Stats
Actions
Tags
From ekline-docs-skills
Generate an llms.txt file for your project following the llms.txt specification. Runs a helper script that detects your docs platform, classifies pages into sections, and resolves URLs. Makes documentation discoverable by large language models. Use when setting up a new docs site or improving AI discoverability.
How this skill is triggered — by the user, by Claude, or both
Slash command
/ekline-docs-skills:llms-txtThis skill is limited to the following tools:
The summary Claude sees in its skill listing — used to decide when to auto-load this skill
Run the helper script to scan documentation, then format and write the llms.txt file.
Run the helper script to scan documentation, then format and write the llms.txt file.
$ARGUMENTS — optional docs directory, --base-url URL for hosted docs, --full to also generate llms-full.txtpython scripts/generate_llms_txt.py $ARGUMENTS
The script handles:
Max 150 files per run. llms-full.txt limited to 20 files / 200KB.
If the JSON contains an error field:
no_docs_found — tell user no documentation files found, suggest passing a directorynot_a_directory — tell user the path is not a valid directoryUsing the sections object from the JSON, build the file:
# {project_name}
> {project_description}
## {Section Name}
- [{title}]({url}): {description}
Rules:
url field from the JSON (already resolved to URLs if base_url was found, otherwise relative paths)Show:
full_warning is present, show itAsk whether to:
llms.txt to project rootpublic/llms.txt for Next.js)Only if can_generate_full is true in the JSON:
full_files using the Read tool# {project_name}
> {project_description}
---
## {Page Title}
{Full page content}
Write to the same directory as llms.txt.
Use the Write tool to create llms.txt (and llms-full.txt if applicable).
Suggest to the user:
.gitignore if generated (or commit if hand-curated)npx claudepluginhub ekline-io/ekline-docs-skills --plugin ekline-docs-skillsGenerates llms.txt and llms-full.txt from git repo wikis for LLM-readable project docs per llms.txt spec. Resolves repo URL/branch first.
Generates a standards-compliant llms.txt file for any website by crawling the live site or reading the codebase directly. Helps make websites discoverable by AI agents and LLMs.
Generates llms.txt and llms-full.txt files for LLM crawler ingestion. Scopes expectations for Google vs. non-Google AI surfaces and resolves dynamic routes via sitemap.