agentleFS
AurelienClere-365AurelienClere-365/ado-cowork-plugin/skills/ado-repositories/SKILL.md

ado-repositories

Skill5 starsChanged 5 months agoMITView on GitHub

Use when the user asks about Azure DevOps Git repositories, branches, source files, commit history, or wants to create a branch. "list repos in the Platform project", "show the file structure of the api-gateway repo", "read the content of appsettings.json", "what branches exist in backend", "create a branch feature/my-feature from main", "show recent commits on the release/2.0 branch", "find commits by Alice last week", "what changed in the last merge to main", "show me the YAML pipeline file"

The file

We split this skill into the rules it gives an agent

6 rules. About 0 are common, 1 is distinctive, and 5 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈1

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 5

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Very specific:

    Call repo_repository(project) — returns all repos with name, ID, default branch, size, and last update time.

    line 44
  2. Very specific:

    Call repo_file(repo, path, branch) with path = "/" for root listing.

    line 51
  3. Distinctive:

    If the content is code, present it in a fenced code block with the correct language tag.

    line 54
  4. Very specific:

    Call repo_branch(repo) — returns all branches with name, last commit hash, last commit date, and author.

    line 58
  5. Very specific:

    If activeProject is set, use it automatically as the project parameter — do not ask the user to re-specify it.

    line 114
  6. Very specific:

    If no context is set and a project is required, invoke Workflow E of ado-context to resolve it (list projects, ask user to pick, then …

    line 116

≈ “Common” is an estimate: at least 1 in 5 of the 350,495 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

ADO Repositories

Browse Azure DevOps Git repositories, explore files and folders, view branch lists, read file contents, inspect commit history, and create branches.

When to use

  • User wants to list all repositories in a project
  • User wants to navigate the file tree of a repository
  • User wants to read the content of a specific file
  • User wants to see which branches exist
  • User wants to create a new branch (e.g. from main for a feature)
  • User wants to see commit history for a branch or file
  • User wants to find commits by a specific author or in a date range

MCP tools used

ToolPurpose
repo_repositoryList repositories or get metadata for a specific repo
repo_branchList branches in a repository
repo_create_branchCreate a new branch from a source ref
repo_fileRead file content or list directory contents
repo_search_commitsSearch commit history with filters

Workflow

Listing repositories

  1. Call repo_repository(project) — returns all repos with name, ID, default branch, size, and last update time.
  2. Present the Repository List table.

Browsing files

  1. Identify: repository name and optional path.
  2. Call repo_file(repo, path, branch) with path = "/" for root listing.
  3. For a folder: returns child items (files and subfolders).
  4. For a file: returns the raw content.
  5. If the content is code, present it in a fenced code block with the correct language tag.

Listing branches

  1. Call repo_branch(repo) — returns all branches with name, last commit hash, last commit date, and author.
  2. Present the Branch List table.

Creating a branch

  1. Identify: repo, new branch name, and source branch (default: main).
  2. Confirm with the user before proceeding (branch creation is a write operation).
  3. Call repo_create_branch(repo, newBranchName, sourceBranch).
  4. Confirm with the new branch name and its source commit.

Commit history

  1. Identify: repo, branch (optional), author filter (optional), date range (optional).
  2. Call repo_search_commits(repo, branch, author, fromDate, toDate, top).
  3. Present the Commit History table.

Output Format

Repository List

RepositoryDefault BranchLast UpdatedSize
api-gatewaymain2h ago4.2 MB
identity-servicemain1d ago1.8 MB
shared-libmain3d ago0.6 MB

Branch List

BranchLast CommitAuthorDate
maina1b2c3dAlice Martin2h ago
feature/redise4f5a6bCarlos Silva4h ago
release/2.0c7d8e9fBob Nguyen1d ago

Commit History

HashMessageAuthorDate
a1b2c3dfix: refresh token before expiry (#1058)Alice Martin2h ago
b2c3d4efeat: add Redis cache layerCarlos Silva1d ago
c3d4e5fchore: update dependenciesBob Nguyen2d ago

Notes

  • File content returned by repo_file is base64-encoded for binary files. For text files, decode and present as a code block.
  • Branch names may contain slashes (e.g. feature/my-feature). Pass them URL-encoded if the MCP tool requires it.
  • Confirm branch creation before calling repo_create_branch — this is a write operation that cannot be easily undone without repo admin access.
  • To read a pipeline YAML file, use repo_file(repo, 'azure-pipelines.yml', branch).

Active context

This skill respects the session context set by the ado-context skill.

  • If activeProject is set, use it automatically as the project parameter — do not ask the user to re-specify it.
  • If no context is set and a project is required, invoke Workflow E of ado-context to resolve it (list projects, ask user to pick, then proceed).

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.