@heihei0299/matt-skills 2.1.13 → 3.0.1

package/template/.agents/skills/improve-codebase-architecture/SKILL.md

@@ -1,71 +0,0 @@
----
-name: improve-codebase-architecture
-description: Scan a codebase for deepening opportunities, present them as a visual HTML report, then grill through whichever one you pick.
-disable-model-invocation: true
----
-
-# Improve Codebase Architecture
-
-Surface architectural friction and propose **deepening opportunities**: refactors that turn shallow modules into deep ones. The aim is testability and AI-navigability.
-
-This command is _informed_ by the project's domain model and built on a shared design vocabulary:
-
-- Call the Skill tool with "codebase-design" for the architecture vocabulary (**module**, **interface**, **depth**, **seam**, **adapter**, **leverage**, **locality**) and its principles (the deletion test, "the interface is the test surface", "one adapter = hypothetical seam, two = real"). Use these terms exactly in every suggestion, and don't drift into "component," "service," "API," or "boundary."
-- The domain language in `CONTEXT.md` gives names to good seams; ADRs in `docs/adr/` record decisions this command should not re-litigate.
-
-## Process
-
-### 1. Explore
-
-**Scope before you scan: YAGNI.** Deepening a module pays off by making future changes to it easier, so put extra weight on the parts of the codebase that have recently changed. Decide *where* to look before you look:
-
-- If the user named a direction (a module, a subsystem, a pain point), take it, and skip the inference below.
-- Otherwise, walk back a good stretch of the commit history (`git log --oneline`) to find the codebase's hot spots, the files and areas that keep coming up, and let those paths pull your attention first. If the changes are scattered with no clear hot spot, widen the net.
-
-Read the project's domain glossary (`CONTEXT.md`) and any ADRs in the area you're touching first.
-
-Then spawn a sub-agent to walk the codebase. Don't follow rigid heuristics; explore organically and note where you experience friction:
-
-- Where does understanding one concept require bouncing between many small modules?
-- Where are modules **shallow**, with an interface nearly as complex as the implementation?
-- Where have pure functions been extracted just for testability, but the real bugs hide in how they're called (no **locality**)?
-- Where do tightly-coupled modules leak across their seams?
-- Which parts of the codebase are untested, or hard to test through their current interface?
-
-Apply the **deletion test** to anything you suspect is shallow: would deleting it concentrate complexity, or just move it? A "yes, concentrates" is the signal you want.
-
-### 2. Present candidates as an HTML report
-
-Write a self-contained HTML file to the OS temp directory so nothing lands in the repo. Resolve the temp dir from `$TMPDIR`, falling back to `/tmp` (or `%TEMP%` on Windows), and write to `<tmpdir>/architecture-review-<timestamp>.html` so each run gets a fresh file. Open it for the user (`xdg-open <path>` on Linux, `open <path>` on macOS, `start <path>` on Windows) and tell them the absolute path.
-
-The report uses **Tailwind via CDN** for layout and styling, and **Mermaid via CDN** for diagrams where a graph/flow/sequence reliably communicates the structure. Mix Mermaid with hand-crafted CSS/SVG visuals: use Mermaid when relationships are graph-shaped (call graphs, dependencies, sequences), and hand-built divs/SVG when you want something more editorial (mass diagrams, cross-sections, collapse animations). Each candidate gets a **before/after visualisation**. Be visual.
-
-For each candidate, render a card with:
-
-- **Files**: which files/modules are involved
-- **Problem**: why the current architecture is causing friction
-- **Solution**: plain English description of what would change
-- **Benefits**: explained in terms of locality and leverage, and how tests would improve
-- **Before / After diagram**: side-by-side, custom-drawn, illustrating the shallowness and the deepening
-- **Recommendation strength**: one of `Strong`, `Worth exploring`, `Speculative`, rendered as a badge
-
-End the report with a **Top recommendation** section: which candidate you'd tackle first and why.
-
-**Use CONTEXT.md vocabulary for the domain, and the `/codebase-design` vocabulary for the architecture.** If `CONTEXT.md` defines "Order," talk about "the Order intake module," not "the FooBarHandler," and not "the Order service."
-
-**ADR conflicts**: if a candidate contradicts an existing ADR, only surface it when the friction is real enough to warrant revisiting the ADR. Mark it clearly in the card (e.g. a warning callout: _"contradicts ADR-0007, but worth reopening because…"_). Don't list every theoretical refactor an ADR forbids.
-
-See [HTML-REPORT.md](HTML-REPORT.md) for the full HTML scaffold, diagram patterns, and styling guidance.
-
-Do NOT propose interfaces yet. After the file is written, ask the user: "Which of these would you like to explore?"
-
-### 3. Grilling loop
-
-Once the user picks a candidate, call the Skill tool with "grilling" to walk the decision tree with them: constraints, dependencies, the shape of the deepened module, what sits behind the seam, what tests survive.
-
-Side effects happen inline as decisions crystallize; call the Skill tool with "domain-modeling" to keep the domain model current as you go:
-
-- **Naming a deepened module after a concept not in `CONTEXT.md`?** Add the term to `CONTEXT.md`. Create the file lazily if it doesn't exist.
-- **Sharpening a fuzzy term during the conversation?** Update `CONTEXT.md` right there.
-- **User rejects the candidate with a load-bearing reason?** Offer an ADR, framed as: _"Want me to record this as an ADR so future architecture reviews don't re-suggest it?"_ Only offer when the reason would actually be needed by a future explorer to avoid re-suggesting the same thing; skip ephemeral reasons ("not worth it right now") and self-evident ones.
-- **Want to explore alternative interfaces for the deepened module?** Call the Skill tool with "codebase-design" and use its design-it-twice parallel sub-agent pattern.

