Requirements
- Target platform
- OpenClaw
- Install method
- Manual import
- Extraction
- Extract archive
- Prerequisites
- OpenClaw
- Primary doc
- SKILL.md
Tencent SkillHub Β· AI
LLMs.txt Generator
Generate a well-structured llms.txt file for any business website. Crawls the site, has a short conversation to fill in gaps, and produces an agent-optimized...
skill openclawclawhub Free
Generate a well-structured llms.txt file for any business website. Crawls the site, has a short conversation to fill in gaps, and produces an agent-optimized...
β¬ 0 downloads β
0 stars Unverified but indexed
Install for OpenClaw
Quick setup
- Download the package from Yavira.
- Extract the archive and review SKILL.md first.
- Import or place the package into your OpenClaw setup.
Package facts
- Download mode
- Yavira redirect
- Package format
- ZIP package
- Source platform
- Tencent SkillHub
- What's included
- SKILL.md, package.json, references/llms_txt_spec.md, scripts/crawl.py
Validation
- Use the Yavira download entry.
- Review SKILL.md after the package is downloaded.
- Confirm the extracted package contains the expected setup assets.
Install with your agent
Agent handoff
Hand the extracted package to your coding agent with a concrete install brief instead of figuring it out manually.
- Download the package from Yavira.
- Extract it into a folder your agent can access.
- Paste one of the prompts below and point your agent at the extracted folder.
New install
I downloaded a skill package from Yavira. Read SKILL.md from the extracted folder and install it by following the included instructions. Tell me what you changed and call out any manual steps you could not complete.
Upgrade existing
I downloaded an updated skill package from Yavira. Read SKILL.md from the extracted folder, compare it with my current installation, and upgrade it while preserving any custom configuration unless the package docs explicitly say otherwise. Summarize what changed and any follow-up checks I should run.
Trust & source
Release facts
- Source
- Tencent SkillHub
- Verification
- Indexed source record
- Version
- 0.1.0
Provenance
- Publisher
- ngm9
- Source page
- View original listing
- Canonical URL
- Open canonical page
Documentation
Overview
This skill crawls a business website, extracts structured information, and generates a properly formatted llms.txt file β the standard that makes any business readable and transactable by AI agents. It follows the llmstxt.org specification with business-specific extensions: ## Team β builds agent trust in the people behind the business ## Clients & Testimonials β social proof for agent decision-making ## For Agents β how agents can interact (or a clear "coming soon" notice) Read references/llms_txt_spec.md before generating any output.
Step 1 β Get the URL
If the user didn't provide a URL, ask: "What's the website URL?" Normalize it (add https:// if missing).
Step 2 β Crawl
Run the crawler: ~/.virtualenvs/llms-txt-generator/bin/python3 \ ~/.openclaw/workspace/llms-txt-generator/scripts/crawl.py \ {url} > /tmp/llms_business_info.json Read /tmp/llms_business_info.json. Note: What pages were crawled What was found vs missing (team, pricing, testimonials, API) Whether an existing llms.txt was found Tell the user briefly: "Crawled {domain} ({N} pages). Found: {what was found}. I'll ask about a few things I couldn't determine." If the crawl found an existing llms.txt, note it: "I noticed you already have a llms.txt at {domain}/llms.txt. I'll generate a fresh one β you can compare and decide which to keep."
Step 3 β Ask for additional sources (always ask this first)
"Are there any other pages I should read? (docs, API reference, existing llms.txt, press page β anything useful)" If they provide URLs, re-run the crawl with those extras: ~/.virtualenvs/llms-txt-generator/bin/python3 \ ~/.openclaw/workspace/llms-txt-generator/scripts/crawl.py \ {url} {extra_url1} {extra_url2} > /tmp/llms_business_info.json If they say no/skip, continue.
Step 4 β Generate Pass 1 draft + gap report
Generate a draft llms.txt now using what you have from the crawl. Use all heuristic signals (team_found, testimonials_found, pricing_found, etc.) and the raw_text_summary. Write the draft. For any section you couldn't populate confidently, use a clear [NOT FOUND] placeholder. Then show it to the user with a gap report: "Here's a first draft of your llms.txt: {draft} Found automatically: {brief list β e.g. emails, pricing page, testimonials from Wybrid + Cital} Couldn't determine: {brief list β e.g. team, pricing figures, API} Two questions to start: {Most important gap β e.g. "Who's on the founding team? Names, roles, and an email if you're comfortable."} {Second most important β e.g. "What's your pricing model? Even a rough description β per-candidate, subscription, etc."} _(I have a few more after these. Also β say 'dig deeper' if you'd rather I try to find it myself.)"
