Wiki LLMs Txt
MicrosoftOfficialCreated by Microsoft
- Skill
- Content generator
- Documents and content
- MIT
- No issues found
AutoGineer summary
Written by AutoGineer from the skill’s own files, not by the author
This skill automates the creation of LLM-friendly documentation files following the llms.txt specification. It scans existing project wikis or documentation to produce a structured discovery file (llms.txt) and a comprehensive, inlined content file (llms-full.txt). By organizing documentation into prioritized sections and providing clear, dense summaries, it ensures that AI agents can efficiently index and understand project architecture, setup guides, and deep-dive technical details.
What it does
- Generates a standard llms.txt file for project discovery.
- Creates an llms-full.txt file with inlined documentation content.
- Organizes documentation links by priority and relevance.
- Strips YAML frontmatter while preserving diagrams and citations.
- Validates that all linked documentation files exist and are accessible.
- Ensures compliance with the official llms.txt specification.
When to use it
- When you need to make your project documentation accessible to AI agents.
- When you want to provide a concise summary of your project for LLM context.
- When you need to bundle documentation into a single file for easier AI ingestion.
- When you are following the llms.txt standard for your repository.
Advantages
- Improves AI agent performance by providing structured, relevant context.
- Reduces token usage by offering both a summary and a full-content version.
- Maintains consistency across project documentation.
- Ensures documentation is machine-readable without losing technical diagrams.
Usage examples
- “Create an llms.txt file for this project.”
- The agent will scan the repository, resolve the source URL, and generate the required llms.txt and llms-full.txt files in the appropriate directories.
- “Make my wiki LLM-friendly.”
- The agent will organize your existing wiki pages into a structured llms.txt format, ensuring all links are valid and content is properly summarized.
Install
Download the skill as a ZIP:
https://autogineer.com/agent-skills/microsoft/wiki-llms-txt/downloadUnzip it into the cross-client skills folder of your project:
mkdir -p .agents/skills && unzip wiki-llms-txt.zip -d .agents/skills
Documentation by Microsoft
llms.txt Generator
Generate llms.txt and llms-full.txt files that provide LLM-friendly access to wiki documentation, following the llms.txt specification.
When This Skill Activates
User asks to generate
llms.txtor mentions the llms.txt standardUser wants to make documentation "LLM-friendly" or "LLM-readable"
User asks for a project summary file for language models
User mentions
llms-full.txtor context-expanded documentation
Source Repository Resolution (MUST DO FIRST)
Before generating, resolve the source repository context:
Check for git remote: Run
git remote get-url originAsk the user: "Is this a local-only repository, or do you have a source repository URL?"
Remote URL → store as
REPO_URLLocal → use relative paths only
Determine default branch: Run
git rev-parse --abbrev-ref HEADDo NOT proceed until resolved
llms.txt Format (Spec-Compliant)
The file follows the llms.txt specification:
# {Project Name}
> {Dense one-paragraph summary — what it does, who it's for, key technologies}
{Important context paragraphs — constraints, architectural philosophy, non-obvious things}
## {Section Name}
- [{Page Title}]({relative-path-to-md}): {One-sentence description of what the reader will learn}
## Optional
- [{Page Title}]({relative-path-to-md}): {Description — these can be skipped for shorter context}Key Rules
H1 — Project name (exactly one, required)
Blockquote — Dense, specific summary (required). Must be unique to THIS project.
