
create-llms
Create an llms.txt file from scratch based on repository structure following the llms.txt specification at https://llmstxt.org/
- Installs
- 536
- Last 24h
- —
- Trending rank
- —
- Security
- Not audited
Install
Works with every agent the skills CLI supports.
npx skills add https://github.com/ilteoood/harness --skill create-llms- 01
Install
Run the command in your project. The CLI asks which agents to install for.
- 02
Describe the task
Ask your agent for something this skill covers. It loads create-llms automatically when relevant.
- 03
Review the result
The agent follows the SKILL.md steps, scripts and references bundled with the skill.
SKILL.md
The instructions your agent reads when the skill is triggered.
Create LLMs.txt File from Repository Structure
Create a new llms.txt file from scratch in the root of the repository following the official llms.txt specification at https://llmstxt.org/. This file provides high-level guidance to large language models (LLMs) on where to find relevant content for understanding the repository's purpose and specifications.
Primary Directive
Create a comprehensive llms.txt file that serves as an entry point for LLMs to understand and navigate the repository effectively. The file must comply with the llms.txt specification and be optimized for LLM consumption while remaining human-readable.
Analysis and Planning Phase
Before creating the llms.txt file, you must complete a thorough analysis:
Step 1: Review llms.txt Specification
- Review the official specification at https://llmstxt.org/ to ensure full compliance
- Understand the required format structure and guidelines
- Note the specific markdown structure requirements
Step 2: Repository Structure Analysis
- Examine the complete repository structure using appropriate tools
- Identify the primary purpose and scope of the repository
- Catalog all important directories and their purposes
- List key files that would be valuable for LLM understanding
Step 3: Content Discovery
- Identify README files and their locations
- Find documentation files (
.mdfiles in/docs/,/spec/, etc.) - Locate specification files and their purposes
- Discover configuration files and their relevance
- Find example files and code samples
- Identify any existing documentation structure
Step 4: Create Implementation Plan
Based on your analysis, create a structured plan that includes:
- Repository purpose and scope summary
- Priority-ordered list of essential files for LLM understanding
- Secondary files that provide additional context
- Organizational structure for the llms.txt file
Implementation Requirements
Format Compliance
The llms.txt file must follow this exact structure per the specification:
- H1 Header: Single line with repository/project name (required)
- Blockquote Summary: Brief description in blockquote format (optional but recommended)
- Additional Details: Zero or more markdown sections without headings for context
- File List Sections: Zero or more H2 sections containing markdown lists of links
Content Requirements
Required Elements
- Project Name: Clear, descriptive title as H1
- Summary: Concise blockquote explaining the repository's purpose
- Key Files: Essential files organized by category (H2 sections)
File Link Format
Each file link must follow: [descriptive-name](relative-url): optional description
Section Organization
Organize files into logical H2 sections such as:
- Documentation: Core documentation files
- Specifications: Technical specifications and requirements
- Examples: Sample code and usage examples
- Configuration: Setup and configuration files
- Optional: Secondary files (special meaning - can be skipped for shorter context)
Content Guidelines
Language and Style
- Use concise, clear, unambiguous language
- Avoid jargon without explanation
- Write for both human and LLM readers
- Be specific and informative in descriptions
File Selection Criteria
Include files that:
- Explain the repository's purpose and scope
- Provide essential technical documentation
- Show usage examples and patterns
- Define interfaces and specifications
- Contain configuration and setup instructions
Exclude files that:
- Are purely implementation details
- Contain redundant information
- Are build artifacts or generated content
- Are not relevant to understanding the project
Execution Steps
Step 1: Repository Analysis
- Examine the repository structure completely
- Read the main README.md to understand the project
- Identify all documentation directories and files
- Catalog specification files and their purposes
- Find example files and configuration files
Step 2: Content Planning
- Determine the primary purpose statement
