How real projects summarise themselves for language models.
agentskillexchangellms.txtagentskillexchange/skills/llms.txt
other tools as DeepSeek Harness sessions. url: https://agentskillexchange.com/skills/move-agent-chat-histories-into-deepseek-harness-with-dsh-chat-import/ ## Build deterministic SaaS API test worlds for agents with Backlot slug: build-deterministic-saas-api-test-worlds-for-agents-with
anzy-renlab-aillms.txtanzy-renlab-ai/pronounce/docs/llms-full.txt
playwright.dev/ Cypress | /ˈsaɪprəs/ | sigh press | tool | community-consensus | https://www.cypress.io/ Vitest | /ˈviːtɛst/ | vee test | tool | community-consensus | https://vitest.dev/ Jest | /dʒɛst/ | jest | tool | community-consensus | https://jestjs.io/ Heroku
bsmi021llms.txtbsmi021/mcp-file-context-server/docs/llms-full.txt
Emacs. | | [fast-agent][fast-agent] | ✅ | ✅ | ✅ | ✅ | ✅ | ✅ | Full multimodal MCP support, with end-to-end tests | | [FLUJO][FLUJO] | ❌ | ❌ | ✅ | ❓ | ❌ | ❌ | Support for resources, Prompts and Roots are coming soon | | [Genkit][Genkit] | ⚠️ | ✅ | ✅ | ❓ | ❌ | ❌ | Supports resource list
manufoselallms.txtmanufosela/karajan-code/llms.txt
Plans** — emits a versioned `plan- .json` with HUs, dependencies and per-HU acceptance tests. 3. **Runs** — for each HU: coder writes code → reviewer evaluates → tester checks tests → SonarQube gates quality
Microsoftllms.txtmicrosoft-foundry/forgebook/site/public/llms.txt
mini on Microsoft Foundry, create an AI agent with Web Search, and test it from the Foundry portal. Tags: agents, agent-service, prompt-agents, tools, web-search. - [Generate Images with
Servosityllms.txtServosity/msp-skills/docs/llms-full.txt
reported as a gap, not zero agents; the partner's live re-test remains necessary. Governance: The skill drives the acronis-cli and acronis-mcp binaries, authenticating with an Acronis
Servosityllms.txtServosity/msp-skills/docs/llms.txt
raw.githubusercontent.com/servosity/msp-skills/main/skills/kaseya-bms/install.sh) - KnowBe4 (Security) - ask "Who clicked the bait in more than one phishing test?" - Hunt repeat clickers, track risk drift, and close training-coverage gaps across every KnowBe4 client
booklib-aillms.txtbooklib-ai/booklib/llms-full.txt
Covers Safety (Items 1-10: mutability, scope, nulls, types, expectations, errors, resources, tests), Readability (Items 11-18: operators, receivers, properties, naming), Reusability (Items 19-25: DRY, generics, delegation, variance), Abstraction
lineai-intelligencellms.txtlineai-intelligence/lineai-mcp-server/context/llms-full.txt
servers defined in VS Code `mcp.json` Apidog, an all-in-one API development and testing platform, features a built-in MCP Client designed for debugging and testing MCP Servers
luuucllms.txtluuuc/sense/docs/llms-full.txt
sprawl. | Tool | Capability | |---|---| | `sense_graph` | Symbol relationships, callers, callees, inheritance, tests, dead code | | `sense_search` | Hybrid bi-encoder + cross-encoder semantic code search with keyword and text fallback | | `sense_blast
luuucllms.txtluuuc/sense/docs/llms.txt
same correctness. The four MCP tools: `sense_graph` (symbol relationships, callers, callees, inheritance, tests, dead code), `sense_search` (hybrid bi-encoder + cross-encoder semantic code search with keyword and text
retracesoftwarellms.txtretracesoftware/retracesoftware/llms.txt
hard to understand from logs, metrics, traces, or a traceback alone, including: - flaky tests and intermittent pytest failures - failed CI runs where runtime state is missing - non-reproducible bugs
The-Best-Codesllms.txtThe-Best-Codes/agent-one/.agents/docs/modelcontextprotocol.io/llms-full.txt
# Build an MCP client Source: https://modelcontextprotocol.io/docs/2026-07-28/develop/build-client Get started building your own client
The-Best-Codesllms.txtThe-Best-Codes/agent-one/.agents/docs/modelcontextprotocol.io/llms.txt
best practices for MCP implementations - [MCP Inspector](https://modelcontextprotocol.io/docs/2026-07-28/tools/inspector.md): Interactive developer tooling for testing and debugging MCP servers, in the browser, on the command line, and in the terminal
The-Best-Codesllms.txtThe-Best-Codes/agent-one/.agents/docs/tauri.app/llms-full.txt
This is the full developer documentation for Tauri # Tauri 2.0 > The cross-platform app
bluebear-iollms.txtbluebear-io/baloo-bear/docs/llms.txt
Container setup, private key options, and production notes. - [Development](https://blue-bear-security.github.io/baloo-bear/development/): Contributor commands, test workflow, and local development. ## Optional Features - [False-Positive Verification](https://blue-bear-security.github.io/baloo-bear/features/fp-verification/): Optional second-pass
luocfprimellms.txtluocfprime/labtasker/docs/llms.txt
raw.githubusercontent.com/luocfprime/labtasker/refs/heads/main/docs/getting-started.md): Install Labtasker, submit several experiment cases, and process them through one Queue. - [Tested demo](https://raw.githubusercontent.com/luocfprime/labtasker/refs/heads/main/docs/demo.md): Run the canonical submission and Python Worker example whose source files
NickCrewllms.txtNickCrew/Claude-Cortex/site/llms-full.txt
server definitions for Claude Code, and enforces quality gates — independent code review, test-coverage audits, lint checks — so that no agent grades its own homework. Cortex is published as `claude
NickCrewllms.txtNickCrew/Claude-Cortex/site/llms.txt
skills, rules, and hooks for Claude Code, and enforces quality gates — independent code review, test-coverage audits, lint checks — so that no agent grades its own homework. ## Core principle
qormllms.txtqorm/platform/llms.txt
agent. Docs marked "auto-generated" are regenerated from the code and guarded by tests — trust them over prose. Write apps in the format the runtime accepts **today**: follow getting-started
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.
