agentleFS
sohaibdevvsohaibdevv/project-template/.agents/skills/start/SKILL.md

start

Skill2 starsChanged 3 months agoMITView on GitHub

Write the project brief and set up the starter. Use when someone describes something they want to build, describes a business problem they want software for, or asks where to begin, and project/BRIEF.md does not exist yet.

130 other projects use a version of this.

Adopted by

Most recently taken up by

Used with

Projects with it also use setup-engine, team-audio and 10 more.

Other files people use alongside this one.

Files found in the same public projects as a version of this one, more often than they turn up anywhere else. Each project counts once, large collections count for less, and this file's own repository is left out.
  • CoralGameSkill

    setup-engine

    Configure the project's game engine and version. Pins the engine in CLAUDE.md, detects knowledge gaps, and populates engine reference docs via WebSearch when the version is beyond the LLM's training data.

    Also in 13 projects that use this

  • CoralGameSkill

    team-audio

    Orchestrate audio team: audio-director + sound-designer + technical-artist + gameplay-programmer for full audio pipeline from direction to implementation.

    Also in 13 projects that use this

  • lilangMaxSkill

    create-stories

    Break a single epic into implementable story files. Reads the epic, its GDD, governing ADRs, and control manifest. Each story embeds its GDD requirement TR-ID, ADR guidance, acceptance criteria, story type, and test evidence path. Run after /create-epics for each epic.

    Also in 11 projects that use this

  • lilangMaxSkill

    story-done

    End-of-story completion review. Reads the story file, verifies each acceptance criterion against the implementation, checks for GDD/ADR deviations, prompts code review, updates story status to Complete, and surfaces the next ready story from the sprint.

    Also in 11 projects that use this

  • +5 more from CoralGame
  • +3 more from lilangMax

The file

We split this skill into the rules it gives an agent

6 rules. 0 are common, 3 are distinctive, and 3 are very specific to this project.

  • 0

    Common

    Most of the 116 edited versions we read keep these.

  • 3

    Distinctive

    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:

    If BRIEF.md exists, summarise it in five lines and ask whether to continue that project or replace it.

    line 16
  2. Distinctive:

    Done when: every profile question in INTAKE.md has an answer in this conversation.

    line 26
  3. Distinctive:

    When nothing forced it up, the answer is level 0.

    line 42
  4. Distinctive:

    Before naming level 2 or 3, check the answer to question 2 of the interview.

    line 44
  5. Very specific:

    Create project/PROFILE.md, project/BRIEF.md, project/SLICES.md, and project/DECISIONS.md from the templates in INTAKE.md.

    line 50
  6. Very specific:

    Done when: all four files exist, .stack-level holds a valid level, and every heading in every template carries a real answer.

    line 54

“Common” is measured: kept by at least 6 in 10 of the 116 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

Start

Turn what someone says into a brief, route them to a level, and build the starter.

Take this slowly. The interview decides what gets built.

1. Check for an existing brief

Read project/.

If BRIEF.md exists, summarise it in five lines and ask whether to continue that project or replace it.

Done when: project/ holds no brief, or they have chosen continue or replace.

2. Interview the person

Work through the profile questions in INTAKE.md. One question at a time. Wait for each answer before asking the next.

Give two named options wherever you can, and say what each means for their business rather than for the code.

Done when: every profile question in INTAKE.md has an answer in this conversation. None batched, none skipped, none assumed.

3. Interview the project

Work through the brief questions in INTAKE.md the same way.

Then read back a five-line brief: the one person it is for, the recurring problem in their words, the one job the app does, what working looks like, what is out of scope.

Done when: they have confirmed that brief, in their own words, and corrected anything you got wrong.

4. Route to a level

Work docs/decision-tree.md in order. Start at level 0 and let the questions push it up.

State the level, quote the question that forced it word for word, and say in one sentence what they can and cannot do there.

When nothing forced it up, the answer is level 0. Recommend it as the good outcome, not a downgrade: it costs nothing, works today, and has no server to maintain. Name the one thing that would move them up later.

Before naming level 2 or 3, check the answer to question 2 of the interview. A team with nobody who writes code is capped at level 1, whatever the workload looks like.

Done when: they have agreed to a level, you can quote the exact question that forced it, and the maintenance answer supports it.

5. Write the memory

Create project/PROFILE.md, project/BRIEF.md, project/SLICES.md, and project/DECISIONS.md from the templates in INTAKE.md. Write the level into .stack-level as l0, l1, l2, or l3.

Seed SLICES.md with the three smallest slices that would prove the app works, smallest first.

Done when: all four files exist, .stack-level holds a valid level, and every heading in every template carries a real answer. No placeholder text remains anywhere.

6. Build the starter

For level 0, run /make-skill and stop here. There is nothing to scaffold.

For levels 1 to 3, follow SCAFFOLD.md.

Done when: for level 0, they have run their new skill once on a real instance of the job. For levels 1 to 3, the dev server is running and they confirm they can see the first screen in their own browser.

7. Tell them what happens next

Three things:

  • Say what you want and it gets built. There are no commands to learn.
  • project/DECISIONS.md is the record of everything they decide, in plain English.
  • ./scripts/preflight.sh is the safety check, and it runs before anything goes live.

Then ask what the first slice should be, and run /build.

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.