Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx skills add HolobiomicsLab/asb-skill-collections --skill sphinx-documentation-generation-and-api-reference-inclusiongit clone --depth 1 https://github.com/HolobiomicsLab/asb-skill-collectionsWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/holobiomicslab/asb-skill-collections/sphinx-documentation-generation-and-api-reference-inclusion)<a href="https://agentmods.dev/skills/holobiomicslab/asb-skill-collections/sphinx-documentation-generation-and-api-reference-inclusion"><img src="https://agentmods.dev/badge/skills/holobiomicslab/asb-skill-collections/sphinx-documentation-generation-and-api-reference-inclusion/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/holobiomicslab/asb-skill-collections/sphinx-documentation-generation-and-api-reference-inclusion"><img src="https://agentmods.dev/badge/skills/holobiomicslab/asb-skill-collections/sphinx-documentation-generation-and-api-reference-inclusion.svg" alt="Reviewed on agentmods" width="80" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00031 | $0.01525 |
| Opus 5 | $0.00015 | $0.00763 |
| Sonnet 5 | $0.00006 | $0.00305 |
| Haiku 4.5 | $0.00003 | $0.00153 |
Grade B, and why
sphinx-documentation-generation-and-api-reference-inclusion scanned grade B with 1 finding against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 6d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Strips warnings and disclaimersmediumAnti-refusal
Omitting safety caveats hides risk from the user and is a common jailbreak preamble.
After implementing or modifying utility functions in a library subpackage (e.g., cooltools.lib), use this skill to verify that the function is discoverable in the generated API documentation, that its docstring is proper How it starts
The opening of the file, as written. The whole thing — 103 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Sphinx Documentation Generation and API Reference Inclusion
Summary
Build and validate Sphinx documentation for a Python library, ensuring that utility functions and their docstrings are correctly rendered in the generated API reference. This workflow integrates Numpy-style docstrings with Sphinx to produce HTML documentation that exposes the library's public API.
When to use
After implementing or modifying utility functions in a library subpackage (e.g., cooltools.lib), use this skill to verify that the function is discoverable in the generated API documentation, that its docstring is properly formatted, and that the documentation build succeeds without warnings or errors.
When NOT to use
- Function docstrings are written in a non-Numpy style (e.g., Google or reST style) without Sphinx extensions configured to parse them — the resulting API documentation will render incorrectly or be missing parameter details.
- The target function has not been added to the library's public API interface or init.py imports — Sphinx will not discover it for inclusion in the reference.
- The Sphinx configuration is not set up to parse Python docstrings (e.g., sphinx.ext.autodoc or sphinx.ext.napoleon is not enabled) — no docstring content will be extracted.
Inputs
- Python source code files with function definitions in a library subpackage (e.g., cooltools/lib/adaptive_coarsegrain.py)
- Numpy-style docstrings attached to functions and classes
- Sphinx configuration file (conf.py)
- Documentation source files (e.g., docs/api.rst or equivalent)
Outputs
- Generated HTML documentation (docs/_build/html/)
- API reference pages listing functions, classes, and their docstrings
- Build report indicating successful or failed Sphinx compilation
- Documentation validation report confirming function visibility and formatting
How to apply
First, ensure that all utility functions use Numpy-style docstrings, which Sphinx can automatically parse and render into the API reference. Run make docs from the repository root to trigger the Sphinx build process, which will generate HTML documentation from the source code and docstrings. Inspect the generated HTML files in the build directory (typically docs/_build/html/) to confirm that the target function appears in the appropriate API section (e.g., cooltools.lib) with correctly formatted parameters, returns, and examples. If the function is missing or malformed, verify that (1) the module is correctly imported in the documentation configuration, (2) the docstring follows Numpy format conventions, and (3) no Sphinx warnings were emitted during the build. Re-run the build after corrections and re-inspect the HTML output.
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 6d ago First seen · 103 lines · 31 tokens per session scan B 523ca034f9fd
sphinx-documentation-generation-and-api-reference-inclusion is a skill published in the GitHub repository HolobiomicsLab/asb-skill-collections (15 stars, last pushed 2d ago), licensed Apache-2.0. It adds 31 tokens to every session and 1,525 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it B with 1 finding (strips warnings and disclaimers). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-06.
Other skills, from other repositories
automated-soap-note-generator
Generate structured SOAP notes from clinical narratives, transcripts, or existing notes; use when the user needs de-identified clinical documentation organized into Subjective, Objective, Assessment, and Plan sections, with clear assumptions and review points.
digital-twin-discharge-drafter
Use when drafting patient discharge summaries, creating personalized discharge instructions, simulating post-discharge outcomes, reducing hospital readmissions, or optimizing care transitions. Generates AI-enhanced discharge documentation with digital twin predictions for improved patient safety.
discharge-summary-writer
Generate hospital discharge summaries from admission data, hospital course, diagnoses, procedures, and follow-up plans; use when a structured discharge document is required from clinical notes.
ectd-xml-compiler
Automatically convert uploaded drug application documents (Word/PDF) into XML skeleton structure compliant with eCTD 4.0/3.2.2 specifications.
medical-scribe-dictation
Convert physician verbal dictation into structured SOAP notes. Trigger.
format-references-zotero
Zotero reference formatting workflow. Converts [PMID: xxxx] markers in Markdown manuscripts to Word (.docx) with native Zotero field codes (ADDIN ZOTEROITEM / ADDIN ZOTEROBIBL). Users click "Refresh" once in Word to complete formatting. Includes searchstyles.py for searchin...