How real projects summarise themselves for language models.
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
browser-useReads credentialsllms.txtbrowser-use/bux/docs/llms-full.txt
browser. Repository: https://github.com/browser-use/bux Public site: https://browser-use.github.io/bux/ ## What Bux Provides - Claude Code logged in and always available. - Telegram control through a private bot. - A persistent Chromium session
aallanReads credentialsllms.txtaallan/vera/docs/llms-full.txt
# Vera — Language Reference Documentation > Vera is a statically typed, purely functional programming language designed
1mancompanyllms.txt1mancompany/OneManCompany/docs/llms.txt
cost tracking - **1-on-1 Coaching**: Shape employee behavior through direct guidance - **File Approval**: Review and approve employee file changes ## Documentation - Full docs: https://1mancompany.github.io/OneManCompany/docs/ - Getting started: https://1mancompany.github.io
xixihhhhllms.txtxixihhhh/hotclip/docs/llms.txt
dynamic word-level captions, filler-word/silence removal, speaker diarization, speaker-filtered transcript review, and explicit model-picker controls. No credit system, no watermark, no uploads, no sign
kydlikebtcllms.txtkydlikebtc/awesome-grokbot/llms.txt
attribution), first_seen, checked, link_status, license. ## Categories coding-shipping (43) — write code, review PRs, babysit coding agents, keep the box healthy inbox-calendar (20) — triage mail, draft replies, defend
neoneyeReads credentialsllms.txtneoneye/PlanExe/public/llms.txt
governance structure, SWOT analysis, team role profiles, simulated expert criticism, work breakdown structure, plan review (critical issues, KPIs, financial strategy, automation opportunities), Q&A, premortem with failure scenarios, self-audit
timwuhaotianllms.txttimwuhaotian/the-pair/llms.txt
code, runs commands, and verifies the result. The main value is cross-validated AI code review. Instead of asking one model to write and self-review, The Pair separates planning
griddynamicsPipes a download into a shellllms.txtgriddynamics/rosetta/llms-full.txt
breaking stable; instant rollback. AI behavior authored in markdown, git-versioned, PR-reviewed, approved (rules-as-code). ================================================================================ 5 · DESIGN PRINCIPLES / MENTAL MODEL ================================================================================ - Agent-agnostic never lock to one IDE/model; adopt
ffrolivallms.txtffroliva/gflow-cli/llms.txt
/ffroliva/gflow-cli/blob/main/docs/USAGE.md): Command-by-command reference, including `gflow credits user|list`, manifest format, and exit codes. - [Architecture](https://github.com/ffroliva/gflow-cli/blob/main/docs/ARCHITECTURE.md): Provider abstraction, ui_automation transport, RFC 9457 error model. - [Authentication
daymoniollms.txtdaymonio/daymon/docs/llms-full.txt
Staff) — Proactive business ops 2. Sage (Researcher) — Deep research with strong opinions 3. Lux (Code Reviewer) — Catches what linters miss 4. Nova (Writer) — Sharp writing, cuts fluff 5. Iris (Email
daymoniollms.txtdaymonio/daymon/docs/llms.txt
search. - **Workers**: Named agent personalities with system prompts. 9 templates (Chief of Staff, Researcher, Code Reviewer, Writer, Email Assistant, Tech Trend Analyst, Competitor Tracker, DevOps, Data Analyst) or create your
ZeKaiNiellms.txtZeKaiNie/universal-examprep-skill/llms.txt
GitHub Copilot and 40+ agents): `npx skills add ZeKaiNie/universal-examprep-skill`, then `pip install pypdfium2`. - Claude Code plugin: `/plugin marketplace add ZeKaiNie/universal-examprep-skill`, then `/plugin install universal-exam-cram-coach@exam-cram-coach
mindroom-aiReads credentialsllms.txtmindroom-ai/mindroom/skills/mindroom-docs/references/llms-full.txt
# MindRoom > AI agents that know you and your work, in a chat app anyone
gameworkerkimllms.txtgameworkerkim/vibe-investing/01.Trading Strategy/llms.txt
estimates, not statistical-model outputs. All crypto trading-bot code is a research prototype requiring testnet validation and legal review before live use. - Korea residents face foreign-stock capital-gains
gameworkerkimllms.txtgameworkerkim/vibe-investing/llms.txt
selling, inverse/leveraged products can converge to total loss. Crypto bot code is research prototype only — testnet validation and legal review required before live deployment. Investment and legal-risk responsibility rests
gameworkerkimllms.txtgameworkerkim/vibe-investing/TechDoc/llms.txt
context management. - [Quivr Guide](LLM/Quivr_guide.md) | Open-source second brain / knowledge management with LLMs. - [Open Code Review Guide](LLM/Open%20code%20review%20guide.md) | AI coding CLI tool review: DeepSeek V4 Pro integration
SirAllapllms.txtSirAllap/agentglass/landing/llms.txt
machine holds the terminals (real tmux panes), the agents — Claude Code, Codex, Gemini CLI, OpenCode — their pull requests and reviews, the diffs they write, git and Docker, a browser they
zenodollms.txtzenodo/zenodo-rdm/static/llms.txt
change, so take the current values from the response headers rather than hard-coding them. - Clients identified as crawlers get a much stricter limit, which is shared by every client
baseReads credentialsllms.txtbase/docs/docs/llms-full.txt
# Base Documentation — Full Context > Full context for AI agents building on Base, the blockchain
raysonmengPipes a download into a shellllms.txtraysonmeng/agent-bridge/site/llms.txt
largely built by Claude Code and Codex collaborating through it — the very tool they were building together. Every PR written by one agent was reviewed by the other, with
A markdown file at a website's root that gives language models a short guide to the site and links to the pages worth reading.
The same idea with the content included, so an agent can read the documentation in one request.
Agents and tools that fetch documentation on someone's behalf. It's a proposal, not a standard, and support varies.
Start with a one-line summary, then sections of links with a sentence each. The examples here show what real projects do.
