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

ado-project-discovery

Skill5 starsChanged 5 months agoMITView on GitHub

Use when the user asks about Azure DevOps projects, teams, organisation structure, or wants to list what projects or teams exist. "list my ADO projects", "what projects are in my organisation", "show teams in the Platform project", "which team owns the backend workload", "find the project for the mobile app", "how many teams does the Finance project have", "who is in the Cloud Infra team"

The file

We split this skill into the rules it gives an agent

8 rules. About 0 are common, 4 are distinctive, and 4 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈4

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 4

    Very specific

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

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

    List projects: Call core_list_projects to get the full project list with IDs, names, state (active/deleted), and visibility.

    line 34
  2. Distinctive:

    Filter if needed: If the user named a specific project, match by name (case-insensitive).

    line 37
  3. Distinctive:

    If ambiguous, present the full list and ask the user to confirm.

    line 38
  4. Very specific:

    List teams (if asked): Call core_list_project_teams(projectId) to get team names, team IDs, and descriptions.

    line 40
  5. Distinctive:

    Surface next steps: After listing, suggest follow-up actions the user can take: browse repos, create work items, check pipelines in the …

    line 43
  6. Very specific:

    Use the project name and ID returned here as inputs to other skills (ado-work-items, ado-pipelines, ado-repositories, etc.).

    line 66
  7. Distinctive:

    If the organisation has a large number of projects (>20), ask the user for a keyword to filter before presenting results.

    line 68
  8. Very specific:

    After listing and selecting a project here, the result can be passed to ado-context to store it as the session-wide active project.

    line 75

≈ “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 Project Discovery

List and explore Azure DevOps projects and team structure across an organisation.

When to use

  • User wants to know which projects exist in their ADO organisation
  • User needs to find the right project before creating work items or browsing repos
  • User wants to see the teams inside a project
  • User is onboarding and needs an overview of the organisation structure

MCP tools used

ToolPurpose
core_list_projectsList all projects in the organisation
core_list_project_teamsList all teams within a specific project

Workflow

  1. List projects. Call core_list_projects to get the full project list with IDs, names, state (active/deleted), and visibility.
  2. Filter if needed. If the user named a specific project, match by name (case-insensitive). If ambiguous, present the full list and ask the user to confirm.
  3. List teams (if asked). Call core_list_project_teams(projectId) to get team names, team IDs, and descriptions. Present as a flat table.
  4. Surface next steps. After listing, suggest follow-up actions the user can take: browse repos, create work items, check pipelines in the project.

Output Format

Projects

ProjectStateVisibilityID
PlatformActivePrivateabc-123
Mobile AppActivePrivatedef-456
Finance ModulesActivePrivateghi-789

Teams in a project

TeamDescription
Platform CoreOwns backend services and infra
Platform QAQuality assurance and test automation
Platform DevOpsPipeline and environment management

Notes

  • Use the project name and ID returned here as inputs to other skills (ado-work-items, ado-pipelines, ado-repositories, etc.).
  • If the organisation has a large number of projects (>20), ask the user for a keyword to filter before presenting results.
  • core_list_projects returns projects across all process templates (Agile, Scrum, CMMI).

Active context

This skill also powers the implicit context resolution used by all other skills.

  • After listing and selecting a project here, the result can be passed to ado-context to store it as the session-wide active project.
  • Suggest: "To avoid specifying the project every time, say: 'set active project Platform'."

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.