squid-scaffold
Bootstrap a new repo or component from the opinionated spec library (mode=create), or audit an existing scaffolded repo for drift against the scaffold rules (mode=evaluate, report-only).
iusztinpaul · 已有 AI 审核记录
安装与使用
运行命令前先阅读来源与依赖说明。复制命令不会自动安装或执行。
npx skills add iusztinpaul/squid --skill squid-scaffold技能说明
name: squid-scaffold description: >- Bootstrap a new repo or component from the opinionated spec library (mode=create), or audit an existing scaffolded repo for drift against the scaffold rules (mode=evaluate, report-only). disable-model-invocation: true argument-hint: "[mode=create|evaluate] [project description | target repo path]"
Scaffold
Interactive bootstrap for a new repo (or a new component in an existing one): read only the specs under specs/ that apply, distil them into a tailored AGENTS.md, lay down an empty skeleton, hand back.
Modes
$ARGUMENTS may lead with mode=create (default) or mode=evaluate:
mode=create(default) — bootstrap a repo / component. The flow in "## Flow" below.mode=evaluate— audit an existing scaffolded repo for drift (report-only). Formode=evaluate, readevaluate.mdand follow E1–E4 instead of the Flow.
Every rule both modes honour lives in rules.md — the single source of truth; mode=create follows every P# + I# while composing, mode=evaluate audits the I#. Do not restate any rule in this file.
When to use
- Bootstrapping a brand-new repo.
- Adding a new runtime component (backend / frontend-web / frontend-tui) to an existing scaffolded repo.
- Re-generating the root
AGENTS.mdafter a major stack change (e.g. swapping Vue for React).
When NOT to use
- Authoring application source or business logic (
P1). - Adjusting opinions inside an existing project — edit the generated
AGENTS.mddirectly. - Non-polyglot single-package projects where the full machinery is overkill. (You can still use a single spec as reference, but skip the scaffold flow.)
Flow
1. Gather requirements
Use AskUserQuestion to collect answers. Consolidate where possible — one or two prompts, not a twelve-step interview. Minimum set:
- Project identity — name, short description, license (MIT / Apache-2.0 / proprietary). Name becomes the repo / root AGENTS.md title; slug is derived.
- Layout — monorepo (
packages/<c>/tree) or standalone single-package? - Components (multi-select; at least one required):
backend— Python service / pipeline / libraryfrontend-web— TypeScript browser SPAfrontend-tui— Go terminal UI
- Backend variant (if backend chosen):
fastapi-service/fastmcp-server/cli-tool-python/library-only. - Frontend-web framework (if frontend-web chosen):
react/vue/svelte/vanilla. - Frontend-tui framework (if frontend-tui chosen):
bubbletea(default) /tview. - Shared OpenAPI contracts (only if backend + ≥1 frontend): yes / no.
- Infra (multi-select):
docker,github-actions,pre-commit-hooks. - Agent team + tracker? yes (recommended) / no. Also: file-based tracker or GitHub Issues?
- Process & documentation (multi-select, optional):
adr(Architecture Decision Records underdocs/adr/),ubiquitous-language(project glossary atdocs/glossary.md). Recommendadrfor any project expected to live > 6 months; recommendubiquitous-languagefor backend services with named domain entities. - External services (optional, multi-select — skip any category that doesn't apply). Each selection pulls a
specs/<category>-<choice>.mdstub and emits a one-line bullet into the generated AGENTS.md, wrapped perI9:
- Datastore:
mongodb/postgresql/redis/sqlite/other/none - Orchestrator:
prefect/dagster/temporal/other/none - Observability & evals:
opik/opentelemetry/sentry/other/none - LLM API:
anthropic/openai/gemini/other/none - Embedding API:
voyageai/openai/sentence-transformers/other/none - Model serving:
modal/replicate/other/none - Web scraping:
firecrawl/playwright/requests-bs4/other/none
Ask this as ONE consolidated question: "Which external services will you use? (deselect anything you don't need)." none skips the category entirely — no stub read, no bullet emitted. other keeps an AGENT: fill in placeholder so the SWE can document the real choice on first use.
- Reference docs (
llms.txt) — which tools / frameworks / services publish anllms.txt, and each one's index URL (e.g. Pydantic AI →https://pydantic.dev/docs/ai/llms.txt)? Governed byP5; fully skippable.
Before proceeding to step 2, echo the picked configuration back to the user in a two-line summary and confirm.
2. Select specs
Always include:
monorepo-layout.md— unless the user chose standalone single-package.makefile-delegator.md— unless standalone.
Conditionally include (from answers):
| Answer | Specs to read |
|---|---|
backend (any variant) | python-backend.md + uv-python.md + pyproject.md + ruff-python.md |
backend = fastapi-service | + fastapi-service.md |
backend = fastmcp-server | + fastmcp-server.md |
backend = cli-tool-python | + cli-tool-python.md |
frontend-web | typescript-frontend.md + the chosen framework spec (react-app.md / vue-app.md / svelte-app.md / vanilla-ts-app.md) |
frontend-tui | go-tui.md (already covers both bubbletea and tview) |
| shared OpenAPI contracts | openapi-contracts.md |
| docker | docker.md |
| github-actions | github-actions.md |
| pre-commit-hooks | pre-commit-hooks.md |
| agent team + |