How real projects summarise themselves for language models.
JayantChoprallms.txtJayantChopra/stanley-mcp-playground/site/llms.txt
public](https://stanley-cookbook.vercel.app/recipes/03-build-in-public.html): Your merged PRs, retold as posts worth reading. - [04 · Analytics review](https://stanley-cookbook.vercel.app/recipes/04-analytics-review.html): Ask your own numbers questions in plain English. - [05 · Trend scouting
katalon-labsllms.txtkatalon-labs/true-skills/llms.txt
design, test management and requirement traceability, test review, test execution, failure analysis and release readiness, and test maintenance - operated from any AI coding agent's chat through the Katalon
ken-jollms.txtken-jo/agent-connector/llms-full.txt
agent-host end user (has NOT authored a connector) You already run Claude Code / Codex / Cursor / … and you just want to know **how many tokens your agent hosts are burning
KKWANG4444llms.txtKKWANG4444/ai-api-proxy-china-guide/llms-full.txt
current AI model catalog without mixing client setup with unsupported performance claims. Last reviewed: 2026-09-01. ## What this repository solves Use this repository when a client asks
KKWANG4444llms.txtKKWANG4444/ai-api-proxy-china-guide/llms.txt
maintained by the operator of AIFast. Model configuration and maintenance status can change. Last reviewed: 2026-09-01. ## AIFast service capabilities - [Full LLM context](https://github.com/KKWANG4444/ai-api-proxy-china-guide/blob/main/llms-full.txt): client setup, tool
KyaniteLabsllms.txtKyaniteLabs/tastecheck/llms.txt
ship or hold decision. TasteCheck skills are plain Markdown, readable by any coding agent — no SDK or install required. The ship-gate adds optional dependency-free Node and browser scripts
littlebearappsllms.txtlittlebearapps/pitchdocs/llms-full.txt
friendly README.md. Supports --review (force review) and --no-review (skip review) flags - [/pitchdocs:features](./commands/features.md): Extract features from code and translate to benefits - [/pitchdocs:changelog](./commands/changelog.md): Generate CHANGELOG.md from
littlebearappsllms.txtlittlebearapps/pitchdocs/llms.txt
friendly README.md — supports --review (force review) and --no-review (skip review) flags - [/pitchdocs:features](./commands/features.md): Extract features from code and translate to user benefits — auto-scan or conversational path - [/pitchdocs
MSKazemillms.txtMSKazemi/aobench/docs/llms-full.txt
# AOBench > AOBench (Agent Operations Benchmark) is an open-source Python benchmark framework for evaluating
nometalalchemistllms.txtnometalalchemist/KitchenSink4Word/docs/llms.txt
next `tools/list`, announced by `tools/list_changed`. - Pack costs, from `scripts/measure_surface.py`: references 8 tools / 2.9k, review 9 / 2.4k, academic 24 / 7.6k, assembly 7 / 2.1k, media-forms
osauerllms.txtosauer/canary/docs/llms-full.txt
sources. A delayed, held, fallback, partial, or unavailable result must retain its data quality, warning code, freshness, source health, and session context; returning a value does not make a fallback green
osauerllms.txtosauer/canary/docs/llms.txt
option-strategy grouping, read-only protection proposals, and option-exercise opportunity review; - explicit freshness, entitlement, source-health, warning-code, and session context; and - Go programs reading the daemon through `github.com
Speraxllms.txtSperax/sperax-skills/llms-full.txt
block explorer 2. Look up audit history 3. Check token distribution (top holders) 4. Review social signals and news 5. Check for known scam patterns (honeypot, high tax) ## Transaction Patterns
veggiemonkllms.txtveggiemonk/backlog/docs/llms.txt
backlog create "Design the new dashboard" -a "alex" # Assign to multiple people: backlog create "Code review for the payment gateway" -a "jordan" -a "casey" # 4. Adding Labels
Amey-Thakurllms.txtAmey-Thakur/AI-SKILLS/docs/llms.txt
accessibility of UI that automated tools cannot fully assess. ## Skills: ai-coding-tools - [agent-code-review](https://raw.githubusercontent.com/Amey-Thakur/AI-SKILLS/main/skills/ai-coding-tools/agent-code-review/SKILL.md): Use an agent to review a diff productively, with the right
aunysillymellms.txtaunysillyme/model-orchestrator/llms.txt
Templates](https://github.com/aunysillyme/model-orchestrator/blob/main/templates/README.md): routing rules, task brief, context, acceptance checks and protocols - [Claude Code plugin](https://github.com/aunysillyme/model-orchestrator/blob/main/plugin/README.md): installing read-only routing hooks and subagents through the plugin marketplace
bablsoftllms.txtbablsoft/accessflow/website/llms.txt
record who approved it - [Automate with Terraform](https://accessflow.io/docs/guides/terraform/): Declare datasources, review plans and policies as code with the Terraform / OpenTofu provider - [Ask the help assistant](https://accessflow.io/docs/guides/help-assistant/):
backant-iollms.txtbackant-io/jevelry/llms.txt
answer, every question comes back `fall_back` with the reason in `d.error`, so the code keeps its old path. `npx jevelry types --out src/jevels.d.ts` writes the types, so `d.team.answer
chenyuxiaojinllms.txtchenyuxiaojin/video-agent-skills/llms.txt
into a DaVinci/CapCut-ready timeline — from research to publish. A collection of 11 specialized Claude Code skills that form a coordinated video production pipeline. Ten skills cover the full production chain
joris887llms.txtjoris887/exosuit/llms.txt
server vs built-in tool selection guide with decision matrix ## Native Agents (.claude/agents/) - .claude/agents/code-reviewer.md: Code review with severity classification (correctness, conventions, security lenses) — temperature: 0.1 - .claude/agents/spec-reviewer.md: Spec compliance verification 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.
