agentleFS
Sign inStart free
RamtoiRamtoi/skill-tree/skills/skt-mcp/SKILL.md

skt-mcp

Skill4 starsChanged 47 days agoApache-2.0View on GitHub

Use when asked to equip/enable/disable a skill or bundle, create or edit a skill, mcp, or inspect the Skill Hub registry. Trigger: "equip", "skill tree", "enable skill", "snippet", "update skill"

The file

We split this skill into the rules it gives an agent

2 rules. About 0 are common, 0 are distinctive, and 2 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈0

    Distinctive · estimate

    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:

    Create a skill: skill_create, then edit its files on disk, then equip it.

    line 30
  2. Very specific:

    Every result is {ok, result, output, error}.

    line 48

≈ “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

Skill Hub over MCP

The skill-tree MCP server is the control plane for the Skill Hub registry: skills, bundles (ordered skill groups), snippets (reusable agent-doc blocks), and their assignment to projects. Every write auto-syncs symlinks and harness configs — you never need to follow up with sync after a normal mutation.

Discover before you write

Names must be exact. Discover them first:

  • project_list — the only source of valid project values (+ each project's active skills).
  • skill_list — all skills; pass project to see what's active there.
  • bundle_list — bundles, their ordered skills, and where they're applied.
  • snippet_list — snippets; name for detail, project/scan for placement status.
  • inspect — harness inventory, permissions (read-only), risk scan, agent-doc root status.
  • skill_candidates — hand-authored project-local skills the hub doesn't manage yet.

Core operations

  • Equip/unequip: equip {target: skill|bundle, name, project, state: on|off}. Optional invocation (skill + on only) sets a per-project invocation override.
  • Create a skill: skill_create, then edit its files on disk, then equip it.
  • Edit metadata: skill_set_meta (scope, description, harness affinity as an array, invocation mode; new_name renames — alone, not combined with other fields).
  • Adopt a hand-authored skill: skill_candidates → skill_import.
  • Bundles: bundle_save upserts (the skills array order is preserved).
  • Snippets: snippet_save upserts the library copy; snippet_place {op: apply|remove|refresh} manages placements in project agent docs.

Safety rules

  • skill_archive and bundle_delete are destructive: they preview by default and only act with confirm: true. Preview first; ask the user before confirming unless they already told you to.
  • snippet_delete deletes the library definition immediately — no preview. It refuses while the snippet is still applied anywhere unless force: true, which orphans the in-file blocks.
  • Permissions and harnesses are READ-ONLY over MCP (inspect) — by design there is no MCP tool to change them; direct the user to the hub CLI or the Skill Tree app.
  • Every result is {ok, result, output, error}. On ok: false read error — it often names the fix (e.g. "use project_list to discover project names").

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