package/template/.agents/skills/improve-codebase-architecture/agents/openai.yaml

@@ -1,5 +0,0 @@
-interface:
-  display_name: "Improve Codebase Architecture"
-  short_description: "Find and grill architecture improvements"
-policy:
-  allow_implicit_invocation: false

package/template/.agents/skills/instance-test/SKILL.md

@@ -1,70 +0,0 @@
----
-name: instance-test
-disable-model-invocation: true
-description: "matt-skills 专属功能测试示范（由 scaffold-functional-test 从 spec 生成）— 验证 sync 合并 update 后的行为；仅显式调用"
----
-
-# Instance Test — matt-skills 专属示范
-
-本 skill 是 **matt-skills 专属**的功能测试示范，由 `scaffold-functional-test` 从 `.scratch/sync-merge-update/spec.md` 生成（见 `references/instances.md` 头部 `spec hash` + `generatedAt`）。它是生成器产出形态的示例，不随 Template Snapshot 分发，仅保留于 Workspace。旧通用执行器文案已废弃。
-
-兼容别名：`instance-test` 保留原名以兼容历史调用，实际为 `matt-functional-test` 的示范实现。
-
-## Steps
-
-### 1. Gather instances
-
-实例集已由生成器按**受控扩展模型**落盘于 `references/instances.md`（头部含 `spec hash` + `generatedAt`，每实例含**溯源** `spec.md` 章节/行号，`<!-- manual -->` 段受保护）。
-
-执行前校验指纹：若当前 spec 的 `spec hash` 与 `references/instances.md` 头部不一致，提示「spec 已变更，建议重跑 scaffold-functional-test」但不自动覆盖，需用户显式确认才 regenerate（AI 先给 diff 建议）。
-
-每实例声明：`prompt/command/expected files/content/expected stdout phrases/expected exit code` 必选，`setup/env/timeout/type/teardown` 可选，默认 `type: cli`。
-
-完成：实例清单已固定（含溯源与指纹），`<!-- manual -->` 段未被覆盖。
-
-### 2. Run instances
-
-For each **instance** in order:
-
-1. `mktemp -d` 隔离目录（或项目支持的 `git worktree` / `--dest`），单线程串行，不并行。
-2. 执行实例的 `command` 与可选 `setup`，捕获 stdout/stderr 与 exit code。
-3. 快照 `expected` 声明的文件与副作用。
-
-一个 **instance** 一次，失败不阻断后续，产物不碰撞。
-
-完成：每实例均有独立 run dir 与捕获输出。
-
-### 3. Evaluate
-
-对比每实例的 actual vs expected：
-
-- 文件存在性/内容（`test -f`/`grep -q`/`diff`）
-- Stdout/stderr 含预期短语
-- Exit code 一致
-- 扩展字段（`env`/`timeout`/`type`）行为符合声明
-
-标记 `PASS`/`FAIL`，附 `expected vs actual` diff 与 run dir 证据。
-
-完成：每实例均有 `PASS` 或 `FAIL` 且含证据。
-
-### 4. Report
-
-对话内汇总：
-
-- `PASS m/n` + per-instance evidence
-- 失败项列出 gap（expected vs actual）与 run dir 复现路径
-- 成功默认清理临时目录、失败默认保留；`--keep` 保留全部；`--report` 显式开启才落盘报告文件
-
-不以文件刷屏——默认输出在对话，报告文件仅显式开启才写。
-
-## 实例来源
-
-- 源 spec：`.scratch/sync-merge-update/spec.md`（`spec hash` 见 `references/instances.md` 头部）
-- 推导策略：混合推导（验收标准锚点 + 需求/接口/边界补充），每实例含溯源，无溯源视为幻觉
-- 手工段：`<!-- manual -->` 保护
-
-## 引用
-
-- 生成器：`scaffold-functional-test`（读 spec 产出本 skill）
-- 领域术语：`CONTEXT.md`
-- 技能设计：`docs/agents/skill-design.md`

package/template/.agents/skills/instance-test/agents/openai.yaml

@@ -1,5 +0,0 @@
-interface:
-  display_name: "Instance Test"
-  short_description: "matt-skills 专属功能测试示范 — 验证 sync 合并 update 后行为"
-policy:
-  allow_implicit_invocation: false

