llms-txt-generator
Upgrade llmtxt-generator.py by scanning apps/ for doc structure changes, then regenerate llms.txt and llms-en.txt while only adding missing sections. Use when updating the generator, adding new doc sections, or refreshing LLM text files.
Best use case
llms-txt-generator is best used when you need a repeatable AI agent workflow instead of a one-off prompt.
Upgrade llmtxt-generator.py by scanning apps/ for doc structure changes, then regenerate llms.txt and llms-en.txt while only adding missing sections. Use when updating the generator, adding new doc sections, or refreshing LLM text files.
Teams using llms-txt-generator should expect a more consistent output, faster repeated execution, less prompt rewriting.
When to use this skill
- You want a reusable workflow that can be run more than once with consistent structure.
When not to use this skill
- You only need a quick one-off answer and do not need a reusable workflow.
- You cannot install or maintain the underlying files, dependencies, or repository context.
Installation
Claude Code / Cursor / Codex
Manual Installation
- Download SKILL.md from GitHub
- Place it in
.claude/skills/llms-txt-generator/SKILL.mdinside your project - Restart your AI agent — it will auto-discover the skill
How llms-txt-generator Compares
| Feature / Agent | llms-txt-generator | Standard Approach |
|---|---|---|
| Platform Support | Not specified | Limited / Varies |
| Context Awareness | High | Baseline |
| Installation Complexity | Unknown | N/A |
Frequently Asked Questions
What does this skill do?
Upgrade llmtxt-generator.py by scanning apps/ for doc structure changes, then regenerate llms.txt and llms-en.txt while only adding missing sections. Use when updating the generator, adding new doc sections, or refreshing LLM text files.
Where can I find the source code?
You can find the source code on GitHub using the link provided at the top of the page.
SKILL.md Source
# LLMs.txt Generator Upgrader ## Goal Upgrade `llmtxt-generator.py` using current app structure and existing `apps/web/public/llms.txt`, then regenerate outputs. Only add new or missing sections and links. Do not remove, rename, or rewrite existing sections unless the user explicitly asks. ## Discovery: apps structure 1. Scan `apps/` to understand doc surfaces and routing structure. 2. Note any new top-level doc categories or developer resources that are not represented in the current `llms.txt`. ## Baseline: current llms.txt 1. Read `apps/web/public/llms.txt`. 2. Extract section headings (`##`) and link lists. 3. Treat this as the canonical baseline: preserve all existing sections and links, and avoid duplicates. ## Update the generator (llmtxt-generator.py) Always edit the generator, not the output files. - Add only missing sections or links to `CURATED_SECTIONS` or `ENGLISH_EXTRAS` so the generator reproduces the current `llms.txt` plus any new additions. - Keep descriptions short, factual, and consistent with the current style. - Keep URL patterns canonical (no `utm_` parameters). - Keep `LOCALES` aligned with `packages/i18n/src/config.ts` and update `LANGUAGE_NAMES` for any newly added locale. - If new routing patterns appear, update `normalize_llms_urls()` accordingly. ## Regeneration From the repo root: ``` python llmtxt-generator.py ``` Outputs: - `apps/web/public/llms.txt` - `apps/web/public/llms-en.txt` ## Output constraints - Only add new or missing sections/links; never delete existing ones. - Preserve ordering unless a new section clearly belongs next to related ones. - Do not fabricate `llms-full.txt`. Follow repo guidance or user instructions. - For non-English locales, note the generator preserves existing content if the file exists; change this behavior only if explicitly requested. ## Verification - `apps/web/public/llms.txt` contains all prior sections and any new additions. - Locale files exist for all configured locales. - Output URLs are canonical and contain no `utm_` parameters. ## Example requests - "Upgrade llmtxt-generator.py after a new docs section" - "Add missing llms.txt sections based on apps structure" - "Add a new locale and regenerate llms files"
Related Skills
refresh-agent-context
Audit this Turborepo for stale or missing agent-reference docs, then refresh repo and app-level `AGENTS.md` and related onboarding docs using the bundled workspace inventory script. Use when apps, packages, routes, ports, or shared tooling changed and the repo needs a fresh agent-oriented context pass.
migrate-page
Migrate a legacy page from apps/web/src/pages/ (Pages Router) to apps/web/src/app/ (App Router). Use when moving any existing page from the pages directory to the app directory.
create-page
Scaffold a new page in apps/web/src/app following the project's established pattern. Use when creating any new page or route under the web app.
magic-ui-generator
Utilizes Magic by 21st.dev to generate, compare, and integrate multiple production-ready UI component variations.
landing-page-generator
Generates high-converting Next.js/React landing pages with Tailwind CSS. Uses PAS, AIDA, and BAB frameworks for optimized copy/components (Heroes, Features, Pricing). Focuses on Core Web Vitals/SEO.
k8s-manifest-generator
Step-by-step guidance for creating production-ready Kubernetes manifests including Deployments, Services, ConfigMaps, Secrets, and PersistentVolumeClaims.
Invoice Generator
Creates professional invoices in markdown and HTML
Incident Postmortem Generator
Generate blameless incident postmortems from raw notes, Slack threads, or bullet points.
Partnership Agreement Generator
Generate comprehensive partnership agreements, joint venture frameworks, and strategic alliance documents for B2B relationships.
Employee Onboarding Generator
Build a structured 90-day onboarding plan for any role. Covers pre-boarding, Day 1, Week 1, 30/60/90-day milestones, buddy assignments, and success metrics.
Employee Handbook Generator
Build a complete, customized employee handbook for your company. Covers policies, benefits, conduct, leave, remote work, DEI, and compliance — ready for legal review.
IT Disaster Recovery Plan Generator
Build production-ready disaster recovery plans that actually get followed when things break.