agentleFS
anorthanorth/agent-skills/skills/lets-build/SKILL.md

lets-build

Skill1 starsChanged 10 days agoMITView on GitHub

Build from a written ticket or task, collaborating with the user: design it with them first if it isn't ready, then build it with the user in the loop. Use when the user says let's build, build together, or asks to build from a ticket or task description.

The file

We split this skill into the rules it gives an agent

7 rules. About 0 are common, 4 are distinctive, and 3 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈4

    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. Distinctive:

    Use when the user says let's build or build together, or asks to build a ticket or task with them.

    line 17
  2. Very specific:

    If the user wants the ticket built independently, with the agent making its own decisions, use /build-ticket.

    line 19
  3. Very specific:

    If they want to design without building yet, use /lets-design.

    line 20
  4. Distinctive:

    If it is unclear which item: ask.

    line 27
  5. Very specific:

    Read the ticket in full. If it doesn't satisfy /ready-ticket, load and follow /lets-design first, then write the agreed design into tickets …

    line 29
  6. Distinctive:

    If that makes more than one ticket, stop there, and suggest which ticket is ready to pick up.

    line 31
  7. Distinctive:

    When they do, keep the ticket's original brief and append a note saying what changed and why.

    line 40

≈ “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

Let's Build

Build one ticket together. The agent does the work; the user stays in the loop for design and decisions. A ticket that isn't ready yet gets designed first.

When to use

Use when the user says let's build or build together, or asks to build a ticket or task with them.

If the user wants the ticket built independently, with the agent making its own decisions, use /build-ticket. If they want to design without building yet, use /lets-design.

Workflow

1. Load the ticket

Identify the written ticket or task. The user may give an id, URL, file path, or pasted text. If it is unclear which item: ask. Do not guess.

Read the ticket in full. If it doesn't satisfy /ready-ticket, load and follow /lets-design first, then write the agreed design into tickets with /to-tickets. If that makes more than one ticket, stop there, and suggest which ticket is ready to pick up.

2. Build

Build with the /build-ticket skill, with the user in the loop.

Guidelines

The user is the authority on what the system should do: their answers override the ticket. When they do, keep the ticket's original brief and append a note saying what changed and why.

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.