agentleFS
SuShuhengSuShuheng/making-things/skills/mts-split/SKILL.md

mts-split

Skill1 starsChanged 4 months agoMITView on GitHub

Use when an approved Electron contract must split one feature into frontend, backend, and integration workstreams with TDD task records.

The file

We split this skill into the rules it gives an agent

3 rules. About 0 are common, 0 are distinctive, and 3 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.

  • 3

    Very specific

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

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

    Read the sidecar PROJECT.md and an approved CONTRACT.md.

    line 15
  2. Very specific:

    Create one or more TDD task records under work-items/{frontend|backend|integration}/<work-item-id>/TASK.md.

    line 41
  3. Very specific:

    Do not start implementation.

    line 56

≈ “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

MTS Split

Turn an approved Electron contract into three coordinated, Git-backed Markdown workstreams. This Skill writes or directs the parent Agent to write sidecar records only; it never runs Git operations.

Preconditions

  1. Require an explicit user request to split the feature.
  2. Read the sidecar PROJECT.md and an approved CONTRACT.md.
  3. Reject the split if the contract does not define renderer ownership, main/preload/IPC ownership, errors, permissions, and cross-track acceptance.
  4. Choose a lowercase YYYY-MM-DD-english-summary. Reject another form.
  5. Inspect active sidecar tracks and tasks. Reject any cross-lane scope overlap unless an explicit dependency serializes the work.

Create records

Using the packaged templates, create exactly these tracks under the sidecar:

workstreams/
  frontend/<date-summary>/TRACK.md
  backend/<date-summary>/TRACK.md
  integration/<date-summary>/TRACK.md

For each track record:

  • Set branch to {lane}/{date-summary}.
  • Set worktree to .worktrees/{lane}/{date-summary}.
  • Set status: NOT_STARTED, an initial current_task, and an execution mode.
  • State the owned paths and excluded paths. Do not create a code worktree or branch; the responsible parent Agent does that manually before activation.

Create one or more TDD task records under work-items/{frontend|backend|integration}/<work-item-id>/TASK.md.

  • Each task declares dependencies, scope, deliverables, and execution mode.
  • Frontend owns renderer work; backend owns main/preload/IPC work; integration owns cross-track E2E and assembly work.
  • Integration tasks depend on the specific declared frontend and backend deliverables. Do not mark integration ready before they are complete.
  • A task must not declare a Git branch or worktree.

Report and stop

Report the three track locations, task IDs, scope boundaries, dependencies, and the manual action each parent Agent must take to create/enter its declared worktree. Do not claim parallel safety without the recorded disjoint scopes. Do not start implementation; route the chosen task to mts-one or mts-more.

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.