# Agent Skills vs llms.txt

The map lists them as complementary: sites and agents commonly implement both. They answer different questions: Agent Skills is a step 5 (Act) standard, llms.txt step 4 (Read), so they are not substitutes.

[5 Act](/category/act/) [Agent Skills](/protocols/anthropic-agent-skills-format/) · [4 Read](/category/read/) [llms.txt](/protocols/llms-txt/)

|  | [Agent Skills](/protocols/anthropic-agent-skills-format/) | [llms.txt](/protocols/llms-txt/) |
| --- | --- | --- |
| Lifecycle step | 5 Act: Do something for me | 4 Read: Give me the content |
| Answers | How can reusable, on-demand procedural instructions and bundled resources be packaged so any compatible agent can load and run them? | Where can an agent find a concise, curated map of a site's content, written for language models rather than browsers? |
| Governed by | Originated by Anthropic and donated on 22 October 2026 to the Linux Foundation's Agentic AI Foundation (AAIF); developed in the open at github.com/agentskills/agentskills alongside MCP and A2A | Jeremy Howard / Answer.AI; maintained as an open proposal in the AnswerDotAI/llms-txt GitHub repository with a public Discord for implementation discussion |
| Status (issuer's words) | Active open format under the Linux Foundation Agentic AI Foundation (AAIF), adopted across 35+ agent products | "This is v2 of the proposal" — explicitly a community proposal open for input, not a standards-track document |
| Version | unversioned living spec (agentskills.io/specification) | v2 (2026-08) |
| Form / transport | document format | well-known file |
| Found at | /.well-known/agent-skills/index.json | /llms.txt (or /<path>/llms.txt, e.g. /docs/llms.txt) |
| Implementation | multi-implementation | multi-implementation — Rankability (Tranco top-1000, June 2026: 8.7%) and SE Ranking (~300,000 domains analyzed: 10.13%) — independent third-party publisher-side counts, not our own probe |
| Evidence | 3 verified | 4 verified, 4 reported |
| Primary use case | Describe an agent's capabilities | Serve readable content to agents |
| Last verified | 2026-10-23 (current) | 2026-10-23 (current) |
| Specification | [https://agentskills.io/specification](https://agentskills.io/specification) | [https://llmstxt.org](https://llmstxt.org) |

## When to use which

- Choose Agent Skills when your question is “How can reusable, on-demand procedural instructions and bundled resources be packaged so any compatible agent can load and run them?” and you accept its maturity: status "Active open format under the Linux Foundation Agentic AI Foundation (AAIF), adopted across 35+ agent products", implementation multi-implementation.
- Choose llms.txt when your question is “Where can an agent find a concise, curated map of a site's content, written for language models rather than browsers?” and you accept its maturity: status ""This is v2 of the proposal" — explicitly a community proposal open for input, not a standards-track document", implementation multi-implementation (Rankability (Tranco top-1000, June 2026: 8.7%) and SE Ranking (~300,000 domains analyzed: 10.13%) — independent third-party publisher-side counts, not our own probe).

Guidance is derived from the two records (question, status, implementation, prerequisites, pairings), not from opinion. Each record's page carries its numbered references.

## Read the full articles

- [Agent Skills](/protocols/anthropic-agent-skills-format/): How can reusable, on-demand procedural instructions and bundled resources be packaged so any compatible agent can load and run them?
- [llms.txt](/protocols/llms-txt/): Where can an agent find a concise, curated map of a site's content, written for language models rather than browsers?

Ask the MCP server to compare any two: the compare-protocols prompt, or get on both ids. [Connect](/connect/).

[anthropic-agent-skills-format.json](/data/protocols/anthropic-agent-skills-format.json) · [llms-txt.json](/data/protocols/llms-txt.json) · [Markdown](/compare/anthropic-agent-skills-format-vs-llms-txt/index.md)