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.
wesmllms.txtwesm/middleman/docs/llms.txt
review, stacks, and merging - [Browse repositories](https://forge.kenn.io/docs/workflows/repositories.md): Repository source browser, refs, previews, and file history - [Work in local sessions](https://forge.kenn.io/docs/workflows/workspaces.md): Worktree workspaces, tmux sessions, and coding
tmseidelllms.txttmseidel/ai-git-bot/llms-full.txt
shared setup (workflow configurations, triggers, running workflows). - `doc/PR_WORKFLOWS_REVIEW.md`: the default always-on AI code review workflow. - `doc/PR_WORKFLOWS_AGENTIC_REVIEW.md`: deeper agentic PR review workflow. - `doc/PR_WORKFLOWS_UNIT_TEST.md`: AI unit-test workflow, supported toolchains, slash
tmseidelllms.txttmseidel/ai-git-bot/llms.txt
/tmseidel/ai-git-bot Docker image: https://hub.docker.com/r/tmseidel/ai-git-bot License: MIT ## Core capabilities - AI-powered pull-request code reviews triggered by reviewer assignment or re-request. - Interactive PR and inline review conversations with
paolobietolinillms.txtpaolobietolini/gtm-mcp-server/llms.txt
template details including .tpl code | | `create_template` | Create a custom template from .tpl code | | `update_template` | Modify an existing template | | `delete_template` | Remove a template (requires `confirm: true`) | | `import_gallery
willynikes2Reads credentialsllms.txtwillynikes2/knowledge-base-server/llms.txt
src/safety/review.js | Destructive action review with multi-model consensus. | | src/promotion/promoter.js | Knowledge promotion from sources to structured notes. | | src/synthesis/weekly-review.js | Weekly cross-source synthesis generator. | ## Integration Patterns ### Claude Code (local, stdio) Register with
arronKlerPipes a download into a shellllms.txtarronKler/pairfob/site/llms.txt
Sessions run in Herdr, which the installer sets up automatically. Pair once by QR code; no phone app required, no Pairfob account, no VPN, no inbound ports. An optional sideloaded
wiz-sec-publicllms.txtwiz-sec-public/SITF/app/llms-full.txt
controls: - Acceptable use policy against unapproved AI tools - Approved AI tools with data protection - Code review for AI-generated code Detective controls: - Network monitoring for AI service connections Observed
ihuzaifashoukatllms.txtihuzaifashoukat/x-use/llms.txt
bounded thread reads; structured notifications; visible inbox and conversation reads; local leads and campaigns; reviewed messages, follows, and multi-post threads. - Inbox folders are inbox, requests and other. All/unread/read filters
kestra-iollms.txtkestra-io/docs/public/llms.txt
environments directly from the Kestra UI with a diff review and confirmation gate — no Git or pipeline required - [VS Code extension](https://kestra.io/docs/version-control-cicd/vscode.md): Edit flows in VS Code with
softsparkReads credentialsllms.txtsoftspark/ai-toolkit/llms-full.txt
diffs for regression risk and blast radius, generates risk-scored impact report. Triggers: PR review, code change risk, breaking change, blast radius, regression check. - **prepare-test-env**: Prepare or verify
softsparkllms.txtsoftspark/ai-toolkit/llms.txt
kb/howto/autonomous-development.md) - [Claude Code Account Profiles by Project](kb/howto/claude-account-profiles.md) - [Codex account profiles](kb/howto/codex-account-profiles.md) - [Plan: Cloud Security Pack — Multi-Cloud Audit](kb/planning/cloud-security-pack-plan.md) - [Ecosystem sync, 2026-09-23](kb/planning/ecosystem-sync-20260923.md) - [Ecosystem review
magnus919Reads credentialsllms.txtmagnus919/agent-skills/llms.txt
substitute for project documentation, production-readiness testing, legal review, or general architecture methodology. - [code-review](code-review/SKILL.md): Review a code change for correctness, security, maintainability, and test adequacy
alfadur7llms.txtalfadur7/llm-wiki-newsroom/docs/llms.txt
Claude Code that turns a folder of documents into a cross-linked, human-readable markdown wiki. The agent that writes a page is never the one that reviews
tubecreatellms.txttubecreate/tubecli/docs/llms.txt
with no API key. Representative operations, all executed by agents rather than suggested as code: describe a site in plain language and the website agent runs `git clone` → `npm install
tubecreatellms.txttubecreate/tubecli/llms.txt
tunnel the user opened. Representative operations, all executed by agents rather than suggested as code: say "make a video from what you read today" and the `content_video` extension writes
gravity-uiReads credentialsllms.txtgravity-ui/aikit/llms-full.txt
message with a diagram and verify cached SVG does not flash as source code. - Review screenshot differences before updating baselines: palette and menu changes are expected, overflow or missing content
PsiACEllms.txtPsiACE/skills/skills/llms.txt
Reuse and composition](https://raw.githubusercontent.com/psiace/skills/main/skills/friendly-python/references/reuse-composition.md): Composition-oriented design. - [Review checklist](https://raw.githubusercontent.com/psiace/skills/main/skills/friendly-python/references/review-checklist.md): Code review focus areas. ## Piglet references (Markdown) - [Variables and naming](https://raw.githubusercontent.com/psiace/skills/main/skills/piglet/references/variables-and-naming.md): Naming, scope
PrimeFoldToolsllms.txtPrimeFoldTools/andon/llms.txt
file to parallel sessions. - [Hook install](https://raw.githubusercontent.com/PrimeFoldTools/andon/main/HOOK_INSTALL.md): Registering the hooks in Claude Code settings, warn mode first, and how to turn them off. ## Hook source - [claim_check_hook.py](https://raw.githubusercontent.com
Patdolitsellms.txtPatdolitse/piia-engram/llms.txt
local-first personal AI identity and memory layer shared across MCP-compatible coding tools. Its JSON/Markdown data stays on your machine. Install the package with `pip install piia-engram`, then
xhlucallms.txtxhluca/session-migrate/llms.txt
session-migrate`. Use `"$TMP/venv/bin/session-migrate"` for every operation and verify its version. Do not run code from an untrusted fork. If installation or version verification fails, stop; never reproduce or infer
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.
