tasks that involve Task breakdown
  • Tasks that involve PDF
  • Tasks that involve Educational content

Example prompts

  • “/document-generation”

Workflow steps

7 steps, taken from the first numbered list in SKILL.md.

  1. Read all source material and identify
  2. Choose a layout based on how the document will actually be used.
  3. Start from the closest known-good reference in references/ rather than inventing Typst structure from scratch.
  4. Write the Typst source to /home/user/output//main.typ.
  5. Compile using the connector documented in /home/user/skills/typst/SKILL.md.
  6. If compilation fails, fix the Typst error and recompile until successful.
  7. Return the PDF only after successful compilation.

What it can do on your machine

Read from SKILL.md and the folder at commit c155c00. It shows what the files ask for, not the result of running them.

  • Tool permissions

    Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

    From allowed-tools in the SKILL.md frontmatter.

  • Runs code

    No scripts in the folder and no shell commands in SKILL.md (its code samples are typst).

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    No URLs in SKILL.md.

    From URLs in SKILL.md, links to its own repository left out.

  • Credentials

    Names no API keys, tokens, secrets or passwords.

    From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Document Generation loads about 1.1k tokens when it runs, and up to ~2.9k if it reads all its reference files. Until then it costs about 53 tokens; SKILL.md has 541 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~53
When it runs · the whole SKILL.md, loaded when a task matches
~1.1k
With references · SKILL.md plus every file in references/, read only if the agent opens them
~2.9k

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Auto-check passed

The automated check found no risky patterns in SKILL.md.

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.

SKILL.md

The full file from bionic-gpt/bionic-gpt at commit c155c00, republished under its Apache-2.0 licence (© bionic-gpt). 541 words, ~1,088 tokens.

Download SKILL.mdSave it as .claude/skills/document-generation/SKILL.md (or your agent's skills folder). This skill also uses 3 other files; get the full folder from GitHub.
name
document-generation
description
Create polished printable documents and PDFs, including forms, checklists, reports, briefs, comparisons, worksheets, task lists, and other operational documents. Use Typst and compile to PDF.

Document Generation

Use this skill when the user asks for a printable document or PDF artifact.

Workflow

  1. Read all source material and identify:
    • required content
    • information users must fill in
    • approvals or signatures required
    • operational sequence or sections
  2. Choose a layout based on how the document will actually be used.
  3. Start from the closest known-good reference in references/ rather than inventing Typst structure from scratch.
  4. Write the Typst source to /home/user/output/<document-name>/main.typ.
  5. Compile using the connector documented in /home/user/skills/typst/SKILL.md.
  6. If compilation fails, fix the Typst error and recompile until successful.
  7. Return the PDF only after successful compilation.

References

Choose the closest reference and adapt it:

  • references/operational-form.typ — forms, checklists, task lists, sign-offs, handwritten fields.
  • references/professional-report.typ — reports with title, summary, sections, findings, tables, and recommendations.
  • references/comparison-recommendation.typ — side-by-side option or vendor comparisons with criteria and a recommendation.

Use references as working Typst patterns, not as fixed visual designs. Preserve their known-good structure where practical and change content, labels, sections, and layout to fit the task.

Design Principles

Treat the document as an operational artifact, not just formatted text.

  • Preserve all required source content.
  • Infer useful fields from the workflow when they are clearly implied, such as date, location, prepared by, check time, assigned employee, initials, notes, or verification.
  • Use clear visual hierarchy: title, metadata, sections, task groups, verification, final approval.
  • Prefer tables for repeated tasks and structured data entry.
  • Give handwriting fields enough physical space.
  • Make task descriptions the widest column.
  • Keep initials and signature fields narrow but usable.
  • Use page breaks deliberately when a section is easier to use on its own page.
  • Keep final manager approval at the end when requested.
  • Use concise completion-standard wording where appropriate without changing the underlying requirement.
  • Add small workflow aids when they clearly improve usability, such as task IDs, section labels, or instructions.
  • Do not add unsupported policies, business rules, names, dates, or requirements.
Show full SKILL.md (226 more words)Show less

Source Fidelity

When the task is based on attached material:

  • Treat the source as authoritative for required content and terminology unless the user asks for rewriting.
  • Do not omit required source items to make the document shorter or prettier.
  • You may improve grouping, labels, typography, field design, and concise task wording without changing the underlying requirement.

