agentleFS
richkuorichkuo/rk-skills/skills/new-app-pipeline/SKILL.md

new-app-pipeline

Skill50 starsChanged yesterdayMITView on GitHub

Use when the user wants to take a new app from raw idea to running multi-agent implementation — "/new-app-pipeline", "let's build a new app", "run the app pipeline on this idea". Orchestrates the full sequence - idea → PRD → question refinement → GitHub issues with Execution blocks → execution-plan review → milestone pre-flight → milestone workflow — with a user checkpoint between every stage.

The file

We split this skill into the rules it gives an agent

3 rules. About 0 are common, 2 are distinctive, and 1 is very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈2

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 1

    Very specific

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

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Never skip a checkpoint: Every stage boundary stops for the user.

    line 24
  2. Distinctive:

    If the artifacts already exist (a PRD in the repo, issues filed), enter at the first stage whose artifact is missing or stale.

    line 33
  3. Very specific:

    When a milestone already has Execution blocks, run milestoneplan first to check their state before treating stage 5 as finished.

    line 35

≈ “Common” is an estimate: at least 1 in 5 of the 350,495 skill files we read have a rule of the same kind, not the same words. “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

new-app-pipeline

Each stage produces a durable artifact (PR, issues, workflow run), and those artifacts hold the pipeline state.

Stages

#StageSkillArtifactCheckpoint before next stage
1Idea → PRDapp-prdPRD.md on a PRUser iterates on the draft, in bursts
2Resolve questionsprd-questionsUpdated PRD, empty Open QuestionsUser answered every batch
3Review and merge the PRD PRfix-pr-review-loopPRD on mainReview loop to LGTM on the PRD PR, then explicit user go
4Issues + milestonesprd-to-issuesMilestones, complete scoped issues with Execution blocksUser reviews the breakdown table
5Execution planexecution-plan-reviewRevised Execution blocksUser settles the final table
6Show the planmilestoneplanSingle per-issue plan table (complexity, dependencies, models, efforts, plan, first review)User reviews the table (recommended, not required)
7Run a milestonemilestone-workflowWorkflow run → PRs → LGTMsUser approves the run plan (mandatory)

Rules

  • Never skip a checkpoint. Every stage boundary stops for the user.
  • Stages are re-enterable: the user can jump back ("actually keep Drizzle", "12 should be medium") at any point. Apply each revision to the artifact.
  • Stages 6–7 repeat per milestone (v0, then v1, …), chaining workflow invocations where cross-phase dependencies require earlier merges.
  • Stage 6 is read-only and skippable; it never edits an issue.
  • Tech-stack debates during stage 1–2 (framework, ORM, hosting) are settled in chat and recorded in the PRD's Platforms & Technology table.
  • The global CLAUDE.md rules apply throughout, including worktree + PR for every change, attribution footers, and github-issue-format before filing.

Starting mid-pipeline

If the artifacts already exist (a PRD in the repo, issues filed), enter at the first stage whose artifact is missing or stale; never redo a finished stage. Verify from the repo and issues, without asking the user.

When a milestone already has Execution blocks, run milestoneplan first to check their state before treating stage 5 as finished.

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.