package/template/.agents/skills/instance-test/references/instances.md

@@ -1,75 +0,0 @@
-# Instances for matt-skills — sync 行为功能测试（由 scaffold-functional-test 生成）
-
-> 源 spec：`.scratch/sync-merge-update/spec.md`
-> spec hash: `062a76fc872d`  # .scratch/sync-merge-update/spec.md 的 sha256 前 12 位
-> generatedAt: 2026-05-11
-> 推导策略：混合推导（验收标准锚点 + 需求/行为补充），每实例含溯源，无溯源视为幻觉
-
-本文件由 `scaffold-functional-test` 按**受控扩展模型**生成：必选 `prompt/command/expected files/content/expected stdout phrases/expected exit code`，可选 `setup/env/timeout/type/teardown`，默认 `type: cli`。执行语义：`mktemp -d` 隔离、单线程串行、`PASS m/n` 汇总、证据含 `expected vs actual` diff + `run dir`。
-
-执行前校验：对比当前 `.scratch/sync-merge-update/spec.md` 的 hash 与本文件头部 `spec hash`，不一致时提示「spec 已变更，建议重跑 scaffold-functional-test」但不自动覆盖。
-
----
-
-## 1. sync 默认 check（无参不写盘）
-
-- Prompt: 验证 `matt-skills sync` 无参等价 check，打印表且不改 AGENTS.md
-- 溯源: spec.md — 需求/行为「`matt-skills sync` 无参：等价 `check`」+ 验收标准「`sync` 无参在已定制的 `pi-switch` 仓库上不改 `AGENTS.md`」
-- type: cli
-- setup: `node bin/cli.js init --dest <tmp>` 后手工改 `AGENTS.md` 加入 `tdd-implement` 定制行
-- Command: `node bin/cli.js sync --dest <tmp>`（无参）
-- Expected:
-  - `git diff HEAD -- AGENTS.md` 为空（`AGENTS.md` 未被覆盖）
-  - stdout 含 `上游 HEAD` 与 `新增/更新/删除/一致` 表头
-  - stdout 含 `--json` 可解析提示或表格行
-  - exit 0 或 1（有差异时 exit 1，判 exit code 符合 check 语义）
-- Expected files/content: `AGENTS.md` 保留定制行，无 `AGENTS.md.bak` 新增
-- Expected stdout phrases: `上游 HEAD`, `一致`
-- Expected exit code: 1（有差异时）/ 0（无差异时）— 按实现定义，测试以实际 check 语义为准
-
-## 2. sync --apply 安全增量（AGENTS.md 跳过、上游强制覆盖不删）
-
-- Prompt: 验证 `sync --apply` 为安全增量，`AGENTS.md` 定制跳过、上游技能被覆盖但 remove 列表不删
-- 溯源: spec.md — 需求/行为「`sync --apply`：安全增量写盘。`AGENTS.md` 若含独有路由则跳过；上游技能 `rm+cp force` 覆盖，跳过 `PROPRIETARY`，不执行 `remove`」+ 验收标准「`sync --apply` 后上游技能被强制更新为上游 `HEAD`，`remove` 列表的技能仍保留」
-- type: cli
-- setup: 在 `<tmp>` 放置旧版上游技能 `test-skill` 过期文件，并手工改 `AGENTS.md`
-- Command: `node bin/cli.js sync --apply --dest <tmp>`
-- Expected:
-  - `AGENTS.md` 仍含定制行（未被模板覆盖）
-  - 上游技能文件已更新为上游 HEAD 内容（`diff` 无旧版残留）
-  - `remove` 列表中的技能目录仍存在（未被删除）
-- Expected files/content: `AGENTS.md` 定制行存在；`test-skill` 被覆盖为新版；无 `AGENTS.md.bak`（安全档不备份）或按实现保留但不覆盖
-- Expected stdout phrases: `已同步` 或 `已更新` 或 `同步`
-- Expected exit code: 0
-- timeout: 30000
-
-## 3. sync --force 硬盖（AGENTS.md 备份后覆盖、全量 add/update/remove）
-
-- Prompt: 验证 `sync --force` 硬盖，`AGENTS.md` 备份后被模板覆盖、技能与模板全量同步含删除
-- 溯源: spec.md — 需求/行为「`sync --force`：硬盖。`AGENTS.md` 先 `backupIfExists → .bak` 再 `cp -r force`；技能与模板均 `add/update/remove` 全做」+ 验收标准「`sync --force` 后 `AGENTS.md` 变为模板且 `AGENTS.md.bak` 存在，`remove` 列表的技能被删除」
-- type: cli
-- setup: 在 `<tmp>` 放置 `AGENTS.md` 定制行 + 一个上游已删的本地技能 `obsolete-skill/`
-- Command: `node bin/cli.js sync --force --dest <tmp>`
-- Expected:
-  - `AGENTS.md` 已被模板覆盖（定制行消失，与 `template/AGENTS.md` 一致）
-  - `AGENTS.md.bak` 存在且含定制行备份
-  - `obsolete-skill/` 已被删除
-- Expected files/content: `AGENTS.md` 内容等于 `template/AGENTS.md`；`AGENTS.md.bak` 存在
-- Expected stdout phrases: `已覆盖` 或 `硬盖`
-- Expected exit code: 0
-
-## 4. update 已合并到 sync --apply（删除分支、提示已合并）
-
-- Prompt: 验证 `matt-skills update` 已删除，执行后报错提示已合并到 `sync --apply`，且 `--help` 不再列 `update`
-- 溯源: spec.md — 需求/行为「`matt-skills update`：删除该分支，`main` 中 `command === 'update'` 改为 `stderr: 'update 已合并到 sync --apply'` 且 `exit 1`，`--help` 不再列 `update`」+ 验收标准「`matt-skills update` 执行后报错提示已合并，`--help` 无 `update`」
-- type: cli
-- Command: `node bin/cli.js update 2>&1; echo "exit:$?"` 与 `node bin/cli.js --help`
-- Expected:
-  - `update` 命令 stdout/stderr 含 `已合并到 sync --apply` 且 exit 1
-  - `--help` 输出不含独立的 `update` 子命令行（不匹配 `^\s*update`）
-- Expected stdout phrases: `已合并到 sync --apply`
-- Expected exit code: 1（`update` 分支）
-- env: {}
-
-<!-- manual -->
-<!-- 以下为人工定制实例保护段：由开发者手写，scaffold-functional-test 重生成时不覆盖此段以上的内容。如需新增手工实例，请在此段后追加。 -->