Typst Guidance

Typst is not Markdown.

Use Typst headings:

typst
= Document Title
== Section Heading

For documents that resemble one of the references, adapt that reference instead of inventing layout primitives.

Avoid unsupported or untested Typst constructs. Prefer primitives already demonstrated in the references.

Compilation

Read /home/user/skills/typst/SKILL.md for the current compilation function.

Call typst_compile_document with run_python. Pass the workspace files using the documented file_paths argument, including /home/user/output/<document-name>/main.typ and any referenced assets. Bionic reads the files from the VFS without placing their contents in model context.

Repair Loop

If compilation fails:

  1. Read the first compiler error carefully.
  2. Fix the relevant Typst syntax or layout issue in main.typ.
  3. Compile again.
  4. Repeat until successful.

Do not switch to Markdown after a Typst error. Do not hide or ignore compilation failures.

Quality Check

Before completing the task, verify:

  • every required source item is present
  • writable fields are large enough to use
  • signatures and approvals are in the correct place
  • the layout is practical when printed
  • sections are not awkwardly orphaned across pages
  • the PDF compiled successfully

© bionic-gpt, Apache-2.0. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

SKILL.md and 3 other files (references) in crates/builtin-skills/skills/document-generation of bionic-gpt/bionic-gpt.

  • SKILL.md
  • references/comparison-recommendation.typ
  • references/operational-form.typ
  • references/professional-report.typ

Open the folder on GitHubat commit c155c00

Compare with similar skills

Document Generation next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

Document Generation compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Document Generation this skillbionic-gpt/bionic-gpt2.4k—~1.1kAutomated safety check: PassApache-2.0
Canvas Reading AnnotationX-isdoingreat/canvas-pilot125—~2.3kAutomated safety check: PassAGPL-3.0
Canvas Reading AnnotationX-isdoingreat/canvas-pilot125—~8.4kAutomated safety check: NotesAGPL-3.0
Paper2posterQuZhan51496/paper2anything468—~9.2kAutomated safety check: NotesApache-2.0
Excel Unmerge Before WriteHKUDS/OpenSpace7.7k—~820Automated safety check: PassMIT
Paw Ps Knowledge Executorpawbytes/skill-suites110—~1.8kAutomated safety check: PassMIT

Similar skills

  • Canvas Reading Annotation

    X-isdoingreat/canvas-pilot

    A skill your agent uses for an approved short academic-reading assignment routed by canvas-execute, including in-place PDF annotation, answer blanks, video worksheets, or short reflection drafts.

    125 GitHub stars~2.3k tokensUpdated 2 mo ago
    EducationAuto-check passed

  • Canvas Reading Annotation

    X-isdoingreat/canvas-pilot

    Generic reading-annotation handler for academic-writing courses — annotates reading PDFs with color-coded highlights + margin notes + filled answer blanks per the instructor's rubric.

    125 GitHub stars~8.4k tokensUpdated 2 mo ago
    EducationAuto-check: notes

  • Paper2poster

    QuZhan51496/paper2anything

    Convert academic papers (PDF) into conference posters (HTML/PNG).

    468 GitHub stars~9.2k tokensUpdated 2 mo ago
    Documents & OfficeAuto-check: notes

  • Excel Unmerge Before Write

    HKUDS/OpenSpace

    Unmerge merged cells in openpyxl worksheets before writing values to avoid AttributeError

    7.7k GitHub stars~820 tokensUpdated 1 mo ago
    Documents & OfficeAuto-check passed

  • Paw Ps Knowledge Executor

    pawbytes/skill-suites

    Builder of knowledge products such as courses, ebooks, guides, memberships, and educational assets.

    110 GitHub stars~1.8k tokensUpdated 4 days ago
    Documents & OfficeAuto-check passed

  • Japanese Tutor

    sundial-org/awesome-openclaw-skills

    Interactive Japanese learning assistant. An agent skill from sundial-org/awesome-openclaw-skills.

