Segment Anything Model Guide
Orchestra-Research/AI-Research-SKILLs
Guide to using Meta's Segment Anything Model for zero-shot image segmentation with point, box or mask prompts, or automatic mask generation.
Official agent skill
Cross Repository References
How to configure cross-repository references (CRR) and create API class links for Microsoft Learn docs in this repository.
Install Cross Repository References
$ npx skills add MicrosoftDocs/semantic-kernel-docs --skill cross-repository-references -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install MicrosoftDocs/semantic-kernel-docs cross-repository-references --agent claude-codeProject scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).
$ git clone --depth 1 https://github.com/MicrosoftDocs/semantic-kernel-docs.git skills-src && mkdir -p .claude/skills && cp -r skills-src/.github/skills/cross-repository-references .claude/skills/cross-repository-references && rm -rf skills-srcUse ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.
Claude Code skills documentation · loads skills from .claude/skills/
Install the "cross-repository-references" agent skill from https://github.com/MicrosoftDocs/semantic-kernel-docs/tree/main/.github/skills/cross-repository-references into .claude/skills/cross-repository-references/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "cross-repository-references", then confirm the skill loads.Claude Code copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$skill-installer install https://github.com/MicrosoftDocs/semantic-kernel-docs/tree/main/.github/skills/cross-repository-referencesType this inside Codex. $skill-installer <name> installs a curated skill from openai/skills. The installer writes to $CODEX_HOME/skills (default ~/.codex/skills). Restart Codex if the skill does not show up.
$ npx skills add MicrosoftDocs/semantic-kernel-docs --skill cross-repository-references -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install MicrosoftDocs/semantic-kernel-docs cross-repository-references --agent codexProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/MicrosoftDocs/semantic-kernel-docs.git skills-src && mkdir -p .agents/skills && cp -r skills-src/.github/skills/cross-repository-references .agents/skills/cross-repository-references && rm -rf skills-srcUse ~/.agents/skills/ instead of .agents/skills for a personal install.
Codex skills documentation · loads skills from .agents/skills/
Install the "cross-repository-references" agent skill from https://github.com/MicrosoftDocs/semantic-kernel-docs/tree/main/.github/skills/cross-repository-references into .agents/skills/cross-repository-references/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "cross-repository-references", then confirm the skill loads.Codex copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add MicrosoftDocs/semantic-kernel-docs --skill cross-repository-references -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install MicrosoftDocs/semantic-kernel-docs cross-repository-references --agent cursorProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/MicrosoftDocs/semantic-kernel-docs.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/.github/skills/cross-repository-references .cursor/skills/cross-repository-references && rm -rf skills-srcUse ~/.cursor/skills/ instead of .cursor/skills for a personal install.
Cursor skills documentation · loads skills from .cursor/skills/, .agents/skills/, .claude/skills/, .codex/skills/
Install the "cross-repository-references" agent skill from https://github.com/MicrosoftDocs/semantic-kernel-docs/tree/main/.github/skills/cross-repository-references into .cursor/skills/cross-repository-references/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "cross-repository-references", then confirm the skill loads.Cursor copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gemini skills install https://github.com/MicrosoftDocs/semantic-kernel-docs.git --path .github/skills/cross-repository-references--scope user (default) or --scope workspace; --path is the subfolder of the repo that holds the skill; --consent skips the security confirmation prompt.
$ npx skills add MicrosoftDocs/semantic-kernel-docs --skill cross-repository-references -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install MicrosoftDocs/semantic-kernel-docs cross-repository-references --agent gemini-cliProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/MicrosoftDocs/semantic-kernel-docs.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/.github/skills/cross-repository-references .gemini/skills/cross-repository-references && rm -rf skills-srcUse ~/.gemini/skills/ instead of .gemini/skills for a personal install, then run /skills reload.
Gemini CLI skills documentation · loads skills from .gemini/skills/, .agents/skills/
Install the "cross-repository-references" agent skill from https://github.com/MicrosoftDocs/semantic-kernel-docs/tree/main/.github/skills/cross-repository-references into .gemini/skills/cross-repository-references/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "cross-repository-references", then confirm the skill loads.Gemini CLI copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gh skill install MicrosoftDocs/semantic-kernel-docs cross-repository-referencesInstalls for Copilot at project scope by default; add --scope user for a personal install. Preview a skill first with gh skill preview. Needs GitHub CLI 2.90.0 or later (public preview).
$ npx skills add MicrosoftDocs/semantic-kernel-docs --skill cross-repository-references -a github-copilotProject install goes to .agents/skills/; add -g for ~/.copilot/skills/.
