agentleFS
razvan-scrazvan-sc/claude-atlas/.claude/skills/atlas-tag/SKILL.md

atlas-tag

Skill0 starsChanged 4 months agoMITView on GitHub

List Atlas projects filtered by a tag

The file

We split this skill into the rules it gives an agent

8 rules. About 0 are common, 3 are distinctive, and 5 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈3

    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:

    Use the atlas MCP server. All tool calls use the mcp__atlas__ prefix.

    line 13
  2. Very specific:

    Check if a tag was provided as an argument (e.g., /atlas-tag platform).

    line 17
  3. Distinctive:

    If not provided, ask the user: "Which tag would you like to filter by?"

    line 18
  4. Very specific:

    Call mcp__atlas__list_projects with limit: 50 and tag: <tag>.

    line 20
  5. Distinctive:

    If status is missing, show "-"

    line 28
  6. Distinctive:

    If target date is missing, show "-"

    line 29
  7. Very specific:

    Check that the Atlas MCP server is configured in .mcp.json

    line 37
  8. Very specific:

    Verify ~/.atlas/config.json exists with valid credentials

    line 38

≈ “Common” is an estimate: at least 1 in 5 of the 372,429 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

Atlas Projects by Tag

List Atlas projects that have a specific tag.

MCP Server

Use the atlas MCP server. All tool calls use the mcp__atlas__ prefix.

Workflow

  1. Check if a tag was provided as an argument (e.g., /atlas-tag platform).
    • If not provided, ask the user: "Which tag would you like to filter by?"
  2. Call mcp__atlas__list_projects with limit: 50 and tag: <tag>.
  3. Parse the returned JSON and format the results as a table:

    KeyNameStatusTarget DateTags
    PROJ-1Example ProjectON_TRACK2025-06-30platform
    • If status is missing, show "-"
    • If target date is missing, show "-"
    • Tags are comma-separated
  4. Show a count summary at the end: Showing N projects tagged "<tag>"
  5. If no projects found, respond: No projects found with tag "<tag>".
  6. On error, display the error message clearly and suggest:
    • Check that the Atlas MCP server is configured in .mcp.json
    • Verify ~/.atlas/config.json exists with valid credentials

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.