- Write a concise summary for the blockquote
- Group identified files into logical categories
- Prioritize files by importance for LLM understanding
- Create descriptions for each file link
Step 3: File Creation
- Create the
llms.txtfile in the repository root - Follow the exact format specification
- Include all required sections
- Use proper markdown formatting
- Ensure all links are valid relative paths
Step 4: Validation
- Verify compliance with https://llmstxt.org/ specification
- Check that all links are valid and accessible
- Ensure the file serves as an effective LLM navigation tool
- Confirm the file is both human and machine readable
Quality Assurance
Format Validation
- ✅ H1 header with project name
- ✅ Blockquote summary (if included)
- ✅ H2 sections for file lists
- ✅ Proper markdown link format
- ✅ No broken or invalid links
- ✅ Consistent formatting throughout
Content Validation
- ✅ Clear, unambiguous language
- ✅ Comprehensive coverage of essential files
- ✅ Logical organization of content
- ✅ Appropriate file descriptions
- ✅ Serves as effective LLM navigation tool
Specification Compliance
- ✅ Follows https://llmstxt.org/ format exactly
- ✅ Uses required markdown structure
- ✅ Implements optional sections appropriately
- ✅ File located at repository root (
/llms.txt)
Example Structure Template
# [Repository Name]
> [Concise description of the repository's purpose and scope]
[Optional additional context paragraphs without headings]
## Documentation
- [Main README](README.md): Primary project documentation and getting started guide
- [Contributing Guide](CONTRIBUTING.md): Guidelines for contributing to the project
- [Code of Conduct](CODE_OF_CONDUCT.md): Community guidelines and expectations
## Specifications
- [Technical Specification](spec/technical-spec.md): Detailed technical requirements and constraints
- [API Specification](spec/api-spec.md): Interface definitions and data contracts
## Examples
- [Basic Example](examples/basic-usage.md): Simple usage demonstration
- [Advanced Example](examples/advanced-usage.md): Complex implementation patterns
## Configuration
- [Setup Guide](docs/setup.md): Installation and configuration instructions
- [Deployment Guide](docs/deployment.md): Production deployment guidelines
## Optional
- [Architecture Documentation](docs/architecture.md): Detailed system architecture
- [Design Decisions](docs/decisions.md): Historical design decision records
Success Criteria
The created llms.txt file should:
- Enable LLMs to quickly understand the repository's purpose
- Provide clear navigation to essential documentation
- Follow the official llms.txt specification exactly
- Be comprehensive yet concise
- Serve both human and machine readers effectively
- Include all critical files for project understanding
- Use clear, unambiguous language throughout
- Organize content logically for easy consumption
FAQ
What does the create-llms skill do?
Create an llms.txt file from scratch based on repository structure following the llms.txt specification at https://llmstxt.org/
How do I install create-llms?
Run npx skills add https://github.com/ilteoood/harness --skill create-llms in your project. The skills CLI detects the agents you use and copies the skill into the right folder. For Claude Code you can also place the skill folder at ~/.claude/skills/create-llms/ (personal) or .claude/skills/create-llms/ (project).
Which AI agents can use create-llms?
Any agent that supports the open Agent Skills format (a folder with a SKILL.md file), including Claude Code, Codex, Cursor, GitHub Copilot, Gemini CLI, Windsurf, Cline, OpenCode and more.
Is create-llms safe to install?
No partner security audit is available yet. Skills can run commands and scripts, so read the SKILL.md and any bundled files before installing.
Who maintains create-llms?
It is published by ilteoood in ilteoood/harness. It has 536 recorded installs.
More from ilteoood/harness
github-issues
ilteoood/harness
Create, update, and manage GitHub issues using MCP tools. Use this skill when users want to create bug reports, feature requests, or task issues, update existing issues, add labels/assignees/milestones, manage repository labels, set issue fields (dates, priority, custom fields), set issue types, manage issue workflows, link issues, add dependencies, or track blocked-by/blocking relationships. Triggers on requests like "create an issue", "file a bug", "request a feature", "update issue X", "set the priority", "set the start date", "create a label", "rename a label", "list repo labels", "link issues", "add dependency", "blocked by", "blocking", or any GitHub issue management task.
