agentleFS
cwhited26cwhited26/pocket-agent-starter-skills/skills/operations/project-scaffolding/SKILL.md

project-scaffolding

Skill0 starsChanged 4 months agoMITView on GitHub

Turn a vague goal into milestones, then milestones into concrete tasks, so a big ask becomes a sequence someone can actually run. The owner names a goal that's too big to act on directly — \"launch the new service,\" \"clean up the books.\" Use before any of it gets dispatched as work.

10 other projects use a version of this.

Adopted by

Most recently taken up by

Used with

Projects with it also use documentation-site and kubernetes.

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.
  • KMaruthi2002Skill

    documentation-site

    Plan, build and maintain a documentation website for a product, API, library, platform or internal system: information architecture (tutorials, how-to guides, reference, explanation), choosing a static site generator or hosted docs platform, navigation and search, versioning for multiple releases, generated API reference, code samples that are tested and actually run, docs-as-code workflow with review, previews, link checking and CI, plus accessibility, internationalisation and analytics. Use when someone asks to create a docs site, developer portal, knowledge base, handbook site, migrate docs to a new generator, add versioning or search to docs, or fix docs that users cannot navigate or that have drifted from the product.

    Also in 3 projects that use this

  • mjunaidcaSkill

    kubernetes

    Production-grade Kubernetes manifests and debugging for containerized applications. This skill should be used when users ask to deploy to Kubernetes, create K8s manifests, containerize for K8s, set up Deployments/Services/Jobs/StatefulSets/CronJobs, create namespaces with resource quotas, set up multi-team isolation, configure ResourceQuota/ LimitRange, secure with RBAC (ServiceAccount, Role, RoleBinding), configure init containers (model download, db wait, migrations), set up sidecars (logging, metrics), or debug pods (CrashLoopBackOff, logs, exec, describe, events). Auto-detects from Dockerfile/code, generates hardened manifests with educational comments. CKAD-aligned.

    Also in 3 projects that use this

The file

Files
SKILL.md

Break a Goal Into Steps

A goal you can't start is a goal stated too big. Break it into a few milestones — the real phases — then break each milestone into tasks small enough to do. The scaffold is what makes it run.

The technique

  • Restate the goal as a finished outcome, so "done" is unambiguous before you plan a single step.
  • Split into milestones — 3 to 5 real phases, each a chunk that ends in something you can point at.
  • Under each milestone, list tasks small enough to actually do — a task is one clear action, not another mini-project.
  • Order them by dependency: what has to finish before the next thing can start. Surface what can run in parallel.
  • Name the first task precisely. A plan that doesn't make the next move obvious is a plan nobody starts.

Do this, not that

Do: "Goal: launch the maintenance plan. Milestone 1: define the offer (price it, write what's included, set the terms). Milestone 2: build it (Stripe product, sign-up page, contract). Milestone 3: sell it (email the 40 past customers, add it to quotes). First task: write the three-tier price list — start there."

Don't: Take "launch the maintenance plan" and either freeze because it's too big, or jump straight to building a sign-up page before the offer or price even exists.

Why this works

Big goals stall because there's no obvious first move — the whole thing has to be held in your head at once. Scaffolding externalizes the structure: milestones make the size manageable, tasks make each piece doable, and ordering by dependency stops you from building the sign-up page before you've decided what you're selling. The named first task is what turns a plan into momentum.

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.