squid-architecture-rev…
Periodic architectural sweep — reads existing ADRs, maps modules/dependencies/layering, and reports up to 10 prioritised findings…
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).
$ npx -y skills add iusztinpaul/squid --skill squid-scaffold --agent claude-codeHow it fires
How this skill gets triggered: by you, by Claude, or both.
/squid-scaffoldContext preview
The summary Claude sees to decide when to auto-load this skill.
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).
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]"
Interactive bootstrap for a new repo (or a new component in an existing one): read only the specs under [`specs/`](specs/) that apply, distil them into a tailored `AGENTS.md`, lay down an empty skeleton, hand back.
`$ARGUMENTS` may lead with `mode=create` (default) or `mode=evaluate`:
Every rule both modes honour lives in [`rules.md`](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.
Use `AskUserQuestion` to collect answers. Consolidate where possible — one or two prompts, not a twelve-step interview. Minimum set:
1. **Project identity** — name, short description, license (MIT / Apache-2.0 / proprietary). Name becomes the repo / root AGENTS.md title; slug is derived. 2. **Layout** — monorepo (`packages/<c>/` tree) or standalone single-package? 3. **Components** (multi-select; at least one required):
4. **Backend variant** (if backend chosen): `fastapi-service` / `fastmcp-server` / `cli-tool-python` / `library-only`. 5. **Frontend-web framework** (if frontend-web chosen): `react` / `vue` / `svelte` / `vanilla`. 6. **Frontend-tui framework** (if frontend-tui chosen): `bubbletea` (default) / `tview`. 7. **Shared OpenAPI contracts** (only if backend + ≥1 frontend): yes / no. 8. **Infra** (multi-select): `docker`, `github-actions`, `pre-commit-hooks`. 9. **Agent team + tracker?** yes (recommended) / no. Also: file-based tracker or GitHub Issues? 10. **Process & documentation** (multi-select, optional): `adr` (Architecture Decision Records under `docs/adr/`), `ubiquitous-language` (project glossary at `docs/glossary.md`). Recommend `adr` for any project expected to live > 6 months; recommend `ubiquitous-language` for backend services with named domain entities. 11. **External services** (optional, multi-select — skip any category that doesn't apply). Each selection pulls a `specs/<category>-<choice>.md` stub and emits a one-line bullet into the generated AGENTS.md, wrapped per `I9`:
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.
12. **Reference docs (`llms.txt`)** — which tools / frameworks / services publish an `llms.txt`, and each one's index URL (e.g. Pydantic AI → `https://pydantic.dev/docs/ai/llms.txt`)? Governed by `P5`; fully skippable.
Before proceeding to step 2, echo the picked configuration back to the user in a two-line summary and confirm.
Always include:
Conditionally include (from answers):
| Answer | Specs to read | |---|---| | `backend` (any variant) | [`python-backend.md`](specs/python-backend.md) + [`uv-python.md`](specs/uv-python.md) + [`pyproject.md`](specs/pyproject.md) + [`ruff-python.md`](specs/ruff-python.md) | | backend = `fastapi-service` | + [`fastapi-service.md`](specs/fastapi-service.md) | | backend = `fastmcp-server` | + [`fastmcp-server.md`](specs/fastmcp-server.md) | | backend = `cli-tool-python` | + [`cli-tool-python.md`](specs/cli-tool-python.md) | | `frontend-web` | [`typescript-frontend.md`](specs/typescript-frontend.md) + the chosen framework spec ([`react-app.md`](specs/react-app.md) / [`vue-app.md`](specs/vue-app.md) / [`svelte-app.md`](specs/svelte-app.md) / [`vanilla-ts-app.md`](specs/vanilla-ts-app.md)) | | `frontend-tui` | [`go-tui.md`](specs/go-tui.md) (already covers both bubbletea and tview) | | shared OpenAPI contracts | [`openapi-contracts.md`](specs/openapi-contracts.md) | | docker | [`docker.md`](specs/docker.md) | | github-actions | [`github-actions.md`](specs/github-actions.md) | | pre-commit-hooks | [`pre-commit-hooks.md`](specs/pre-commit-hooks.md) | | agent team +
Periodic architectural sweep — reads existing ADRs, maps modules/dependencies/layering, and reports up to 10 prioritised findings…
Strip redundancy from prose — docs, READMEs, code comments, docstrings — keeping behaviour identical.
Shrink an agent harness (.agents/ skills + resources) to the minimum tokens that keep the exact same logic. Never touches…
Shrink the memory files sessions load — the root AGENTS.md plus every nested AGENTS.md / CLAUDE.md — to the minimum words that…
Interview the user relentlessly about a plan or design. Use when the user wants to stress-test a plan before building, or uses…
Run the full agent-team pipeline end-to-end for one feature whose Tasks Plan is already approved by /squid-plan, handing the…