git-commit
ilteoood/harness
Execute git commit with conventional commit message analysis, intelligent staging, and message generation. Use when user asks to commit changes, create a git commit, or mentions "/commit". Supports: (1) Auto-detecting type and scope from changes, (2) Generating conventional commit messages from diff, (3) Interactive commit with optional type/scope/description overrides, (4) Intelligent file staging for logical grouping
conventional-commit
ilteoood/harness
Prompt and workflow for generating conventional commit messages using a structured XML format. Guides users to create standardized, descriptive commit messages in line with the Conventional Commits specification, including instructions, examples, and validation.
create-technical-spike
ilteoood/harness
Create time-boxed technical spike documents for researching and resolving critical development decisions before implementation.
codeql
ilteoood/harness
Comprehensive guide for setting up and configuring CodeQL code scanning via GitHub Actions workflows and the CodeQL CLI. This skill should be used when users need help with code scanning configuration, CodeQL workflow files, CodeQL CLI commands, SARIF output, security analysis setup, or troubleshooting CodeQL analysis.
create-specification
ilteoood/harness
Create a new specification file for the solution, optimized for Generative AI consumption.
Popular ai & agents skills
google-agents-cli-publish
google/agents-cli
This skill should be used when the user wants to "publish an agent", "publish my ADK agent", "register an agent with Gemini", "publish to Gemini" (formerly Gemini Enterprise), or needs guidance on the agents-cli publish gemini command. Also use when the user wants to "manage agents in Agent Registry", "list/update/delete registered agents", or "register an MCP server". Covers ADK vs A2A registration modes, programmatic and interactive usage, flag reference, auto-detection from deployment metadata, Agent Registry fleet management, and troubleshooting. Part of the agents-cli skills suite. Do NOT use for deployment (use google-agents-cli-deploy).
google-agents-cli-eval
google/agents-cli
This skill should be used when the user wants to "run an evaluation", "evaluate my agent", "evaluate my ADK agent", "write an eval dataset", "analyze eval failures", "compare eval results", "optimize agent", or needs guidance on the Gemini platform eval methodology and the Quality Flywheel. Covers eval metrics, dataset schema, LLM-as-judge scoring, and common failure causes. Applies to any agents-cli project, whatever framework the agent is written in. Do NOT use for agent API code patterns (ADK: use google-agents-cli-adk-code), deployment (use google-agents-cli-deploy), or project scaffolding (use google-agents-cli-scaffold).
skill-creator
anthropics/skills
Create new skills, modify and improve existing skills, and measure skill performance. Use when users want to create a skill from scratch, edit, or optimize an existing skill, run evals to test a skill, benchmark skill performance with variance analysis, or optimize a skill's description for better triggering accuracy.
codex-pet
prime-skills/runcomfy-agent-skills
Codex Pet generator on RunComfy. Build a Codex-compatible Codex Pet spritesheet.webp + pet.json from a single reference image, drop it into ${CODEXHOME:-$HOME/.codex}/pets/ / and Codex picks it up as a custom Codex Pet next to the 8 built-ins. This skill produces the exact Codex Pet atlas Codex expects (1536x1872 PNG/WebP, 8 cols x 9 rows, 192x208 cells, 9 animation states — idle, running-right, running-left, waving, jumping, failed, waiting, running, review). Calls OpenAI GPT Image 2 edit ONCE via the local RunComfy CLI as runcomfy run openai/gpt-image-2/edit to produce a canonical Codex Pet pose, then assembles all 9 animation rows programmatically with ImageMagick micro-transforms — no Codex Pro, no $imagegen, no OPENAIAPIKEY required, only RUNCOMFYTOKEN. Triggers on "codex pet", "create codex pet", "make codex pet", "hatch codex pet", "/hatch image", "desktop pet codex", "codex pets", "spritesheet.webp", or any explicit ask to build a custom pet for OpenAI Codex.
full-output-enforcement
leonxlnx/taste-skill
Overrides default LLM truncation behavior. Enforces complete code generation, bans placeholder patterns, and handles token-limit splits cleanly. Apply to any task requiring exhaustive, unabridged output.
executing-plans
obra/superpowers
Use when executing an implementation plan in the current session as the implementer yourself — your human partner chose inline execution, or no subagent tool is available