Context paragraphs — Non-obvious constraints, things LLMs would get wrong without being told
H2 sections — Organized by topic, each with a list of
[Title](url): Descriptionentries"Optional" H2 — Special meaning: links here can be skipped for shorter context
Relative links — All paths relative to wiki directory
Dynamic — ALL content derived from actual wiki pages, not templates
Section order — Most important first: Onboarding → Architecture → Getting Started → Deep Dive → Optional
Description Quality
| ❌ Bad | ✅ Good |
|---|---|
| "Architecture overview" | "System architecture showing how Orleans grains communicate via message passing with at-least-once delivery" |
| "Getting started guide" | "Prerequisites, local dev setup with Docker Compose, and first API call walkthrough" |
| "The API reference" | "REST endpoints with auth requirements, rate limits, and request/response schemas" |
llms-full.txt Format
Same structure as llms.txt but with full content inlined:
# {Project Name}
> {Same summary}
{Same context}
## {Section Name}
<doc title="{Page Title}" path="{relative-path}">
{Full markdown content — frontmatter stripped, citations and diagrams preserved}
</doc>Inlining Rules
Strip YAML frontmatter (
---blocks) from each pagePreserve Mermaid diagrams — keep
```mermaidfences intactPreserve citations — all
[file:line](URL)links stay as-isPreserve tables — all markdown tables stay intact
Preserve
<!-- Sources: -->comments — these provide diagram provenance
Prerequisites
This skill works best when wiki pages already exist (via /deep-wiki:generate or /deep-wiki:page). If no wiki exists yet:
Suggest running
/deep-wiki:generatefirstOR generate a minimal
llms.txtfrom README + source code scan (without wiki page links)
Output Files
Generate three files:
| File | Purpose | Discoverability |
|---|---|---|
./llms.txt | Root discovery file | Standard path per llms.txt spec. GitHub MCP get_file_contents and search_code find this first. |
wiki/llms.txt | Wiki-relative links | For VitePress deployment and wiki-internal navigation. |
wiki/llms-full.txt | Full inlined content | Comprehensive reference for agents needing all docs in one file. |
The root ./llms.txt links into wiki/ (e.g., [Guide](./wiki/onboarding/contributor-guide.md)). The wiki/llms.txt uses wiki-relative paths (e.g., [Guide](./onboarding/contributor-guide.md)).
If a root llms.txt already exists and was NOT generated by deep-wiki, do NOT overwrite it.
Validation Checklist
Before finalizing:
[ ] All linked files in
llms.txtactually exist[ ] All
<doc>blocks inllms-full.txthave real content (not empty)[ ] Blockquote is specific to this project (not generic boilerplate)
[ ] Sections ordered by importance
[ ] No duplicate page entries across sections
[ ] "Optional" section only contains truly optional content
[ ]
llms.txtis concise (1-5 KB)[ ]
llms-full.txtcontains all wiki pages
Files
- ATTRIBUTION.mdAdded by AutoGineer936 B
- LICENSELicence file added by AutoGineer1.1 KiB
- SKILL.md5.0 KiB
SKILL.md
llms.txt Generator
Generate llms.txt and llms-full.txt files that provide LLM-friendly access to wiki documentation, following the llms.txt specification.
When This Skill Activates
User asks to generate
llms.txtor mentions the llms.txt standardUser wants to make documentation "LLM-friendly" or "LLM-readable"
User asks for a project summary file for language models
User mentions
llms-full.txtor context-expanded documentation
Source Repository Resolution (MUST DO FIRST)
Before generating, resolve the source repository context:
Check for git remote: Run
git remote get-url originAsk the user: "Is this a local-only repository, or do you have a source repository URL?"
Remote URL → store as
REPO_URLLocal → use relative paths only
Determine default branch: Run
git rev-parse --abbrev-ref HEADDo NOT proceed until resolved
llms.txt Format (Spec-Compliant)
The file follows the llms.txt specification:
# {Project Name}
> {Dense one-paragraph summary — what it does, who it's for, key technologies}
{Important context paragraphs — constraints, architectural philosophy, non-obvious things}
## {Section Name}
- [{Page Title}]({relative-path-to-md}): {One-sentence description of what the reader will learn}
## Optional
- [{Page Title}]({relative-path-to-md}): {Description — these can be skipped for shorter context}Key Rules
H1 — Project name (exactly one, required)
Blockquote — Dense, specific summary (required). Must be unique to THIS project.
