Basinfy/Basinfy-SaaS-Studio / .agents/skills/saas-setup-stack
saas-setup-stack
UnverifiedConfigure SaaS stack (Golden Stack for founders or custom Next.js/FastAPI/Go/Cloudflare).
| File | Kind | Size |
|---|---|---|
| SKILL.md | skill md | 7.4 KB |
| references/11-upgrade.md | markdown | 4.4 KB |
| references/12-output-summary.md | markdown | 1.8 KB |
| references/2-guided-mode.md | markdown | 1.7 KB |
| references/3-version.md | markdown | 2.0 KB |
| references/4-claude-md-stack.md | markdown | 2.0 KB |
| references/5-technical-preferences.md | markdown | 5.9 KB |
| references/5.5-project-yaml.md | markdown | 1.8 KB |
| references/6-knowledge-gap.md | markdown | 1.7 KB |
| references/7-reference-docs.md | markdown | 5.9 KB |
| references/7.5-scaffold.md | markdown | 2.5 KB |
| references/8-verify.md | markdown | 921 B |
| references/saas-stack-config.md | markdown | 4.5 KB |
SKILL.md
View on GitHub---
name: saas-setup-stack
description: "Configure SaaS stack (Golden Stack for founders or custom Next.js/FastAPI/Go/Cloudflare)."
argument-hint: "[engine] | [engine version] | refresh | upgrade [old-version] [new-version] | no args for guided selection"
user-invocable: true
---
<!-- Generated from .claude/skills by scripts/sync-agent-skills.py. -->
## Running this workflow on this client
Run commands from the project root (use Git Bash on Windows if `bash` points to an unavailable WSL distro). Shared studio files live in `.claude/`; follow `.agents/PORTABLE-RUNTIME.md` and `.claude/docs/config-resolution.md` for client tools, delegation, and approval rules.
# Engine Setup
> **Locale & User Profile**: Match `locale` (`pt-BR` → natural Brazilian Portuguese questions/options, overriding English examples; `en` → English) and `user_profile` (`founder` → plain business language with `(Recomendado)` first, zero tech jargon; `developer` → technical). Keep code/tests in English.
When this skill is invoked:
Run `bash .claude/hooks/yaml-helper.sh resolve_config --keys locale,workflow` and use its output below.
**Tier awareness.** The `workflow` tier resolved above governs which design
artifact this skill expects and the finish path it recommends in §12:
- **`minimal`** — the design artifact is the one-page `design/product-brief.md`
(no PRDs, systems decomposition, or per-system design at this tier).
`/saas-setup-stack` runs *first* in the minimal path, so a missing brief here is
normal, not a gap. The finish path is the 4-step floor.
- **`standard` / `full`** — the design artifact is `design/prd/product-concept.md`
and the finish path is the full pipeline.
If the block did not render (shell preprocessing disabled), assume `minimal` (the default).
## 1. Parse Arguments
Four modes:
- **Full spec**: `/saas-setup-stack nextjs 4.7` — engine and version provided
- **Engine only**: `/saas-setup-stack fastapi` — engine provided, version will be looked up
- **No args**: `/saas-setup-stack` — fully guided mode (engine recommendation + version)
- **Refresh**: `/saas-setup-stack refresh` — update reference docs (see Section 10)
- **Upgrade**: `/saas-setup-stack upgrade [old-version] [new-version]` — migrate to a new engine version (see Section 11)
---
## 2. Guided Mode (No Arguments)
**Read `references/2-guided-mode.md` now and follow it** — this phase's steps are in that file, not here. Read it again if the conversation was compacted or resumed during this phase.
## 3. Look Up Current Version
**Read `references/3-version.md` now and follow it** — this phase's steps are in that file, not here. Read it again if the conversation was compacted or resumed during this phase.
## 4. Update CLAUDE.md Technology Stack
**Read `references/4-claude-md-stack.md` now and follow it** — this phase's steps are in that file, not here. Read it again if the conversation was compacted or resumed during this phase.
## 5. Populate Technical Preferences
**Read `references/5-technical-preferences.md` now and follow it** — this phase's steps are in that file, not here. Read it again if the conversation was compacted or resumed during this phase.
## 5.5 Populate `project.yaml` (Primary Config Store)
**Read `references/5.5-project-yaml.md` now and follow it** — this phase's steps are in that file, not here. Read it again if the conversation was compacted or resumed during this phase.
## 6. Determine Knowledge Gap
**Read `references/6-knowledge-gap.md` now and follow it** — this phase's steps are in that file, not here. Read it again if the conversation was compacted or resumed during this phase.