package/template/.agents/skills/prototype/LOGIC.md

@@ -1,67 +0,0 @@
-# Logic Prototype
-
-A single, self-contained HTML file (a **shareable demo**) that lets anyone drive a state model by clicking buttons. Use this when the question is about **business logic, state transitions, or data shape**: the kind of thing that looks reasonable on paper but only feels wrong once you push it through real cases.
-
-Because it's one file with nothing to install, you can hand it to a non-developer (a designer, a PM, a domain expert) and let them feel the model for themselves. So it speaks their language, not the code's.
-
-## When this is the right shape
-
-- "I'm not sure if this state machine handles the edge case where X then Y."
-- "Does this data model actually let me represent the case where..."
-- "I want to feel out what the API should look like before writing it."
-- Anything where someone wants to **press buttons and watch state change**.
-
-If the question is "what should this look like," this is the wrong branch. Use [UI.md](UI.md).
-
-## Process
-
-### 1. State the question
-
-Before writing code, write down what state model and what question you're prototyping. One paragraph, at the top of the demo (in a visible intro, not just a comment). A logic prototype that answers the wrong question is pure waste, so make the question explicit so it can be checked later, whether the user is watching now or returning to it AFK.
-
-### 2. Isolate the logic in a portable module
-
-Put the actual logic (the bit that's answering the question) in a single `<script>` block written as a small, pure module that could be lifted out and dropped into the real codebase later. The page around it is throwaway; this module isn't.
-
-The right shape depends on the question:
-
-- **A pure reducer**: `(state, action) => state`. Good when actions are discrete events and state is a single value.
-- **A state machine**: explicit states and transitions. Good when "which actions are even legal right now" is part of the question.
-- **A small set of pure functions** over a plain data type. Good when there's no implicit current state, just transformations.
-- **A class or module with a clear method surface** when the logic genuinely owns ongoing internal state.
-
-Pick whichever shape best fits the question being asked, *not* whichever is easiest to wire to a page. Keep it pure: no DOM, no `document`, no button handlers reaching inside it. The page calls into it; nothing flows the other direction. This is what makes the prototype useful past its own lifetime: once the question's answered, the validated reducer / machine / function set lifts into the real module on its own.
-
-### 3. Build the shareable HTML file
-
-One file, plain HTML/CSS/JS: no framework, no bundler, no server, everything inline so it opens by double-click and survives being emailed around. Anyone should be able to run it by opening it.
-
-Write it for a non-developer. Every label is in **domain language**, not code: buttons and state read like the business, not the reducer. Explain in plain words what's happening.
-
-Lay it out with a clean hierarchy, top to bottom:
-
-1. **Title and one-line explanation** of what this demo lets you explore (the question from step 1).
-2. **Current state**: the full relevant state, rendered as a readable panel (labelled fields, not a raw JSON dump), re-rendered after every click so the change is visible. Where it helps a non-developer follow, call out what just changed.
-3. **Free-play buttons**: one button per action, always available, so anyone can poke at the model in any order. Each click dispatches its action and re-renders the state.
-4. **Guided walkthroughs**: a set of **scenarios**, one per tab. Each tab holds a short plain-language description of the scenario (the situation it sets up and what to watch for) and underneath it, the ordered **buttons to press** for that scenario. Each step is a real button: clicking it performs that action and moves to the next step. Starting a walkthrough resets to a known initial state so the scenario runs the same way every time.
-
-Choose scenarios that demonstrate the awkward cases, the ones hard to reason about on paper: the happy path, a tricky edge case, an attempt at something that should be illegal.
-
-Keep it beautiful but restrained: clean typography, generous spacing, one accent colour. No animations, no gimmicks: nothing that competes with the state and the buttons.
-
-### 4. Hand it over
-
-Send them the file, or open it for them. They'll click through the walkthroughs and free-play whenever they get to it; the interesting moments are when they say "wait, that shouldn't be possible" or "huh, I assumed X would be different"; those are the bugs in the _idea_, which is the whole point. If they want new actions or a new scenario, add them. Prototypes evolve.
-
-### 5. Capture the answer and the prototype
-
-Once the prototype has answered its question, capture the answer, then capture the prototype the way the [SKILL](SKILL.md) describes. The logic-specific mapping: the validated reducer / machine / function set lifts into the real module (the decision, absorbed); the HTML shell rides along to the throwaway branch that keeps the prototype as a primary source, and being one self-contained file, it stays trivially re-runnable there.
-
-## Anti-patterns
-
-- **Don't add tests.** A prototype that needs tests is no longer a prototype.
-- **Don't wire it to the real database.** Use in-memory state unless the question is specifically about persistence.
-- **Don't generalise.** No "what if we wanted to support X later." The prototype answers one question.
-- **Don't blur the logic and the page together.** If the pure module references the DOM, `document`, or button handlers, it's no longer liftable. Keep the page as a thin shell over a pure module.
-- **Don't reach for a framework, bundler, or server.** One file the recipient double-clicks; a React app or a dev server defeats "shareable".
-- **Don't ship the HTML shell into production.** The page is optimised for being clicked through by hand. The logic module behind it is the bit worth keeping.

