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

build

Skill2 starsChanged 3 months agoMITView on GitHub

Build one slice of the app, end to end. Use when the app should do something new, should do something differently, or has stopped working.

156 other projects use a version of this.

Adopted by

Most recently taken up by

Used with

Projects with it also use backprop, finances 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.
  • JuliusBrusseeSkill

    backprop

    Bug → spec protocol. When a bug is found or a test fails, trace the cause, decide whether a new §V invariant would catch recurrence, append to §B. This is the one non-obvious thing SDD does that plan-then-execute doesn't. Triggers on test failure, bug report, post-mortem, or explicit user ask.

    Also in 4 projects that use this

  • GerardoRdz96Skill

    finances

    Use when Gera talks about his money — logging an expense ("I spent X on Y"), checking where he stands this pay-period, closing a period, planning debt payoff, onboarding his financial picture, or asking for budgeting/finance opinions. Servy's financial brain. Triggers — "I spent", "log this expense", "where am I this period", "close the period", "how's my budget", "debt plan", "should I pay off", "finances onboard", "/finances".

    Also in 3 projects that use this

  • cpiprintSkill

    favicon

    Generate favicons from a source image

    Also in 3 projects that use this

  • madeehahassanSkill

    Go-Live

    Pre-launch checklist. Use before making any app public, sharing a link externally, or announcing a product launch. Adapts to Claude Code, claude.ai, and Cowork.

    Also in 3 projects that use this

  • JuliusBrusseeSkill

    deepen

    Optional design-improvement pass for when you have spare usage to drain. Finds the shallowest modules in the code the spec touches, researches a deeper design, and proposes refactors that shrink interfaces and hide decisions — behavior held constant, tests green before and after. Proposes §I/§V/§T edits, never silent rewrites. Triggers when the user says "deepen this", "improve the design", "this module feels shallow", "pull complexity down", "use spare budget on the codebase", or invokes /ck:deepen. Leans on the codebase-design skill's deep-module vocabulary when present.

    Also in 3 projects that use this

  • synaptiaiSkill

    gate

    Create a BDSK review_gate artifact. Defines a checkpoint that controls whether generated output may proceed toward acceptance. Use when defining quality, security, or scope gates for execution plans.

    Also in 5 projects that use this

The file

We split this skill into the rules it gives an agent

5 rules. 0 are common, 1 is distinctive, and 4 are very specific to this project.

  • 0

    Common

    Most of the 142 edited versions we read keep these.

  • 1

    Distinctive

    This author's own choices. Worth a look.

  • 4

    Very specific

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

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

    Read everything in project/.

    line 12
  2. Very specific:

    If that sentence needs an "and" in the middle, it is two slices.

    line 18
  3. Very specific:

    If the slice needs people to sign in and .stack-level says l1, run /level-up first.

    line 20
  4. Very specific:

    Follow docs/recipes/l<n>.md for the level in .stack-level.

    line 44
  5. Distinctive:

    Done when: every file in step 3's list has its line.

    line 66

“Common” is measured: kept by at least 6 in 10 of the 142 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

Build

One slice at a time: a screen someone looks at, the rule that decides what happens, and the place the answer is stored.

1. Name the slice

Read everything in project/. If it is empty, run /start first.

Restate what they asked for as one sentence in this shape:

so that [person] can [do thing] and see [result]

If that sentence needs an "and" in the middle, it is two slices. Split it, take the smaller one, and put the rest in project/SLICES.md as planned.

If the slice needs people to sign in and .stack-level says l1, run /level-up first.

Done when: they agree to one sentence that touches a screen, a rule, and a stored record, and everything split off is written into SLICES.md.

2. Ask the design questions

At most three questions, from QUESTIONS.md. One at a time.

Two named options each, with what each means for their business. When there is no real choice, pick the sensible thing and say you picked it.

Done when: three or fewer questions are answered, and each one is appended to project/DECISIONS.md with the date, the question as you asked it, their choice, one line of why, and what it rules out.

3. Place the seam

Two sentences: where this behaviour will live, and what stays out of it. That place is the seam, and putting it well is what makes the next change cheap.

Aim for a deep module: one door into a big room. sendInvoiceReminder(order) is one thing a caller has to learn, hiding formatting, sending, and recording. Five functions the caller has to call in the right order is the same work with the cost pushed onto everyone who uses it.

Then list every file you are about to create or change, by path, before writing any of them.

Done when: one seam is named, and the full list of files is on screen.

4. Build it

Follow docs/recipes/l<n>.md for the level in .stack-level.

Screen, rule, and storage together. A screen with nothing behind it is not a slice.

New tables go through /add-data, never by hand and never through the Supabase dashboard.

Done when: the slice runs start to finish in the browser, the record it created is visible in the Supabase table editor, and pnpm lint, pnpm typecheck, and pnpm build all pass.

5. Hand them the mouse

Walk them through doing the job themselves. Give the address and the steps, then wait.

Watching someone use it is how you find out what you built wrong.

Done when: they confirm they did the action in their own browser and saw the result, and SLICES.md marks this slice built with today's date.

6. Say what changed

One line per file from step 3, in their words, at the level of detail in project/PROFILE.md.

Then name one thing they could safely change and try right now, with the file and the value.

Done when: every file in step 3's list has its line.

When something is broken rather than missing

Steps 1 and 2 change; the rest is the same.

First reproduce it. Have them show you the exact thing that goes wrong, or do it yourself. A bug you cannot reproduce is a bug you cannot fix.

Then find why it happens before changing anything. Say the cause out loud in one sentence. If you cannot, keep looking rather than guessing.

Then continue from step 3.

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.