Sixian-Li/knowledge-base-kit / skills/process_docs
process_docs
VerifiedIngest documents into this local knowledge workspace, preserving source content, drafting full text and summaries, validating, classifying and updating the catalog. Also supports check, batch, group, delete and teach requests.
| File | Kind | Size |
|---|---|---|
| SKILL.md | skill md | 6.5 KB |
| config.defaults.yaml | config | 792 B |
| references/agent-compatibility.md | markdown | 1.4 KB |
| references/extraction-methods.md | markdown | 2.2 KB |
| references/generation-templates.md | markdown | 3.1 KB |
| references/group-mode.md | markdown | 1.2 KB |
| references/modes.md | markdown | 1.5 KB |
| references/stages-5-6.md | markdown | 1.3 KB |
| references/usage-guide.md | markdown | 1.0 KB |
| scripts/_config.py | script | 5.9 KB |
| scripts/check_agent_setup.py | script | 4.9 KB |
| scripts/check_tex.js | script | 1.1 KB |
| scripts/extract_document.py | script | 4.6 KB |
| scripts/extract_docx.py | script | 4.4 KB |
| scripts/extract_html.py | script | 3.1 KB |
| scripts/extract_notebook.py | script | 16.9 KB |
| scripts/extract_pdf.py | script | 6.1 KB |
| scripts/fold_archives.py | script | 1.7 KB |
| scripts/generate_output.py | script | 1.2 KB |
| scripts/kb_tree.py | script | 11.4 KB |
| scripts/orchestrate_workers.py | script | 8.6 KB |
| scripts/render_rmd.py | script | 6.1 KB |
| scripts/validate_generated.py | script | 14.2 KB |
| scripts/worker_backends.py | script | 9.3 KB |
references/generation-templates.md
View on GitHub# Generation templates
These headings and scalar metadata fields are part of the validator contract.
Explanatory prose follows `OUTPUT_LANGUAGE`; keep the structural headings below.
Write factual coverage, not a fixed word count or a promise of perfect extraction.
## Full text
````markdown
---
source: source.pdf
format: <pdf|docx|html|htm|md|txt|ipynb|rmd|png|jpg|jpeg|gif|bmp|tif|tiff>
converted: YYYY-MM-DD
category: category/subcategory
description: "One concise description of this source."
doc_type: normal
---
# Source title
## Table of Contents
- [Content](#content)
- [Related Documents](#related-documents)
## Content
Follow the source's sections. Keep all substantive details, code and values.
Place each image or its description beside its original context. Mark uncertainty.
<details>
<summary>Raw source text (verbatim archive)</summary>
```text
Unmodified extracted PDF page text, including extraction artifacts.
```
</details>
## Related Documents
No related documents yet.
````
Choose one format label, not the literal alternatives. Keep the original source
filename, including spaces and extension; YAML-quote strings containing `:` or
`#`. `converted` is the actual conversion date. Parent documents add `children`
(a list of direct child slugs). Child documents add `parent` (the direct parent
slug). All documents preserve the original source when one exists; a synthetic
parent overview must have an explicit self-authored source attachment.
## Summary
```markdown
# Title — Reading guide
## Overview
What the document covers and when it is useful.
## Prerequisites
Required background, inputs or assumptions. State “None” if appropriate.
## Key Steps
The main procedure, argument or concepts in a useful order. A research or lecture
source may summarize reasoning instead of inventing an operational procedure.
## Configuration Reference
Important parameters, symbols, values and units; “Not applicable” when appropriate.
## Common Pitfalls
Source caveats, common mistakes and clearly identified extraction limitations.
## References
- [Full document](full.md#content)
```
## Formulas and fidelity
Use `$...$` for inline math and `$$...$$` for display math. Keep code and currency
as code/currency; do not turn every dollar sign or single letter into math. Pandoc
identifies math spans and the pinned KaTeX engine checks syntax. Viewer support
may differ. Never repair an apparent source formula error without preserving the
original and labeling the correction as commentary.
Keep raw PDF text archives intact when folding or editing prose. Fences may need
more than three backticks when source code itself contains backticks. Keep notes,
captions, axes, table cells, code output and error output. Absence of saved notebook
output means results are unavailable, not that the code succeeded.
## Category and catalog
A category `README.md` explains the category and lists its immediate children.
The root catalog lists each document's summary with a concise description and
useful keywords. Do not put a category README inside a document folder. Use
relative links that work after filing. Avoid duplicate or speculative relations.
Related skills
| Skill | Stars | Updated | Works with | Status | Install |
|---|---|---|---|---|---|
| slack-gif-creatoranthropics/skillsKnowledge and utilities for creating animated GIFs optimized for Slack. Provides constraints, validation tools, and animation concepts. Use when users request animated GIFs for Slack like "make me a GIF of X doing Y for Slack." | Stars: 197k | Updated | Claude CodeCodex | Verified | Install |
| ponytailDietrichGebert/ponytailLazy senior dev mode for any coding task: the smallest change that fully solves it, and a reply a busy human understands in one read. | Stars: 194k | Updated | Claude CodeCodex | Verified | Install |
| ponytail-debtDietrichGebert/ponytailHarvest every shortcut: comment into one debt ledger, so deferrals get tracked instead of forgotten. One-shot report. | Stars: 194k | Updated | Claude CodeCodex | Verified | Install |
| ponytail-debtDietrichGebert/ponytailList every `shortcut:` comment (and older `ponytail:` ones) as a debt ledger. One-shot report, changes nothing. Use for "ponytail debt", "what did ponytail defer", "list the shortcuts", /ponytail-debt. | Stars: 194k | Updated | Claude CodeCodex | Verified | Install |