package/template/.agents/skills/prototype/SKILL.md

@@ -1,26 +0,0 @@
----
-name: prototype
-description: Build a throwaway prototype to answer a design question. Use when the user wants to sanity-check whether a state model or logic feels right, or explore what a UI should look like.
----
-
-# Prototype
-
-A prototype is **throwaway code that answers a question**. The question decides the shape.
-
-## Pick a branch
-
-Identify which question is being answered, using the user's prompt, the surrounding code, or by asking if the user is around:
-
-- **"Does this logic / state model feel right?"** → [LOGIC.md](LOGIC.md). Build a single shareable HTML file (free-play buttons plus tabbed guided walkthroughs) that pushes the state machine through cases that are hard to reason about on paper, and that a non-developer can drive.
-- **"What should this look like?"** → [UI.md](UI.md). Generate several radically different UI variations on a single route, switchable via a URL search param and a floating bottom bar.
-
-The two branches produce very different artifacts, so getting this wrong wastes the whole prototype. If the question is genuinely ambiguous and the user isn't reachable, default to whichever branch better matches the surrounding code (a backend module → logic; a page or component → UI) and state the assumption at the top of the prototype.
-
-## Rules that apply to both
-
-1. **Throwaway from day one, and clearly marked as such.** Locate the prototype code close to where it will actually be used (next to the module or page it's prototyping for) so context is obvious, but name it so a casual reader can see it's a prototype, not production. For throwaway UI routes, obey whatever routing convention the project already uses; don't invent a new top-level structure.
-2. **Trivial to run.** A UI prototype starts from one command in the project's task runner: `pnpm <name>`, `python <path>`, `bun <path>`, etc. A logic demo is a single HTML file the user double-clicks. Either way, no thinking required to start it.
-3. **No persistence by default.** State lives in memory. Persistence is the thing the prototype is _checking_, not something it should depend on. If the question explicitly involves a database, hit a scratch DB or a local file with a clear "PROTOTYPE, wipe me" name.
-4. **Skip the polish.** No tests, no error handling beyond what makes the prototype _runnable_, no abstractions. The point is to learn something fast.
-5. **Surface the state.** After every action (logic) or on every variant switch (UI), print or render the full relevant state so the user can see what changed.
-6. **Capture it when done.** Fold any validated decision into the real code, then capture the prototype itself as a **primary source**: commit it to a throwaway branch, out of main, and leave a context pointer to that branch on the implementation issue. Capture the answer too (the verdict and the question it settled) in the issue or a commit. The main branch keeps only the validated decision.