$ git clone --depth 1 https://github.com/MicrosoftDocs/semantic-kernel-docs.git skills-src && mkdir -p .github/skills && cp -r skills-src/.github/skills/cross-repository-references .github/skills/cross-repository-references && rm -rf skills-srcUse ~/.copilot/skills/ instead of .github/skills for a personal install. Commit .github/skills so cloud agent and code review can use it.
GitHub Copilot skills documentation · loads skills from .github/skills/, .claude/skills/, .agents/skills/
Install the "cross-repository-references" agent skill from https://github.com/MicrosoftDocs/semantic-kernel-docs/tree/main/.github/skills/cross-repository-references into .github/skills/cross-repository-references/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "cross-repository-references", then confirm the skill loads.GitHub Copilot copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add MicrosoftDocs/semantic-kernel-docs --skill cross-repository-references -a opencodeOpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.
$ gh skill install MicrosoftDocs/semantic-kernel-docs cross-repository-references --agent opencodeProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/MicrosoftDocs/semantic-kernel-docs.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/.github/skills/cross-repository-references .opencode/skills/cross-repository-references && rm -rf skills-srcUse ~/.config/opencode/skills/ instead of .opencode/skills for a personal install.
OpenCode skills documentation · loads skills from .opencode/skills/, .claude/skills/, .agents/skills/
Install the "cross-repository-references" agent skill from https://github.com/MicrosoftDocs/semantic-kernel-docs/tree/main/.github/skills/cross-repository-references into .opencode/skills/cross-repository-references/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "cross-repository-references", then confirm the skill loads.OpenCode copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
Facts
- Skill name
cross-repository-references- GitHub stars
- 264
- Token cost
- ~1k tokens
- SKILL.md length
- 346 words
- Files
- 1
- Skills in repo
- 7
- Repo updated
- First seen
- Licence
- MIT
At a glance
How to configure cross-repository references (CRR) and create API class links for Microsoft Learn docs in this repository.
- Works in 4 steps: Add a dependent_repositories entry in… → Use dependency paths from docs content… → If needed, add exclusion rules in… → …
- AI & LLM Engineering work in your project
- SKILL.md covers Purpose, Where CRR is configured, CRR schema and Current repo baseline, plus 5 more sections
- Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md
What it does
Cross Repository References is an agent skill from MicrosoftDocs/semantic-kernel-docs, published by the product's own GitHub organization. How to configure cross-repository references (CRR) and create API class links for Microsoft Learn docs in this repository.
Its SKILL.md is about 1k tokens, which your agent loads only when the skill is triggered. It is a single SKILL.md file with no bundled scripts.
It sits in AI & LLM Engineering. It works with Python. The repository describes itself as: Semantic Kernel (SK) is a lightweight SDK enabling integration of AI Large Language Models (LLMs) with conventional programming languages. The licence is MIT.
When your agent uses it
- AI & LLM Engineering work in your project
Example prompts
- “/cross-repository-references”
Requirements
- Python 3
Workflow steps
4 steps, taken from the first numbered list in SKILL.md.
- Add a dependent_repositories entry in .openpublishing.publish.config.json
- Use dependency paths from docs content ([!INCLUDE], :::code, or static asset references)
- If needed, add exclusion rules in docfx.json so referenced source trees are not published as content
- Add dependency mount folders to .gitignore if local build artifacts create noise
What it can do on your machine
Read from SKILL.md and the folder at commit 6997e10. It shows what the files ask for, not the result of running them.
Tool permissions
Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.
From allowed-tools in the SKILL.md frontmatter.
Runs code
No scripts in the folder and no shell commands in SKILL.md (its code samples are json and markdown).
From the folder's file list and the shell code blocks in SKILL.md.
Network
Links to these hosts (documentation or services it may open):
learn.microsoft.com
From URLs in SKILL.md, links to its own repository left out.
Credentials
Names no API keys, tokens, secrets or passwords.
From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.
Context cost
Cross Repository References loads about 1k tokens when it runs. Until then it costs about 38 tokens; SKILL.md has 346 words of instructions outside code blocks.
Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.
Safety
Auto-check passed
The automated check found no risky patterns in SKILL.md.
Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.
SKILL.md
The full file from MicrosoftDocs/semantic-kernel-docs at commit 6997e10, republished under its MIT licence (© MicrosoftDocs). 346 words, ~1,030 tokens.
Download SKILL.mdSave it as
.claude/skills/cross-repository-references/SKILL.md (or your agent's skills folder).- name
- cross-repository-references
- description
- How to configure cross-repository references (CRR) and create API class links for Microsoft Learn docs in this repository.
Skill: Cross-Repository References (CRR) and API Class Links
Purpose
Use this skill when you need to:
- reference files from another repository during Docs build (CRR)
- add stable links to Python API classes in Microsoft Learn docs pages
CRR replaces Git submodule-based references for docs build scenarios and is easier to reason about for doc authors.
