Skip to content
build logo

build — implement spec

build

Plan-then-execute implementation against SPEC.md. Native single-thread loop, no sub-agents. On test or build failure, auto-invokes the backprop skill before retrying — a failed verification always considers whether a new §V invariant would prevent recurrence. Triggers when the user asks to build, implement, execute the spec, or tackle a specific §T task (build §T.3, build --next, implement next task, run the build). Expects SPEC.md to exist; if not, defers to the spec skill.

SKILL.md

Full skill instructions

build — implement spec

Single-thread native plan→execute. You are main Claude. No swarm.

LOAD

  1. Read SPEC.md. If missing → tell user to invoke the spec skill first. Stop.
  2. Read FORMAT.md once if not loaded.
  3. Read §R if present — external facts the build must honor, ⊥ re-derive or contradict.
  4. Parse invocation args:
    • §T.n → that task only
    • --next → lowest-numbered row with status . or ~
    • --all or empty → every . row in §T order

High blast radius (shared module, auth, data, money, public §I)? Run /​review first. Trivial & reversible? Skip planning ceremony, just do step EXECUTE.

PLAN

Native plan mode — you delegate to it, you do not reinvent task breakdown. For chosen task(s):

  1. Cite every §V invariant that applies. Plan must respect all.
  2. Cite every §I interface touched. Plan must preserve shape.
  3. List files to create / edit.
  4. Verification contract — name the EXACT test(s) / acceptance criteria that prove each §V touched. Which test, not "add tests". "Do TDD" alone backfires; the spec says what to check. Each §V touched → a named test that fails first.
  5. Name verification command (test, build, lint) — this is the external oracle. Green = done; ⊥ "looks done".

Show plan. Wait for user OK unless auto mode.

EXECUTE

Per task in order:

  1. Flip §T.n status cell . → ~. Just write to SPEC.md.
  2. Edit code per plan.
  3. Run verification command.
  4. Pass → flip ~ → x. Next task.
  5. Fail → invoke backprop skill. Do NOT retry blindly.

FAIL → BACKPROP

On test/​build failure:

  1. Read failure output.
  2. Ask: is failure (a) my code bug, (b) spec wrong, or (c) unspecified edge case?
  3. If (a) → fix code, re-run. No spec change.
  4. If (b) or (c) → invoke spec skill with bug: <cause> first, let it update §V and §B, then resume build against updated spec.

Rule: never silently fix root-cause without considering backprop. §B is the memory that stops recurrence.

WRITE POLICY

  • Only flip §T status. No other SPEC.md edits from build.
  • Other spec edits → invoke spec skill.
  • Commit after each §T completes. Message: T<n>: <goal line> + §V cites.

VERIFICATION

Task x only if:

  • Verification command (the oracle) exits 0.
  • Every §V touched has its named test from the verification contract, and it passes.
  • No §V invariant regressed (run full test suite at end).

NON-GOALS

  • No sub-agents. No parallel workers. Main thread only.
  • No progress dashboards. cat SPEC.md | grep §T is the dashboard.
  • No speculative work beyond chosen task scope.

More DevOps & CI/CD skills

Project scaffolding, deployment configuration, and CI/CD setup for Google ADK agents.

6K 472.6K
View

Set up tracing, logging, and monitoring for deployed ADK agents across Cloud Trace, BigQuery, and third-party platforms.

6K 472.6K
View

Enterprise Azure infrastructure architect generating Bicep or Terraform from workload descriptions.

1.5K 454.3K
View
azure-kubernetes logo
DevOps & CI/CD

azure-kubernetes

Plan and configure production-ready Azure Kubernetes Service clusters with Day-0 and Day-1 best practices.

1.5K 447.1K
View

Raw mechanical interfaces fusing Swiss typographic print with military terminal aesthetics. Rigid grids, extreme type scale contrast, utilitarian color, analog degradation effects. For data-heavy dashboards, portfolios, or editorial sites that need to feel like declassified blueprints.

92.7K 354.9K
View
just-scrape logo
DevOps & CI/CD

just-scrape

Web search, scraping, extraction, crawling, and monitoring via ScrapeGraph AI CLI.

69 245K
View

Skill for working with Firebase Hosting (Classic). Use this when you want to deploy static web apps, Single Page Apps (SPAs), or simple microservices. Do NOT use for Firebase App Hosting.

462 159.7K
View

Deploy and manage web apps with Firebase App Hosting. Use this skill when deploying Next.js/Angular apps with backends.

462 159.1K
View
deploy-to-vercel logo
DevOps & CI/CD

deploy-to-vercel

Deploy applications and websites to Vercel. Use when the user requests deployment actions like "deploy my app", "deploy and give me the link", "push this live", or "create a preview deployment".

31.9K 146.6K
View
programmatic-seo logo
DevOps & CI/CD

programmatic-seo

Build SEO-optimized pages at scale using templates, data, and proven playbook patterns.

53.3K 140.1K
View

Design and build isolated, reusable Convex backend components with clear boundaries and app-facing wrappers.

63 123.5K
View

Deploy and manage projects on Vercel using token-based authentication. Use when working with Vercel CLI using access tokens rather than interactive login — e.g. "deploy to vercel", "set up vercel", "add environment variables to vercel".

31.9K 116.1K
View

Coding & apps AI tools

Opus Clip logo
Coding & apps

Opus Clip

Opus.ai: Revolutionize Your Web Experience

Free
View
Imagica logo
Coding & apps

Imagica

Build a no-code AI app in minutes.

Freemium
View
E
Coding & apps

Emergent.sh

An IDE for code migration from legacy to modern frameworks through coding agents.

Freemium
View
Wonder Dynamics logo
Coding & apps

Wonder Dynamics

Automate CGI animation in live-action scenes

Paid
View
M
Coding & apps

Mixo

Launch a website in seconds with AI.

Paid
View
AI Code Convert logo
Coding & apps

AI Code Convert

Streamline Your Coding Experience with AI Code Helper

Free
View