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

mts-one

Skill1 starsChanged 4 months agoMITView on GitHub

Use when a declared frontend, backend, or integration workstream has one READY task for parent-led sequential TDD.

The file

We split this skill into the rules it gives an agent

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

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈1

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 1

    Very specific

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

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Write and run the smallest focused test.

    line 25
  2. Very specific:

    Update the task Evidence, Review, and Result sections with commands, exit codes, platform, and material results.

    line 31

≈ “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 One

Perform one workstream task through parent-led sequential TDD. This is the default execution mode and does not require a native writing subagent.

Preconditions

  1. Require an explicit user request and read the sidecar project, contract, active track, and selected task.
  2. Confirm task status: READY, matching lane/workstream, and a matching current branch/worktree. The parent Agent manually creates or enters that worktree; this Skill never runs Git setup.
  3. Change the task to IN_PROGRESS in the sidecar and record the parent host and identity in the track execution metadata.

TDD loop

For one focused behavior at a time:

  1. Write and run the smallest focused test. Record the intended Red failure.
  2. Implement the smallest Green change in the declared scope; run the test.
  3. Refactor only after Green; rerun focused tests.
  4. Obtain focused review. Native child Agents may assist only with research, review, or testing; they do not edit sidecar records or create commits.

Update the task Evidence, Review, and Result sections with commands, exit codes, platform, and material results. Record NOT RUN with a reason where appropriate. Move the task through IN_REVIEW to DONE, or BLOCKED with a specific owner and unblock condition. The parent Agent is the only maintainer of task records and commits.

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.