    663 GitHub stars~760 tokensUpdated 7 mo ago
    Documents & OfficeAuto-check passed

More from bionic-gpt/bionic-gpt

All 21 skills in this repo

  • Static Sites

    bionic-gpt/bionic-gpt

    Create or modify Bionic's generated marketing site, documentation, blog, course pages, and static assets.

    2.4k GitHub stars~920 tokensUpdated today
    Auto-check passed

  • Automationbench Eval

    bionic-gpt/bionic-gpt

    Load the repository's AutomationBench OpenAPI catalogue and run evaluations against the local simulator.

    2.4k GitHub stars~619 tokensUpdated today
    Auto-check passed

  • Ron Auth

    bionic-gpt/bionic-gpt

    Implement identity and authorization boundaries in Rust on Nails applications.

    2.4k GitHub stars~667 tokensUpdated today
    Auto-check passed

  • Ron Web Pages

    bionic-gpt/bionic-gpt

    Build server-rendered Dioxus pages using opinionated Rust on Nails patterns.

    2.4k GitHub stars~616 tokensUpdated today
    Auto-check passed

  • Local Deployment

    bionic-gpt/bionic-gpt

    Deploy one or more locally built Bionic services into the user's k3d cluster.

    2.4k GitHub stars~540 tokensUpdated today
    Auto-check: notes

  • Office Tools

    bionic-gpt/bionic-gpt

    Regenerate the built-in Office OpenAPI specs from a selected Archipelago ref.

    2.4k GitHub stars~352 tokensUpdated today
    Auto-check passed

Categories

Questions about Document Generation

What does Document Generation do?

Create polished printable documents and PDFs, including forms, checklists, reports, briefs, comparisons, worksheets, task lists, and other operational documents. Document Generation is an agent skill from bionic-gpt/bionic-gpt. Create polished printable documents and PDFs, including forms, checklists, reports, briefs, comparisons, worksheets, task lists, and other operational documents.

When should I use Document Generation?

Document Generation fits situations like: tasks that involve Task breakdown; tasks that involve PDF; tasks that involve Educational content.

How do I install Document Generation in Claude Code?

Run `npx skills add bionic-gpt/bionic-gpt --skill document-generation -a claude-code`. Or copy the skill folder (crates/builtin-skills/skills/document-generation in bionic-gpt/bionic-gpt) into .claude/skills/document-generation in your project. Claude Code loads it when a task matches its description.

How do I install Document Generation in Codex?

Run `npx skills add bionic-gpt/bionic-gpt --skill document-generation -a codex`. Or copy the skill folder (crates/builtin-skills/skills/document-generation in bionic-gpt/bionic-gpt) into .agents/skills/document-generation in your project. Codex loads it when a task matches its description.

Can I use Document Generation in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add bionic-gpt/bionic-gpt --skill document-generation -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/document-generation, .gemini/skills/document-generation, .github/skills/document-generation and .opencode/skills/document-generation in your project.

What does Document Generation need to run?

SKILL.md names no scripts, command-line tools or credentials: Document Generation is instructions for the agent only.

Does Document Generation access the network?

SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.

Is Document Generation safe to install?

Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.

What licence does Document Generation use?

Document Generation is published under the Apache-2.0 licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Document Generation use?

About 1.1k tokens (SKILL.md is roughly 4.4k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full. Its references folder adds about 1.8k tokens, read only when the agent opens those files.

What are the alternatives to Document Generation?

Skills that share tags, products or a category with Document Generation: Canvas Reading Annotation (X-isdoingreat/canvas-pilot, 125 stars), Canvas Reading Annotation (X-isdoingreat/canvas-pilot, 125 stars), Paper2poster (QuZhan51496/paper2anything, 468 stars) and Excel Unmerge Before Write (HKUDS/OpenSpace, 7.7k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Document Generation?

bionic-gpt (a GitHub organization) maintains it in bionic-gpt/bionic-gpt, which has 2,383 GitHub stars. The repository holds 21 skills in this directory. The repository was last updated on October 7, 2026.

Source: bionic-gpt/bionic-gpt on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.