Prospec Quickstart

---
name: prospec-quickstart
description: "Quickstart Onboarding Finisher - localize skill triggers, re-sync agent config, prepare the knowledge scan, and chain into knowledge generation — runs once after `prospec quickstart`, not a per-session step. Triggers: quickstart, onboard, bootstrap, get started, 快速開始, 初始化, 上手, 開始使用"
---
<!-- Generated by `prospec agent sync`. Do not edit — this file is regenerated on every sync. -->

# Prospec Quickstart Skill

## Activation

When triggered, briefly describe:
- That `prospec quickstart` has scaffolded the project and you'll finish onboarding
- You'll localize skill triggers to the configured language (when non-English), re-sync agent config, prepare the knowledge scan, then hand off to knowledge generation
- This is a one-time onboarding flow — it is re-runnable and self-terminating

## CLI Prerequisite (required)

> The prospec CLI is a required file for this skill — its deterministic steps call `prospec`
> commands. Probe BEFORE any other step; there is no manual fallback.

1. Run `prospec --version` (Bash).
2. **Command not found / not executable** → STOP. Ask the user to install the prospec standalone
   executable — the one-click installer script from the project README (macOS/Linux `install.sh`,
   Windows `install.ps1`) or a release binary from GitHub Releases; prospec is NOT published to
   npm. Then re-run this skill.
3. **Version older than 2.3.0** → STOP. Report the installed vs required version
   and ask the user to upgrade, then re-run this skill.

Hand-executing a CLI-owned mutation is NEVER the fallback — that re-introduces the
nondeterministic serialization this contract exists to remove.

## Startup Loading

1. [DYNAMIC] Read `.prospec.yaml` — `artifact_language` and `skill_triggers` decide whether native-language trigger localization runs

## Core Workflow

> This skill shells out to the `prospec` CLI (Bash) throughout. The CLI probe is the shared
> CLI Prerequisite above.

### Step 1: Localize Skill Triggers (non-English only, fill-missing)

Read `.prospec.yaml`. When `artifact_language` is not English, localize the skills that have
**no `skill_triggers` entry yet** (the exact gap `prospec agent sync` names in its hint). This covers
both a fresh project (all skills missing) and a project that just gained new skills (only the new ones
missing) — so you never delete `.prospec.yaml` to re-localize:

1. Run `prospec agent triggers` (Bash) to get a ready-to-translate scaffold with two blocks — `skill_triggers` (invocation words) and `skill_exclusions` (short phrases naming what a skill is NOT for) — listing only the skills still missing an entry in each, each with its English baseline sourced from the CLI (authoritative; never grep a deployed SKILL.md, whose frontmatter already merges custom words); translate both blocks and write both back with `--write`
2. Translate each scaffold value into the `artifact_language` — leave skills that already have an entry untouched (translation is this skill's judgment step)
3. **Show the proposed translations to the user and wait for confirmation** before writing anything
4. On confirmation, save the translated scaffold to a temp file and run `prospec agent triggers --write <file>` (Bash) — the CLI inserts only the missing keys (comment- and order-preserving), validates the result BEFORE writing, and never overwrites an existing entry

Skip this step entirely when the language is English or every skill already has a `skill_triggers`
entry — never overwrite curated triggers.

### Step 2: Re-sync Agent Config

Run `prospec agent sync` (Bash) so the localized triggers render into each SKILL.md
frontmatter and the entry config. Skip only when Step 1 made no change.

### Step 3: Prepare the Knowledge Scan

Run `prospec knowledge init` (Bash) to (re)generate `raw-scan.md` and the knowledge
scaffolding. It always overwrites `raw-scan.md`, so this is safe to re-run and keeps the
scan fresh for the next step.

### Step 4: Generate AI Knowledge

Chain directly into the `prospec-knowledge-generate` workflow — read `raw-scan.md`,
decide module boundaries, and write the module READMEs and `prospec/index.md`. Do NOT inline a
copy of that workflow here; hand off to it so large repositories get their own context
budget.

## Output Contract

> After running, self-assess and emit a concise Output Summary. Every Success Criterion must be objectively checkable (file existence / grep / test result / count) — no subjective adjectives.

### Success Criteria
- [ ] `.prospec.yaml` exists and parses as valid YAML
- [ ] when non-English, `skill_triggers` is populated (or the user declined)
- [ ] `raw-scan.md` exists after `prospec knowledge init`
- [ ] the `prospec-knowledge-generate` workflow was entered

### Failure Conditions
- wrote malformed `skill_triggers` to `.prospec.yaml`
- proceeded silently when the `prospec` CLI was unavailable

### Output Summary
Emit one line: `Met N/M | Unmet: <items> | Overall: PASS|WARN|FAIL | Next: <one-line>`

## NEVER

- **NEVER** proceed silently when the `prospec` CLI is unavailable — stop and tell the user to install prospec (they are adopting it for this project), then re-run
- **NEVER** overwrite an existing `skill_triggers` entry — localize only the skills missing an entry (fill-missing)
- **NEVER** hand-edit `.prospec.yaml` for triggers — `prospec agent triggers --write` owns the fill-missing insertion and validates before writing
- **NEVER** inline the `prospec-knowledge-generate` workflow — chain to it so large repos get a fresh context budget
- **NEVER** translate triggers without showing the user the proposed words first

## Error Handling

| Scenario | Action |
|----------|--------|
| `prospec` CLI unavailable | Stop; point the user at the CLI Prerequisite's install guidance (installer script or GitHub Releases binary — prospec is not on npm), then re-run quickstart — do not proceed silently |
| `prospec agent sync` reports no configured agent | Stop and instruct the user to re-run `prospec init` or add an agent to `.prospec.yaml` |
| `prospec agent triggers --write` rejects the scaffold | Nothing was written (the CLI validates first) — fix the reported entry (unknown skill / empty words) and re-run |
| `raw-scan.md` still missing after `knowledge init` | Report the failure; do not fabricate knowledge |