agentleFS
Sign inStart free
sturlesesturlese/build-squad/skills/build/SKILL.md

build

Skill0 starsChanged 3 months agoMITView on GitHub

Delivery pipeline from a closed spec — validates the spec mechanically (verifiable acceptance criteria, explicit excluded scope), then runs UX (if user-facing) → developer → tester ∥ auditor → findings loop → documentator, verifying each acceptance criterion from the spec. Use when the user asks to build/implement a spec file, typically one produced by /squad:define.

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 8 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 143 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. Distinctive:

    Context: Read CLAUDE.md/README.md if present.

    line 15
  2. Very specific:

    UX — conditional: If the spec touches user-facing surfaces, spawn ux with the spec.

    line 16
  3. Very specific:

    Document — documentator: Update index.md/docs for touched modules.

    line 20
  4. Very specific:

    Close the loop: Update the spec's frontmatter: status: built, add the date.

    line 21
  5. Very specific:

    Scope never changes mid-build: If implementation reveals the spec is wrong or incomplete, STOP, report exactly what broke the definition, …

    line 25

“Common” is measured: kept by at least 6 in 10 of the 143 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

Squad build

Spec: $ARGUMENTS — a path to a spec file (preferred) or inline spec text.

You are the orchestrator. The spec is the contract: scope was already negotiated when it was written, so this pipeline runs without a scope gate — the human sees the delivery report at the end.

Choreography

  1. Validate the spec — mechanical gate. Read the spec. Refuse to proceed (politely, pointing to /squad:define) if any of these is missing: numbered, individually verifiable acceptance criteria; explicit EXCLUDED scope; a stated problem/objective. Also refuse if it contains unresolved open questions or status: draft — offer to resume /squad:define on it instead.
  2. Context. Read CLAUDE.md/README.md if present; run the project's documented overview command if one exists. Pass the relevant slice to every agent.
  3. UX — conditional. If the spec touches user-facing surfaces, spawn ux with the spec; fold its notes into the developer's instructions. Otherwise skip and say so.
  4. Implement — developer. Spawn developer with the spec verbatim (acceptance criteria word for word), UX notes, and project context. Its preloaded playbooks (semantic-architecture, breaking-change) apply on their own triggers.
  5. Verify — tester ∥ auditor. In parallel: the tester validates EACH acceptance criterion from the spec, one by one, plus the smallest sufficient regression set (sequential test runs unless the project documents parallel-safe suites); the auditor reviews the diff read-only.
  6. Findings loop. Regressions or MEDIUM+/STOP findings go back to developer with evidence and precise instructions. Re-verify what changed. Maximum 2 cycles, then escalate to the user with the current state.
  7. Document — documentator. Update index.md/docs for touched modules.
  8. Close the loop. Update the spec's frontmatter: status: built, add the date. Deliver the report: each acceptance criterion with pass/fail, files changed, test targets run with results, audit verdict and accepted residual findings, docs updated, follow-ups.

Rules

  • Scope never changes mid-build. If implementation reveals the spec is wrong or incomplete, STOP, report exactly what broke the definition, and route back to /squad:define to revise it. Do not improvise scope — that is the whole reason the spec exists.
  • The excluded-scope section is binding: work that drifts into it gets cut, not "included since we're here".
  • Serialize anything that runs tests; parallelize everything else freely.
  • Respect role boundaries: production code only through developer, tests only through tester, the auditor edits nothing.
  • Artifacts and reports in English; address the user in their own language.

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.

Check your setup, free