Where CRR is configured
CRR is configured in:
.openpublishing.publish.config.json
The key is:
dependent_repositories
CRR schema
{
"dependent_repositories": [
{
"path_to_root": "<relative path>",
"url": "<repository URL>",
"branch": "<default branch>",
"branch_mapping": {
"<source branch>": "<dependency branch>"
}
}
]
}Fields
| Field | Required | Meaning |
|---|---|---|
dependent_repositories | Yes | List of CRR entries |
path_to_root | Yes | Where the dependency is mounted in the build workspace |
url | Yes | Dependency repository URL |
branch | Yes | Default dependency branch |
branch_mapping | No | Optional source->dependency branch override map |
Current repo baseline
This repository already uses CRR in .openpublishing.publish.config.json for:
_themes_themes.pdfsemantic-kernel-samplessemantic-kernel-samples-java
Prefer extending the existing dependent_repositories list instead of introducing alternate mechanisms.
Path semantics (~, ..) for references
~resolves to the docset root (build_source_folder)- in this repo, for Agent Framework docs, docset root is
agent-framework/ - use
~/..to move from docset root to repository root
Example (from Agent Framework docset to CRR sample repo):
~/../semantic-kernel-samples/path/to/file.pyAdding a new CRR dependency
- Add a
dependent_repositoriesentry in.openpublishing.publish.config.json - Use dependency paths from docs content (
[!INCLUDE],:::code, or static asset references) - If needed, add exclusion rules in
docfx.jsonso referenced source trees are not published as content - Add dependency mount folders to
.gitignoreif local build artifacts create noise
API class links (Python)
For Agent Framework Python API links, use Learn URLs with explicit package + module/class paths.
Preferred link forms
- Module landing:
/python/api/agent-framework-core/agent_framework?view=agent-framework-python-latest
- Class page:
/python/api/agent-framework-core/agent_framework.baseagent?view=agent-framework-python-latest/python/api/agent-framework-core/agent_framework.agent?view=agent-framework-python-latest/python/api/agent-framework-core/agent_framework.supportschatgetresponse?view=agent-framework-python-latest/python/api/agent-framework-core/agent_framework.supportsagentrun?view=agent-framework-python-latest/python/api/agent-framework-core/agent_framework.agentresponseupdate?view=agent-framework-python-latest
Markdown pattern
[`BaseAgent`](/python/api/agent-framework-core/agent_framework.baseagent?view=agent-framework-python-latest)Practical guidance
- prefer class-level links when the class page exists
- if a class page does not exist, link to the module landing page
- when code and API reference differ, prefer code-leading class names and matching URL slug
- keep link text aligned with surrounding docs terminology
- use relative Learn paths (
/python/api/...) instead of hardcoded absolute hostnames
Validation checklist
- link resolves to an existing Learn page
view=agent-framework-python-latestis present- no broken relative paths (
./,../) introduced - doc wording stays accurate after class/protocol name linking
References
© MicrosoftDocs, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file
Files
Just SKILL.md in .github/skills/cross-repository-references of MicrosoftDocs/semantic-kernel-docs.
Open the folder on GitHubat commit 6997e10
Compare with similar skills
Cross Repository References next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.
| Skill | Stars | Used in | Tokens | Auto-check | Licence | Repo updated |
|---|---|---|---|---|---|---|
| Cross Repository References this skillMicrosoftDocs/semantic-kernel-docs | 264 | — | ~1k | Automated safety check: Pass | MIT | |
| Segment Anything Model GuideOrchestra-Research/AI-Research-SKILLs | 13k | 9 repos | ~3.3k | Automated safety check: Pass | MIT | |
| Chroma Vector DatabaseOrchestra-Research/AI-Research-SKILLs | 13k | 8 repos | ~2.3k | Automated safety check: Pass | MIT | |
| CLIP Image-Text MatchingOrchestra-Research/AI-Research-SKILLs | 13k | 8 repos | ~1.7k | Automated safety check: Pass | MIT | |
| LLM Benchmarking with lm-evaluation-harnessOrchestra-Research/AI-Research-SKILLs | 13k | 8 repos | ~3k | Automated safety check: Pass | MIT | |
| Azure AI Projects Python SDKmicrosoft/skills | 3.1k | 6 repos | ~2.8k | Automated safety check: Pass | MIT |
Similar skills
Chroma Vector Database
Orchestra-Research/AI-Research-SKILLs
Shows how to store documents and embeddings in Chroma, query them by similarity with metadata filters, and persist them to disk for RAG and semantic search projects.
CLIP Image-Text Matching
Orchestra-Research/AI-Research-SKILLs
Explains OpenAI's CLIP model for zero-shot image classification, image-text similarity, semantic image search and content moderation, with install steps and code patterns.
