PDF
1. Common requirements
Set SKILL_DIR to the absolute directory containing this file, not the task's
working directory. Identify output format(s), source, content features and
formatting requirements first. Deliver only the requested format(s); an internal
DOCX authoring file is not automatically an extra deliverable.
Honor explicit requirements and supplied templates, including typography, colors,
cover/no-cover layout, spacing, and numbering. Do not silently substitute a
preset. Verify actual capabilities and disclose unavailable fonts or unsupported
requirements. Presets do not supply research, finance, legal or medical expertise
or standards certification.
2. Named manuscript requirement or visual preset
- Named manuscript: for strict APA, IEEE or a journal/institution template,
select capable authoring per requirement profiles.
--type academic does not implement APA/IEEE. Consider
DOCX and PDF export when appropriate; verify its actual fonts
and layout too, rather than claiming unsupported compliance.
- Visual-only: for a generic, nonstandard academic-looking PDF or another
designed report, read presentation before
CREATE/REFORMAT. It owns supported preset names, tokens and overrides.
- DOCX companion control: render the authored DOCX through its own route;
do not independently redesign the PDF with this pipeline.
3. Select the operation
| Authorized task |
Direct workflow |
Existing implementation |
| New cover/body PDF |
Route A: CREATE |
palette.py → cover.py → render_cover.js → render_body.py → merge.py |
| Form inspection or filling |
Route B: FILL |
fill_inspect.py → fill_write.py |
| Requested redesign of an existing document |
Route C: REFORMAT |
reformat_parse.py → CREATE |
| Completed output |
VALIDATE |
Reopen, source comparison and applicable actual-page QA |
For a creation/redesign request, clarify whether a source exists if needed:
existing source → REFORMAT, no source → CREATE. FILL stays separate; an input
alone does not authorize redesign. These remain the three implemented operations,
with no new general READ, OCR, scans, signature or exact-layout editing workflow.
PDF text parsing is best-effort, not lossless layout or source reconstruction.
Read environment for only the selected
route. For this cover/body pipeline, run
bash "$SKILL_DIR/scripts/make.sh" check once per session before this pipeline's
CREATE/REFORMAT; it checks actual Chromium launch. A different authoring route uses
that route's setup and validation instead. DOCX-to-PDF does not require Chromium;
FILL and read-only inspection need Python/pypdf, not the browser pipeline: do
not make them install Chromium.
Load content features directly
For every CREATE/REFORMAT using this pipeline, read the
block contract, then only
applicable sections. This is the single block-schema authority; presentation
owns appearance, not duplicated fields. Follow the operation's workflow and
actual output validation before delivery.
| Required feature |
Direct reference |
| Headings, prose, lists, tables, breaks and spacing |
Common blocks and tables |
| Equations, labels and mathtext limits |
Mathematics |
| Charts, datasets and defaults |
Charts |
| Images, figures, captions and shared numbering |
Figures and captions |
| Citations and references |
Bibliography |
| Code whitespace and language labels |
Code |
| Process nodes, arrows and back-edges |
Flowcharts |
| Delivered content features |
Feature-specific rendering QA |
Package organization
references/common/, domains/, operations/ and implementation/ separate
appearance, applicable requirements, workflows and technical detail. All guides
are linked directly above; load only relevant files. scripts/ entry points and
licenses remain in their existing locations. A successful check, merge or parser
call is not a substitute for inspecting content and actual pages; disclose
unexecuted checks.