package/template/.agents/skills/prototype/UI.md

@@ -1,112 +0,0 @@
-# UI Prototype
-
-Generate **several radically different UI variations** on a single route, switchable from a floating bottom bar. The user flips between variants in the browser, picks one (or steals bits from each), then throws the rest away.
-
-If the question is about logic/state rather than what something looks like, this is the wrong branch. Use [LOGIC.md](LOGIC.md).
-
-## When this is the right shape
-
-- "What should this page look like?"
-- "I want to see a few options for this dashboard before committing."
-- "Try a different layout for the settings screen."
-- Any time the user would otherwise spend a day picking between three vague mockups in their head.
-
-## Two sub-shapes: strongly prefer sub-shape A
-
-A UI prototype is much easier to judge when it's **butting up against the rest of the app**: real header, real sidebar, real data, real density. A throwaway route on its own is a vacuum: every variant looks fine in isolation. Default to sub-shape A whenever there's a plausible existing page to host the variants. Only reach for sub-shape B if the prototype genuinely has no nearby home.
-
-### Sub-shape A: adjustment to an existing page (preferred)
-
-The route already exists. Variants are rendered **on the same route**, gated by a `?variant=` URL search param. The existing data fetching, params, and auth all stay. Only the rendering swaps. This is the default; pick it unless there's a specific reason not to.
-
-If the prototype is for something that doesn't yet have a page but *would naturally live inside one* (a new section of the dashboard, a new card on the settings screen, a new step in an existing flow), it's still sub-shape A. Mount the variants inside the host page.
-
-### Sub-shape B: a new page (last resort)
-
-Only use this when the thing being prototyped genuinely has no existing page to live inside (e.g. an entirely new top-level surface, or a flow that can't be embedded anywhere sensible).
-
-Create a **throwaway route** following whatever routing convention the project already uses. Don't invent a new top-level structure. Name it so it's obviously a prototype (e.g. include the word `prototype` in the path or filename). Same `?variant=` pattern.
-
-Before committing to sub-shape B, sanity-check: is there really no existing page this could be embedded in? An empty route hides design problems that a populated one would expose.
-
-In both sub-shapes the floating bottom bar is identical.
-
-## Process
-
-### 1. State the question and pick N
-
-Default to **3 variants**. More than 5 stops being radically different and starts being noise, so cap there.
-
-Write down the plan in one line, in the prototype's location or a top-of-file comment:
-
-> "Three variants of the settings page, switchable via `?variant=`, on the existing `/settings` route."
-
-This works whether the user is here to push back or not.
-
-### 2. Generate radically different variants
-
-Draft each variant. Hold each one to:
-
-- The page's purpose and the data it has access to.
-- The project's component library / styling system (TailwindCSS, shadcn, MUI, plain CSS, whatever).
-- A clear exported component name, e.g. `VariantA`, `VariantB`, `VariantC`.
-
-Variants must be **structurally different**: different layout, different information hierarchy, different primary affordance, not just different colours. Three slightly-tweaked card grids isn't a UI prototype, it's wallpaper. If two drafts come out too similar, redo one with explicit "do not use a card grid" guidance.
-
-### 3. Wire them together
-
-Create a single switcher component on the route:
-
-```tsx
-// pseudo-code, adapt to the project's framework
-const variant = searchParams.get('variant') ?? 'A';
-return (
-  <>
-    {variant === 'A' && <VariantA {...data} />}
-    {variant === 'B' && <VariantB {...data} />}
-    {variant === 'C' && <VariantC {...data} />}
-    <PrototypeSwitcher variants={['A','B','C']} current={variant} />
-  </>
-);
-```
-
-For sub-shape A (existing page): keep all the existing data fetching above the switcher; only the rendered subtree changes per variant.
-
-For sub-shape B (new page): the throwaway route under `/prototype/<name>` mounts the same switcher.
-
-### 4. Build the floating switcher
-
-A small fixed-position bar at the bottom-centre of the screen with three pieces:
-
-- **Left arrow**: cycles to the previous variant (wraps around).
-- **Variant label**: shows the current variant key and, if the variant exports a name, that name too. e.g. `B (Sidebar layout)`.
-- **Right arrow**: cycles forward (wraps around).
-
-Behaviour:
-
-- Clicking an arrow updates the URL search param (use the framework's router, e.g. `router.replace` on Next, `navigate` on React Router, etc) so the variant is shareable and reload-stable.
-- Keyboard: `←` and `→` arrow keys also cycle. Don't intercept arrow keys when an `<input>`, `<textarea>`, or `[contenteditable]` is focused.
-- Visually distinct from the page (e.g. high-contrast pill, subtle shadow) so it's obviously not part of the design being evaluated.
-- Hidden in production builds: gate on `process.env.NODE_ENV !== 'production'` or an equivalent check, so a stray prototype merge can't ship the bar to users.
-
-Put the switcher in a single shared component so both sub-shapes can reuse it. Locate it wherever shared UI lives in the project.
-
-### 5. Hand it over
-
-Surface the URL (and the `?variant=` keys). The user will flip through whenever they get to it. The interesting feedback is usually **"I want the header from B with the sidebar from C"**, which is the actual design they want.
-
-### 6. Capture the answer and clean up
-
-Once a variant has won, capture the answer (which variant and why), then capture the prototype the way the [SKILL](SKILL.md) describes. Fold the winner into the real code and move the rest onto the throwaway branch, not into main:
-
-- **Sub-shape A**: fold the winner into the existing page; drop the losing variants and the switcher from main.
-- **Sub-shape B**: promote the winning variant to a real route; drop the throwaway route and the switcher from main.
-
-The full set of variants is the primary source, so it lands on the throwaway branch, not the bin, since variant components and the switcher left in the main branch rot fast and confuse the next reader.
-
-## Anti-patterns
-
-- **Variants that differ only in colour or copy.** That's a tweak, not a prototype. Real variants disagree about structure.
-- **Sharing too much code between variants.** A shared `<Header>` is fine; a shared `<Layout>` defeats the point. Each variant should be free to throw out the layout.
-- **Wiring variants to real mutations.** Read-only prototypes are fine. If a variant needs to mutate, point it at a stub: the question is "what should this look like", not "does the backend work".
-- **Promoting the prototype directly to production.** The variant code was written under prototype constraints (no tests, minimal error handling). Rewrite it properly when you fold it in.