Step 4b β Handle "dig deeper" (Pass 2)
If the user says "dig deeper" (or similar β "try again", "re-crawl", "look harder"): Re-run the crawl in deep mode: ~/.virtualenvs/llms-txt-generator/bin/python3 \ ~/.openclaw/workspace/llms-txt-generator/scripts/crawl.py \ {url} {extra_urls} --deep > /tmp/llms_business_info.json This returns pages_raw β the full raw text of every crawled page. Use it to extract structure with the LLM. In your generation prompt (Step 5), add: In addition to the heuristic signals, here is the full raw text from each crawled page. Extract team members, testimonials, pricing details, and any API information directly from this text. Homepage raw text: {pages_raw[homepage_url]} Team page raw text (if available): {pages_raw[team_url]} Pricing page raw text (if available): {pages_raw[pricing_url]} Tell the user: "Doing a deeper crawl β this takes a bit longer but I'll extract everything I can from the raw page content." After Pass 2, show the updated draft with the same gap report format. Whatever still can't be found, ask the user directly.
Step 5 β Conversational gap-filling (for anything still missing)
Ask questions one at a time β only for things still [NOT FOUND] after Pass 1/2. Wait for each answer. Stop as soon as you have enough to finalize. Use your judgment β if the user has already filled most gaps conversationally, skip remaining questions and generate. Q1 β Core value for agents (always ask): "In one or two sentences: what should an AI agent understand about what it can do or get by working with {domain}?" Q2 β Team (ask if team not found in crawl): "I didn't find team info publicly. Want to add a Team section? It helps agents trust who's behind the business. Just names, roles, and emails if you're comfortable." Q3 β Clients / testimonials (ask if not found): "Any existing clients or testimonials I can include? Even a couple of company names or a one-line quote builds agent trust. Totally optional." Q4 β API / integration (ask if api_found=false): "Is there a public API or docs page agents can reference? (skip if not applicable)" Q5 β Pricing (ask if pricing_found=false): "What's the pricing model? Even a rough description helps β like 'per assessment' or 'monthly subscription'." Q6 β ICP / agent-buyers (ask if not obvious from context): "Who are the kinds of agents or automated systems most likely to want to work with you? (e.g. HR bots, recruiting pipelines)" Q7 β Anything else (optional, ask last): "Anything else agents should know before working with you? (geographic limits, onboarding steps, etc.)"
Step 6 β Generate final llms.txt
Read references/llms_txt_spec.md now if you haven't already. Generate the complete llms.txt using ALL information gathered: The crawled business_info JSON (and pages_raw if deep mode ran) The user's answers from the conversation The spec from references/llms_txt_spec.md Generation rules: Follow the spec format exactly: H1 title β blockquote summary β H2 sections β named links Every bullet = - [Title](url): description β no plain text bullets Section order: Services β Team β Clients & Testimonials β For Agents β Pricing β API β Links β Optional ## Team: Always include. Use crawled/user-provided data. If none available, omit silently. ## Clients & Testimonials: Always try to include. Structure: ICP bullets first (who the business serves) Then a ### subsection per named client where you have a real quote or case study detail Each subsection: blockquote with verbatim/lightly-cleaned quote, optional Problem: and Outcome: lines If you only have a name + one-liner with no detail, a single bullet is fine Never invent quotes or outcomes ## For Agents: ALWAYS include. If no API info: add the "coming soon" notice + contact email. Never skip. ## Pricing: If unknown, link to pricing page with no summary. If no pricing page, omit. ## API: Document URL only β no auth details, no secrets. ## Optional: FAQs, blog, case studies, anything supplementary. Do NOT invent facts. If something is unknown and user didn't provide it, either omit it or note it clearly. Keep it tight β this is for agents, not humans. No marketing fluff. Write the final llms.txt to /tmp/llms_final.txt.
Step 7 β Show and confirm
Show the full llms.txt to the user in a code block, then ask: "Here's your llms.txt π Does this look right? You can: Tell me what to change Say 'save' to download it Say 'deploy' when you're ready to push it live (Phase 2)"
Step 8 β Handle revisions
If the user asks for changes, make them and show the updated version. Repeat until satisfied. If they say 'save': tell them the file is at /tmp/llms_final.txt and they can copy it to their project. If they say 'deploy': acknowledge and note that deployment via Cloudflare Workers is coming in Phase 2.
Notes
Existing llms.txt: If the crawl found one, mention it early: "I noticed you already have a llms.txt. I'll generate a fresh one β you can compare and decide which to keep." Anchor-only links (e.g. /#section): Skip for Level 2 crawling β they don't load new content. The For Agents section is mandatory β even if empty of details, it signals intent to support agents and provides a contact path. Never ask all questions at once β it's a conversation, not a form.
Category context
Agent frameworks, memory systems, reasoning layers, and model-native orchestration.
Source: Tencent SkillHub
Largest current source with strong distribution and engagement signals.
Package contents
Included in package
2 Docs1 Scripts1 Config
- SKILL.md
- references/llms_txt_spec.md
- scripts/crawl.py
- package.json