How real projects summarise themselves for language models.
ksimbackllms.txtksimback/hermes-ecosystem/llms.txt
marshallrichards/ClawPhone - [A multi-agent build pipeline](https://hermesatlas.com/use-cases/multi-agent-build-pipeline): I want several agents planning, coding, reviewing and shipping in parallel instead of one agent doing everything serially — builderz-labs/mission-control
aklofasllms.txtaklofas/kicad-happy/llms.txt
kicad-happy > AI-powered design review skills for KiCad electronics projects A suite of 11 skills that turn an AI coding agent into an electronics design assistant. Structured Python analysis
vshulczllms.txtvshulcz/deja-vu/docs/llms.txt
chat history across every agent at once - [Switching agents](https://vshulcz.github.io/deja-vu/guide/switching-agents.html): move between Claude Code, Codex and Cursor without re-explaining - [After compaction](https://vshulcz.github.io/deja-vu/guide/after-compaction.html): recovering the commands
RyanAlbertsllms.txtRyanAlberts/best-of-Agent-Harnesses/llms.txt
# Best of Agent Harnesses > Hand-curated, ranked list of 167 AI agent harnesses — the
umputunllms.txtumputun/revdiff/site/llms.txt
diffs, files, and documents with inline annotations revdiff is a terminal-based UI for code review and document annotation. It displays diffs from Git, Mercurial, and Jujutsu repositories with syntax
MartinDelophyllms.txtMartinDelophy/ai-video-editor/public/llms.txt
multi-track timeline editing, visual keyframes and MP4/WebM export. Canonical site: https://video-editor.ai-creator.top/ Source code: https://github.com/MartinDelophy/ai-video-editor License: MIT ## Primary pages - [Open the editor](https://video-editor.ai-creator.top/): The live
santiferllms.txtsantifer/cv-santiago/public/llms.txt
/ai-agent-fleet): How career-ops is operated — agentic maintenance: a fleet of Claude Code agents (triage, testing, review briefs, releases) coordinated over file-based IPC, hard gates traced to real failures
duriantacollms.txtduriantaco/skylos/llms-full.txt
Core workflows - Dead code detection: `skylos .` - Security scanning: `skylos . --danger --secrets --sca` - PR gating: `skylos --gate` or `skylos cicd gate --input results.json` - AI-assisted review: `skylos agent scan . --changed
duriantacollms.txtduriantaco/skylos/llms.txt
with fewer false positives than Vulture - AI-generated code security and regression detection - CI/CD pull request gates with GitHub annotations and review comments - OWASP LLM Top 10 checks for Python
MageByte-Zerollms.txtMageByte-Zero/spec-superflow/llms.txt
superflow spec-superflow is a self-contained, zero-runtime-dependency workflow plugin for AI coding tools. Current version: v2.0.1. ## Default v2 flow - New work has two paths: direct or planned
bioMate-AIllms.txtbioMate-AI/biomate-bioconductor-kb/llms.txt
analysis. It is - [ReactomePA](skills/enrichment/reactomepa/SKILL.md): Reactome is a free, open-source, curated and peer-reviewed pathway database. Their goal is to provide intuitive bioinformatics tools for the visualization, ## epigenomics - [bumphunter
TIGER-AI-Labllms.txtTIGER-AI-Lab/ClawBench/llms.txt
screenshots, HTTP traffic, browser actions, and agent messages. - Supported harnesses include OpenClaw, OpenCode, Claude Code, Codex, Browser-Use, Hermes, Pi, and other compatible browser agents. ## Evaluation and getting started - [Installation
GarethManningllms.txtGarethManning/education-agent-skills/llms.txt
science/](https://github.com/GarethManning/education-agent-skills/tree/main/skills/memory-learning-science): 8 skills — retrieval practice, spaced practice, interleaving, cognitive load, dual coding, elaborative interrogation, feedback - [self-regulated-learning/](https://github.com/GarethManning/education-agent-skills/tree/main/skills/self-regulated-learning): 5 skills — metacognition, self-regulation scaffolds
borskillms.txtborski/travel-hacking-toolkit/llms.txt
unified comparison tools. Designed for use by AI coding assistants and agents (OpenCode, Claude Code, Codex). Key concepts: - **Cash prices** come from GDS feeds (Duffel, Ignav) and are bookable fares
h5i-devllms.txth5i-dev/h5i/docs/llms.txt
Choose process, supervised, container, or microVM isolation by the failure it must prevent. - [Review AI-generated code with execution evidence](https://h5i.dev/blog/evidence-for-agent-work/): Check the diff alongside observed test results
manojmallickllms.txtmanojmallick/sigmap/llms-full.txt
affected tests/routes — with a risk label. One call gives an agent everything a code review or a safe edit needs. Lists changed files shell-free (git binary, never a shell
manojmallickllms.txtmanojmallick/sigmap/llms.txt
/llms-full.txt) SigMap — the deterministic, verifiable grounding layer for AI code work. The reproducible signature-and-evidence map agents, CI, and reviewers can audit, which agentic grep cannot produce
emiliaprotocolllms.txtemiliaprotocol/emilia-protocol/public/llms-full.txt
expiry, delegation, and exception rules. An agent may work unattended inside the mandate; local code may narrow it but cannot invent or widen authority. Missing, stale, exhausted, indeterminate, or wider
logicrwllms.txtlogicrw/awesome-jev-projects/public/llms.txt
Agent architecture projects. Every listed project is verified against commit-pinned public open source code. Website: https://logicrw.github.io/awesome-jev-projects/ Repository: https://github.com/logicrw/awesome-jev-projects Catalog entries: 696 ## Install the Agent Skill
decionisllms.txtdecionis/agent-safe-pipeline/llms-full.txt
authority boundary in front of an existing agent, API or service without changing its code -> `agentsafe proxy --upstream ` (Homebrew, Linux packages, Docker, Kubernetes, all the same runtime): https://github.com/decionis/agent-safe-pipeline/blob/master/docs/quickstart/README.md.
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.