package/template/.agents/skills/prototype/agents/openai.yaml

@@ -1,3 +0,0 @@
-interface:
-  display_name: "Prototype"
-  short_description: "Prototype to answer a design question"

package/template/.agents/skills/research/SKILL.md

@@ -1,12 +0,0 @@
----
-name: research
-description: Investigate a question against high-trust primary sources and capture the findings as a Markdown file in the repo. Use when the user wants a topic researched, docs or API facts gathered, or reading legwork delegated to a background agent.
----
-
-Spin up a **background agent** to do the research, so you keep working while it reads.
-
-Its job:
-
-1. Investigate the question against **primary sources** (official docs, source code, specs, first-party APIs), not a secondary write-up of them. Follow every claim back to the source that owns it.
-2. Write the findings to a single Markdown file, citing each claim's source.
-3. Save it where the repo already keeps such notes; match the existing convention, and if there is none, put it somewhere sensible and say where.

package/template/.agents/skills/research/agents/openai.yaml

@@ -1,3 +0,0 @@
-interface:
-  display_name: "Research"
-  short_description: "Research from high-trust sources"

package/template/.agents/skills/resolving-merge-conflicts/SKILL.md

@@ -1,14 +0,0 @@
----
-name: resolving-merge-conflicts
-description: "Use when you need to resolve an in-progress git merge/rebase conflict."
----
-
-1. **See the current state** of the merge/rebase. Check git history, and the conflicting files.
-
-2. **Find the primary sources** for each conflict. Understand deeply why each change was made, and what the original intent was. Read the commit messages, check the PRs, check original issues/tickets.
-
-3. **Resolve each hunk.** Preserve both intents where possible. Where incompatible, pick the one matching the merge's stated goal and note the trade-off. Do **not** invent new behaviour. Always resolve; never `--abort`.
-
-4. Discover the project's **automated checks** and run them, typically typecheck, then tests, then format. Fix anything the merge broke.
-
-5. **Finish the merge/rebase.** Stage everything and commit. If rebasing, continue the rebase process until all commits are rebased.

package/template/.agents/skills/resolving-merge-conflicts/agents/openai.yaml

@@ -1,3 +0,0 @@
-interface:
-  display_name: "Resolving Merge Conflicts"
-  short_description: "Resolve merge and rebase conflicts"

package/template/.agents/skills/scaffold-functional-test/SKILL.md

@@ -1,64 +0,0 @@
----
-name: scaffold-functional-test
-disable-model-invocation: false
-description: "Scaffold a repo-specific functional-test skill from spec — use when the user wants to generate a customized functional-test suite/skill from a spec/README/help; supports CLI, HTTP, browser, and file-oriented behaviors; not for regular instance execution nor for TDD"
----
-
-# Scaffold Functional Test
-
-从仓库 spec 生成仓库专属的功能测试 skill。它是一次性 scaffold，不负责常规实例执行，也不进入 TDD 红绿循环。
-
-生成物：`.agents/skills/<repo>-functional-test/`，至少包含 `SKILL.md` 与 `references/instances.md`；可按需要包含 runner。实例字段、溯源、指纹和保护段统一遵循 [`references/schema.md`](references/schema.md)。生成物纳入 git，但不复制到 `template/`。
-
-## 流程
-
-### ① 采集行为
-
-读取用户指定的 spec，默认 `.scratch/<feature>/spec.md`；同时读取相关 `CONTEXT.md` 与 ADR。以 Acceptance Criteria 固定待覆盖行为清单。
-
-spec 不存在时可从 README 与 `--help` 建立候选清单，但必须把它标为候选并进入下一步确认，不得把推断当成需求。
-
-出口：行为清单的来源、范围和未覆盖项已明确。
-
-### ② 推导并确认实例
-
-按 [`references/schema.md`](references/schema.md) 为每个行为选择最接近真实用户路径的实例类型：`cli`、`http`、`browser` 或 `file`。每个实例必须有溯源，不能用无来源的隐含行为扩张范围，也不能为了统一格式给 browser/http 行为强塞无意义的 stdout/exit-code 字段。
-
-向用户展示实例清单并等待一次确认；确认前不落盘。
-
-出口：实例清单已确认，每个实例类型、字段和断言完整且可追溯。
-
-### ③ 生成或更新
-
-写入定制 skill 和实例 reference：
-
-- 写入 spec 的 SHA-256 `spec hash` 与 ISO `generatedAt`；
-- 保留 `<!-- manual -->` 保护段；
-- 新建直接生成；更新已有生成物时先展示 diff，用户确认后才覆盖；
-- 不把本次生成物写入 `template/`。
-
-出口：文件结构、指纹和人工段均符合 schema。
-
-### ④ 结构验证
-
-生成后立即做快速、确定性的结构验证：文件存在、schema 字段、实例类型、实例溯源、spec hash、`generatedAt`、manual 段保护和内部链接均通过后再报告成功。不默认执行完整实例集，不启动服务，不产生功能测试副作用。
-
-出口：结构验证结果为 `PASS`，失败则报告具体 gap，不回滚生成物。
-
-## 可选行为验证
-
-仅当用户明确要求运行实例集时，才调用生成的功能测试 skill 执行隔离、串行的实例验证；执行器按实例 `type` 捕获对应 evidence：CLI 的 stdout/stderr/exit code，HTTP 的 status/body/headers，browser 的页面/DOM/network/console 证据，file 的文件与内容 diff，并报告 expected-vs-actual 与 `PASS m/n`。这不是 scaffold 的默认步骤。
-
-## 不做什么
-
-- 不替代生成后的功能测试 skill；
-- 不替代 `tdd`、`tdd-implement` 或 `commit-check`；
-- 不覆盖 `<!-- manual -->` 段，不静默重生成，不把 README/`--help` 推断写成无溯源实例；
-- 不把所有行为强制降格成 CLI 测试。
-
-## 引用
-
-- 实例 schema：[`references/schema.md`](references/schema.md)
-- 领域术语：`CONTEXT.md`
-- 技能设计规则：`docs/agents/skill-design.md`
-- 示范产物：`.agents/skills/instance-test/`

