Use when the user wants the full package on a repo, says run my project workflow, project check-in, or is overwhelmed opening an old or new folder. Runs the project onboarding checklist—explain-new-project, project-worth-my-time, and project-catch-up—in order or on demand.
The English summary is being prepared. Showing the original description.
See how to installReview the instructions the agent will receive before you install.
One ask → the right steps in order → three files on disk + a short chat summary.
| User means… | Run |
|---|---|
| New folder / “what is this?” / guide only | Step 1 only → explain-new-project |
| “Worth my time?” / build vs buy | Step 2 → project-worth-my-time (read PROJECT_GUIDE.md first if it exists) |
| “I’m back after a while” / what’s new | Step 3 → project-catch-up |
| “Full workflow” / “check-in” / “do everything” | Steps 1 → 2 → 3 in order (unless skip rules below) |
| Unclear | Default: full (1 → 2 → 3) |
Same audience as the other skills: self-taught, plain language, Learn: for jargon.
| Step | Skill | File |
|---|---|---|
| 1 | explain-new-project | PROJECT_GUIDE.md |
| 2 | project-worth-my-time | PROJECT_VERDICT.md |
| 3 | project-catch-up | PROJECT_CATCH_UP.md |
PROJECT_*.md files already exist—report in chat, then follow skip rules or user request.For each step you run: read that skill’s SKILL.md and follow it completely (do not shorten sub-skills).
user-pieces: get_user_persona, ask_pieces_ltm) when available.Do not ask permission to save files—sub-skills always save.
| User says | Skip |
|---|---|
| guide only / step 1 only | 2 and 3 |
| no verdict / no worth | 2 |
| no catch-up | 3 |
| verdict only | 1 if PROJECT_GUIDE.md exists and is usable; else run 1 first |
| catch-up only | 1 if guide missing; else skip 1 and 2 |
| File already exists | Default |
|---|---|
| All three fresh enough | Ask once: Re-run all three or only what’s missing? If user said full workflow, re-run all (overwrite). |
| User said full workflow | Overwrite all three |
Use this checklist in the reply:
Done:
- [ ] PROJECT_GUIDE.md — paste "In one minute" + "How you run it"
- [ ] PROJECT_VERDICT.md — paste Quick verdict + What I'd do (if ran step 2)
- [ ] PROJECT_CATCH_UP.md — paste Headline + Do these first (if ran step 3)
Files saved at: [project root path]
If a step was skipped, say which and why.
| Need | For |
|---|---|
| Write access to project root | All steps |
PiecesOS + the pieces MCP server configured in your agent | Step 2 (ok to skip Pieces if down—say so) |
| Web search | Step 3 |
pieces or user-pieces). Use whichever name your coding agent exposes; the flow is identical.No reviews yet. Tell others what you thought.
No login needed. Share how it worked for you, ask a question, or note where it did not run.
No comments yet. Be the first to write one.
Use when creating a new project folder, starter pack, app scaffold, or agent-ready workspace — AGENTS.md, README, TASKS, DECISIONS, PROMPTS, an idempotent bootstrap script, and starter-pack modes.
The English summary is being prepared. Showing the original description.
Use when designing or implementing states for AI agent tasks, background jobs, local model runs, queues, and notifications — one shared set of states, only legal transitions, and a recovery path out of every failure.
The English summary is being prepared. Showing the original description.
Use when exposing app features to App Intents, Shortcuts, Siri, Spotlight, widgets, controls, or system actions — small safe AppIntents, AppShortcutsProvider, AppEnum/AppEntity, parameters, and open-vs-background behavior.
The English summary is being prepared. Showing the original description.
Use when designing, reviewing, or implementing a command-palette / ⌘K layer for an Apple-platform app — keyboard-first global search, ranked and grouped results, native floating panel, and protected destructive commands.
The English summary is being prepared. Showing the original description.
Use when designing or implementing empty, first-run, no-result, offline, error, or waiting states in Apple-platform apps — every empty state explains what is missing, why it matters, and what to do next.
The English summary is being prepared. Showing the original description.
Use when designing or implementing feedback, status, progress, alerts, errors, success states, and live activity indicators in Apple-platform apps — inline status, banners, alerts, notifications, and loading states.
The English summary is being prepared. Showing the original description.