Context paragraphs — Non-obvious constraints, things LLMs would get wrong without being told
H2 sections — Organized by topic, each with a list of
[Title](url): Descriptionentries"Optional" H2 — Special meaning: links here can be skipped for shorter context
Relative links — All paths relative to wiki directory
Dynamic — ALL content derived from actual wiki pages, not templates
Section order — Most important first: Onboarding → Architecture → Getting Started → Deep Dive → Optional
Description Quality
| ❌ Bad | ✅ Good |
|---|---|
| "Architecture overview" | "System architecture showing how Orleans grains communicate via message passing with at-least-once delivery" |
| "Getting started guide" | "Prerequisites, local dev setup with Docker Compose, and first API call walkthrough" |
| "The API reference" | "REST endpoints with auth requirements, rate limits, and request/response schemas" |
llms-full.txt Format
Same structure as llms.txt but with full content inlined:
# {Project Name}
> {Same summary}
{Same context}
## {Section Name}
<doc title="{Page Title}" path="{relative-path}">
{Full markdown content — frontmatter stripped, citations and diagrams preserved}
</doc>Inlining Rules
Strip YAML frontmatter (
---blocks) from each pagePreserve Mermaid diagrams — keep
```mermaidfences intactPreserve citations — all
[file:line](URL)links stay as-isPreserve tables — all markdown tables stay intact
Preserve
<!-- Sources: -->comments — these provide diagram provenance
Prerequisites
This skill works best when wiki pages already exist (via /deep-wiki:generate or /deep-wiki:page). If no wiki exists yet:
Suggest running
/deep-wiki:generatefirstOR generate a minimal
llms.txtfrom README + source code scan (without wiki page links)
Output Files
Generate three files:
| File | Purpose | Discoverability |
|---|---|---|
./llms.txt | Root discovery file | Standard path per llms.txt spec. GitHub MCP get_file_contents and search_code find this first. |
wiki/llms.txt | Wiki-relative links | For VitePress deployment and wiki-internal navigation. |
wiki/llms-full.txt | Full inlined content | Comprehensive reference for agents needing all docs in one file. |
The root ./llms.txt links into wiki/ (e.g., [Guide](./wiki/onboarding/contributor-guide.md)). The wiki/llms.txt uses wiki-relative paths (e.g., [Guide](./onboarding/contributor-guide.md)).
If a root llms.txt already exists and was NOT generated by deep-wiki, do NOT overwrite it.
Validation Checklist
Before finalizing:
[ ] All linked files in
llms.txtactually exist[ ] All
<doc>blocks inllms-full.txthave real content (not empty)[ ] Blockquote is specific to this project (not generic boilerplate)
[ ] Sections ordered by importance
[ ] No duplicate page entries across sections
[ ] "Optional" section only contains truly optional content
[ ]
llms.txtis concise (1-5 KB)[ ]
llms-full.txtcontains all wiki pages
Requirements and compatibility
Works with: Claude Code, Claude apps, OpenAI Codex, GitHub Copilot, Cursor, Gemini CLI, Kiro, OpenCode, Goose, Amp, Roo Code, JetBrains Junie, Factory Droid, Devin (ex-Windsurf), Mistral Vibe, OpenHands, Letta
“Works with” means the tool reads the open Agent Skills format; a skill written for one tool may use features others lack.
Security
No issues found by our static scan· No issues found
A static scan is not a guarantee. Skills are third-party content: review a skill before you let an agent use it.
Attribution and licence
- Created by
- Microsoft
- Publisher
- Microsoft (Official)
- Source
- microsoft/skills · .github/plugins/deep-wiki/skills/wiki-llms-txt · commit 0696600
- Licence
- MIT License (redistribution allowed)
- LICENSE (added by AutoGineer from LICENSE)
- ATTRIBUTION.md (written by AutoGineer)
- Synced
AutoGineer is not affiliated with or endorsed by Microsoft or Microsoft.
Download ZIP
The ZIP holds the skill’s files, its licence files and an ATTRIBUTION.md. Download wiki-llms-txt.zip