package/template/.agents/skills/scaffold-functional-test/agents/openai.yaml

@@ -1,5 +0,0 @@
-interface:
-  display_name: "Scaffold Functional Test"
-  short_description: "Scaffold a repo-specific functional-test skill from spec — not for running tests nor TDD"
-policy:
-  allow_implicit_invocation: true

package/template/.agents/skills/scaffold-functional-test/references/schema.md

@@ -1,80 +0,0 @@
-# Functional-test instance schema
-
-`scaffold-functional-test` 生成的实例清单以本文件为唯一字段契约。实例是声明式输入，不把执行逻辑散落在生成器正文中。
-
-## Common required fields
-
-每个实例都必须包含：
-
-- `prompt`：实例要覆盖的用户行为；
-- `type`：实例类型，必须是 `cli`、`http`、`browser` 或 `file` 之一；
-- `source`：spec 章节/行号，或 README / `--help` 的明确来源。
-
-`setup`、`env`、`timeout`、`teardown` 为跨类型可选字段。不要为了凑字段写 `none`；某个断言维度不适用时直接省略。
-
-## Type-specific contract
-
-### `type: cli`
-
-必须包含：
-
-- `command`：实际执行命令；
-- `expected exit code`：预期退出码。
-
-按需包含：
-
-- `expected stdout phrases`；
-- `expected stderr phrases`；
-- `expected files/content`。
-
-### `type: http`
-
-必须包含：
-
-- `request`：method + URL/path + 必要 headers/body；
-- `expected status`：预期 HTTP status。
-
-按需包含：
-
-- `expected body`；
-- `expected headers`；
-- `expected side effects`。
-
-### `type: browser`
-
-必须包含：
-
-- `entrypoint`：已有页面、dev server 或浏览器入口；
-- `steps`：最小用户操作序列；
-- `assertions`：DOM、可见文本、URL、网络或控制台等用户可观察断言。
-
-browser 实例不要求伪造 `stdout` 或 `exit code` 字段；执行器负责记录浏览器证据和必要截图/trace 路径。
-
-### `type: file`
-
-必须包含：
-
-- `command` 或已有生成入口；
-- `expected files/content`：应出现、变化或保持不变的文件与内容断言。
-
-按需包含 `expected exit code`、stdout/stderr 断言。
-
-## Assertion rules
-
-- 只写可机器验证或可明确观察的断言，不把“应该正常”“体验良好”这类自然语言目标当作 assertion；
-- 一个实例可以有多个断言，但每个断言必须能回溯到 `source`；
-- 优先验证用户可观察行为，不把内部实现细节当作功能结果；
-- 同一行为存在多种入口时，选择最接近真实使用路径的类型和入口，不强行统一成 CLI。
-
-## Fingerprint
-
-实例 reference 头部必须包含：
-
-- `spec hash`：源 spec 文件字节的 SHA-256；
-- `generatedAt`：生成时的 ISO 8601 时间戳。
-
-执行或更新前发现 hash 不一致时，报告 spec 已变更并给出 regenerate 建议；未经用户确认不覆盖实例清单。
-
-## Protected content
-
-`<!-- manual -->` 与其保护段属于人工维护内容。更新生成物时保留原文；需要改变人工段时先展示 diff 并获得用户确认。