1---2name: pdf3description: >4 Create, fill, or reformat PDF files, including research and technical reports with5 tables, charts, equations, citations, figures, code, and flowcharts. Use for6 "make a PDF", "write a proposal", "professional document", "cover page",7 "fill in this PDF form", "what fields does this PDF have", "reformat this8 document", or "convert this Markdown/text to PDF". Distinguish named manuscript9 requirements (APA, IEEE, journal/institution templates) from visual presets:10 --type academic is appearance, not standards compliance or research expertise.11 For a PDF companion to Word, render the DOCX through ../docx/SKILL.md so both12 requested deliverables retain the same content and layout.13license: MIT14metadata:15 source: https://skillmd.com/skills/vm0-ai/pdf16 version: "1.0"17 category: document-generation18---1920# PDF2122## 1. Common requirements2324Set `SKILL_DIR` to the absolute directory containing this file, not the task's25working directory. Identify output format(s), source, content features and26formatting requirements first. Deliver only the requested format(s); an internal27DOCX authoring file is not automatically an extra deliverable.2829Honor explicit requirements and supplied templates, including typography, colors,30cover/no-cover layout, spacing, and numbering. Do not silently substitute a31preset. Verify actual capabilities and disclose unavailable fonts or unsupported32requirements. Presets do not supply research, finance, legal or medical expertise33or standards certification.3435## 2. Named manuscript requirement or visual preset3637- **Named manuscript:** for strict APA, IEEE or a journal/institution template,38 select capable authoring per [requirement profiles](references/domains/profiles.md).39 `--type academic` does **not** implement APA/IEEE. Consider40 [DOCX](../docx/SKILL.md) and PDF export when appropriate; verify its actual fonts41 and layout too, rather than claiming unsupported compliance.42- **Visual-only:** for a generic, nonstandard academic-looking PDF or another43 designed report, read [presentation](references/common/presentation.md) before44 CREATE/REFORMAT. It owns supported preset names, tokens and overrides.45- **DOCX companion control:** render the authored DOCX through its own route;46 do not independently redesign the PDF with this pipeline.4748## 3. Select the operation4950| Authorized task | Direct workflow | Existing implementation |51|---|---|---|52| New cover/body PDF | [Route A: CREATE](references/operations/create.md) | `palette.py` → `cover.py` → `render_cover.js` → `render_body.py` → `merge.py` |53| Form inspection or filling | [Route B: FILL](references/operations/fill.md) | `fill_inspect.py` → `fill_write.py` |54| Requested redesign of an existing document | [Route C: REFORMAT](references/operations/reformat.md) | `reformat_parse.py` → CREATE |55| Completed output | [VALIDATE](references/operations/validate.md) | Reopen, source comparison and applicable actual-page QA |5657For a creation/redesign request, clarify whether a source exists if needed:58existing source → REFORMAT, no source → CREATE. FILL stays separate; an input59alone does not authorize redesign. These remain the three implemented operations,60with no new general READ, OCR, scans, signature or exact-layout editing workflow.61PDF text parsing is best-effort, not lossless layout or source reconstruction.6263Read [environment](references/implementation/environment.md) for only the selected64route. For this cover/body pipeline, run65`bash "$SKILL_DIR/scripts/make.sh" check` once per session before this pipeline's66CREATE/REFORMAT; it checks actual Chromium launch. A different authoring route uses67that route's setup and validation instead. DOCX-to-PDF does not require Chromium;68FILL and read-only inspection need Python/`pypdf`, not the browser pipeline: do69not make them install Chromium.7071## Load content features directly7273For every CREATE/REFORMAT using this pipeline, read the74[block contract](references/implementation/content.md#block-contract), then only75applicable sections. This is the single block-schema authority; presentation76owns appearance, not duplicated fields. Follow the operation's workflow and77[actual output validation](references/operations/validate.md) before delivery.7879| Required feature | Direct reference |80|---|---|81| Headings, prose, lists, tables, breaks and spacing | [Common blocks and tables](references/implementation/content.md#common-blocks-and-tables) |82| Equations, labels and mathtext limits | [Mathematics](references/implementation/content.md#mathematics) |83| Charts, datasets and defaults | [Charts](references/implementation/content.md#charts) |84| Images, figures, captions and shared numbering | [Figures and captions](references/implementation/content.md#figures-and-captions) |85| Citations and references | [Bibliography](references/implementation/content.md#bibliography) |86| Code whitespace and language labels | [Code](references/implementation/content.md#code) |87| Process nodes, arrows and back-edges | [Flowcharts](references/implementation/content.md#flowcharts) |88| Delivered content features | [Feature-specific rendering QA](references/implementation/content.md#feature-specific-rendering-qa) |8990## Package organization9192`references/common/`, `domains/`, `operations/` and `implementation/` separate93appearance, applicable requirements, workflows and technical detail. All guides94are linked directly above; load only relevant files. `scripts/` entry points and95licenses remain in their existing locations. A successful check, merge or parser96call is not a substitute for inspecting content and actual pages; disclose97unexecuted checks.