agentleFS
Sign inStart free
MosoFinMosoFin/mosofin-plugins/skills/list-skills/SKILL.md

list-skills

Skill3 starsChanged 22 days agoMITView on GitHub

List the user's saved MosoFin skills in the confirmed workspace (maps to the get_skills MCP tool). Use when the user asks what skills they have saved, whether a workflow exists, or before choosing a skill to replay.

7 other projects use a version of this.

Adopted by

Most recently taken up by

The file

We split this skill into the rules it gives an agent

3 rules. 0 are common, 1 is distinctive, and 2 are very specific to this project.

  • 0

    Common

    Most of the 5 edited versions we read keep these.

  • 1

    Distinctive

    This author's own choices. Worth a look.

  • 2

    Very specific

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

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

    If MosoFin tools are absent, a call returns Unknown tool, or MosoFin reports that sign-in is required: the user is not signed in to MosoFin …

    line 14
  2. Very specific:

    Call get_skills with the confirmed workspace_id.

    line 24
  3. Distinctive:

    Never auto-replay a skill because its name looked close to the request.

    line 33

“Common” is measured: kept by at least 6 in 10 of the 5 edited versions of this file we could read. “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

List saved skills

Wraps the server's get_skills tool. Skills are private to the caller and scoped per workspace — a skill saved in workspace A is not listed in B. Full spec: docs/mcp-tool-spec.md §3.5.

If MosoFin tools are missing

If MosoFin tools are absent, a call returns Unknown tool, or MosoFin reports that sign-in is required: the user is not signed in to MosoFin in this host (this is not a company-file reconnect). Keep their request and follow /mosofin:connect (skills/connect/SKILL.md) to get them signed in from this conversation, then continue. Never say "refresh/reconnect". Do not invent saved skills.

Steps

  1. Confirm workspace via list_workspaces if this chat has not already.
  2. Call get_skills with the confirmed workspace_id.
  3. Present each skill by name with its description, datasources, and whether it is enabled. Show skill_id only if the user asks for a machine handle. Ignore dashboard_slug — legacy; never route to show_* tools.
  4. Next steps:
    • To replay one: /mosofin:replay-skill (requires an explicit yes first).
    • Empty list or no match: answer the underlying question directly via /mosofin:query-workspace, and offer /mosofin:save-skill afterwards.

Never auto-replay a skill because its name looked close to the request.

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.

Check your setup, free