## 7. Populate Engine Reference Docs
**Read `references/7-reference-docs.md` now and follow it** — this phase's steps are in that file, not here. Read it again if the conversation was compacted or resumed during this phase.
## 7.5 Scaffold the Engine Project
**Read `references/7.5-scaffold.md` now and follow it** — this phase's steps are in that file, not here. Read it again if the conversation was compacted or resumed during this phase.
## 8. Verify the CLAUDE.md Import
**Read `references/8-verify.md` now and follow it** — this phase's steps are in that file, not here. Read it again if the conversation was compacted or resumed during this phase.
## 9. Update Agent Instructions
Ask: "May I add a Version Awareness section to the stack specialist agent files?" before making any edits.
For the chosen engine's specialist agents, verify they have a
"Version Awareness" section. If not, add one following the pattern in
the existing Next.js specialist agents.
The section should instruct the agent to:
1. Read `docs/engine-reference/<engine>/VERSION.md`
2. Check deprecated APIs before suggesting code
3. Check breaking changes for relevant version transitions
4. Use WebSearch to verify uncertain APIs
---
## 10. Refresh Subcommand
If invoked as `/saas-setup-stack refresh`:
1. Read the existing `docs/engine-reference/<engine>/VERSION.md` to get
the current engine and version
2. Use WebSearch to check for:
- New engine releases since last verification
- Updated migration guides
- Newly deprecated APIs
3. Update all reference docs with new findings
4. Update "Last verified" dates on all modified files
5. Report what changed
---
## 11. Upgrade Subcommand
**Read `references/11-upgrade.md` now and follow it** — this phase's steps are in that file, not here. Read it again if the conversation was compacted or resumed during this phase.
## 12. Output Summary
**Read `references/12-output-summary.md` now and follow it** — this phase's steps are in that file, not here. Read it again if the conversation was compacted or resumed during this phase.
## Guardrails
- NEVER guess an engine version — always verify via WebSearch or user confirmation
- `project.yaml` is the primary config store (v1.1). Always dual-write engine
config to BOTH `project.yaml` (primary) and `technical-preferences.md` (legacy
mirror). If the two ever diverge, `project.yaml` is authoritative.
- NEVER overwrite existing reference docs without asking — append or update
- If reference docs already exist for a different engine, ask before replacing
- Always show the user what you're about to change before making CLAUDE.md edits
- If WebSearch returns ambiguous results, show the user and let them decide
- When the user chose **TypeScript**: copy the TypeScript CLAUDE.md template from **A1** in `references/nextjs-language-config.md` exactly. NEVER add "C++ via GDExtension" to the Language field. TypeScript projects may use GDExtension, but it is not a primary project language. The `prisma-drizzle-specialist` in the routing table is available for when native extensions are needed — it does not make C++ a project language.
---
## Appendix A — Next.js Language Configuration
Moved out of this file so it costs nothing on non-Next.js runs.
**When the chosen engine is Next.js, read**
`references/nextjs-language-config.md`
and use the subsection for the chosen language:
- **A1** — CLAUDE.md Technology Stack templates (TypeScript / C# / Both)
- **A2** — naming conventions
- **A3** — stack specialist routing and file-extension tables
**Load discipline.** On any engine other than Next.js, **never load it** — nothing in Sections 4, 5 or 5.5 needs it, and reading it anyway spends the tokens the split exists to save. On Next.js, read it once when you first reach Section 4 and keep using it for Sections 5 and 5.5; do not re-read it at each reference.
Related skills
| Skill | Stars | Updated | Works with | Status | Install |
|---|---|---|---|---|---|
| slack-gif-creatoranthropics/skillsKnowledge and utilities for creating animated GIFs optimized for Slack. Provides constraints, validation tools, and animation concepts. Use when users request animated GIFs for Slack like "make me a GIF of X doing Y for Slack." | Stars: 198k | Updated | Claude CodeCodex | Verified | Install |
| ponytailDietrichGebert/ponytailLazy senior dev mode for any coding task: the smallest change that fully solves it, and a reply a busy human understands in one read. | Stars: 194k | Updated | Claude CodeCodex | Verified | Install |
| ponytail-debtDietrichGebert/ponytailHarvest every shortcut: comment into one debt ledger, so deferrals get tracked instead of forgotten. One-shot report. | Stars: 194k | Updated | Claude CodeCodex | Verified | Install |
| ponytail-debtDietrichGebert/ponytailList every `shortcut:` comment (and older `ponytail:` ones) as a debt ledger. One-shot report, changes nothing. Use for "ponytail debt", "what did ponytail defer", "list the shortcuts", /ponytail-debt. | Stars: 194k | Updated | Claude CodeCodex | Verified | Install |