LLM Benchmarking with lm-evaluation-harness
Orchestra-Research/AI-Research-SKILLs
Runs lm-evaluation-harness to benchmark language models on academic suites such as MMLU, GSM8K and HumanEval, compare models and track training checkpoints.
- Official
Azure AI Projects Python SDK
microsoft/skills
Reference for building on Microsoft Foundry with the azure-ai-projects Python SDK: project clients, versioned agents, evaluations, connections, datasets and indexes.
Paddle Design Distributed
PaddlePaddle/Paddle
A skill your agent uses when working with Paddle's distributed training system: understanding parallelism strategies (DP, ZeRO, TP, PP, SP), semi-automatic parallel with ProcessMesh + shardtensor…
More from MicrosoftDocs/semantic-kernel-docs
- Official
Breadcrumbs
MicrosoftDocs/semantic-kernel-docs
How breadcrumbs work on Microsoft Learn: structure, creation, configuration in docfx.json, and best practices for documentation repos.
- Official
Code Snippets
MicrosoftDocs/semantic-kernel-docs
How to reference code from sample repos in Agent Framework docs pages using :::code directives, snippet tags, zone pivots, and highlight attributes.
- Official
Redirection
MicrosoftDocs/semantic-kernel-docs
How to delete, rename, or move articles on Microsoft Learn while preserving Platform IDs, preventing broken links, and managing redirects.
- Official
Sample Structure
MicrosoftDocs/semantic-kernel-docs
Conceptual organization of Agent Framework documentation and samples.
- Official
Toc
MicrosoftDocs/semantic-kernel-docs
How to create, structure, and configure table of contents (TOC) files for Microsoft Learn documentation using toc.yml and docfx.json.
- Official
Per Concept Documentation
MicrosoftDocs/semantic-kernel-docs
Required when reviewing, updating, auditing, or creating any concept documentation page.
Related
Works with
Categories
Questions about Cross Repository References
What does Cross Repository References do?
How to configure cross-repository references (CRR) and create API class links for Microsoft Learn docs in this repository. Cross Repository References is an agent skill from MicrosoftDocs/semantic-kernel-docs, published by the product's own GitHub organization. How to configure cross-repository references (CRR) and create API class links for Microsoft Learn docs in this repository.
When should I use Cross Repository References?
Cross Repository References fits situations like: AI & LLM Engineering work in your project.
How do I install Cross Repository References in Claude Code?
Run `npx skills add MicrosoftDocs/semantic-kernel-docs --skill cross-repository-references -a claude-code`. Or copy the skill folder (.github/skills/cross-repository-references in MicrosoftDocs/semantic-kernel-docs) into .claude/skills/cross-repository-references in your project. Claude Code loads it when a task matches its description.
How do I install Cross Repository References in Codex?
Run `npx skills add MicrosoftDocs/semantic-kernel-docs --skill cross-repository-references -a codex`. Or copy the skill folder (.github/skills/cross-repository-references in MicrosoftDocs/semantic-kernel-docs) into .agents/skills/cross-repository-references in your project. Codex loads it when a task matches its description.
Can I use Cross Repository References in Cursor, Gemini CLI or GitHub Copilot?
Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add MicrosoftDocs/semantic-kernel-docs --skill cross-repository-references -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/cross-repository-references, .gemini/skills/cross-repository-references, .github/skills/cross-repository-references and .opencode/skills/cross-repository-references in your project.
What does Cross Repository References need to run?
SKILL.md names no scripts, command-line tools or credentials: Cross Repository References is instructions for the agent only. Our summary lists: Python 3.
Does Cross Repository References access the network?
SKILL.md names 1 domain. As links in the text: learn.microsoft.com. This is read from the text; nothing was executed.
Is Cross Repository References safe to install?
Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.
What licence does Cross Repository References use?
Cross Repository References is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.
How many tokens does Cross Repository References use?
About 1k tokens (SKILL.md is roughly 4.1k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.
What are the alternatives to Cross Repository References?
Skills that share tags, products or a category with Cross Repository References: Segment Anything Model Guide (Orchestra-Research/AI-Research-SKILLs, 13k stars), Chroma Vector Database (Orchestra-Research/AI-Research-SKILLs, 13k stars), CLIP Image-Text Matching (Orchestra-Research/AI-Research-SKILLs, 13k stars) and LLM Benchmarking with lm-evaluation-harness (Orchestra-Research/AI-Research-SKILLs, 13k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
Who maintains Cross Repository References?
MicrosoftDocs (a GitHub organization, an official publisher) maintains it in MicrosoftDocs/semantic-kernel-docs, which has 264 GitHub stars. The repository holds 7 skills in this directory. The repository was last updated on October 2, 2026.
Source: MicrosoftDocs/semantic-kernel-docs on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.