create-yss-spec 2.1.8 → 2.1.10

package/template/wiki/wiki/Matt/346/212/200/350/203/275/344/275/223/347/263/273.md

@@ -2,7 +2,7 @@
 
 Matt Engineering Skills 是来自 `mattpocock/skills` 的轻量工程流程技能集合，用于澄清、Spec、Ticket、实现、TDD、诊断、审查和架构治理，不替代 YSS 专项规范（见 [[YSS工程技能体系]]）。
 
-主要技能与用途：`grill-with-docs`（需求澄清与决策沉淀）、`to-spec`（Spec 形成）、`to-tickets`（垂直切片拆分）、`tdd`（测试驱动实现）、`diagnosing-bugs`（Bug 与性能回退诊断）、`code-review`（双轴审查：标准符合性与 Spec 符合性）、`codebase-design` / `improve-codebase-architecture`（深模块设计与架构治理）、`resolving-merge-conflicts`、`writing-skills`（技能编写 RED / GREEN / REFACTOR）、`research`（一手事实研究）与 `handoff`（交接记录）。
+主要技能与用途：`grill-with-docs`（需求澄清与决策沉淀）、`to-spec`（Spec 形成）、`to-tickets`（垂直切片拆分）、`tdd`（测试驱动实现）、`diagnosing-bugs`（Bug 与性能回退诊断）、`code-review`（双轴审查：标准符合性与 Spec 符合性）、`codebase-design` / `improve-codebase-architecture`（深模块设计与架构治理）、`resolving-merge-conflicts`、`maintaining-skills`（轻量技能维护）、`research`（一手事实研究）与 `handoff`（交接记录）。
 
 专项任务强制入口（见 [[Agent入口规则]]）：技术事实影响决策用 `research`；竞品 / 市场 / 用户口碑事实用 `competitive-intelligence`；UI 设计用 `yss-design-system` 后路由 `product-design:index`；Bug、测试失败或性能回退用 `diagnosing-bugs` 建立可复现反馈，再用 `tdd`；架构治理与深模块设计用 `codebase-design`；跨线程、跨仓库、上下文过长或原型结论回流用 `handoff`。
 

package/template/wiki/wiki/YSS/345/267/245/347/250/213/346/212/200/350/203/275/344/275/223/347/263/273.md

@@ -6,4 +6,4 @@ YSS skills 是项目内置的 YSS 工程规范技能，用于 DDD、UI、OpenAPI
 
 技能路由纪律：核心 YSS skills 必须消费批准合同并返回 YSS Skill Execution Result（见 [[切片实现合同]]）；路径越界、证据缺失、未执行验证、`drift`、`violation` 或 `new_impacts` 阻断继续实现或触发重路由。禁止绕过合同与检查清单直接在 `AGENTS.md` 中自行发明细则。
 
-技能治理：`yss-router` 选择最小技能集合（见 [[YSS路由与合同编译]]）；技能来源、版本、哈希与投影目标登记在 `skills-lock.json`（见 [[技能投影与锁定]]）；技能内容变更遵循 `writing-skills` 的 RED / GREEN / REFACTOR 思路（见 [[模板维护流程]]）。
+技能治理：`yss-router` 选择最小技能集合（见 [[YSS路由与合同编译]]）；技能来源、版本、哈希与投影目标登记在 `skills-lock.json`（见 [[技能投影与锁定]]）；技能维护使用 `maintaining-skills`，验证强度由模板维护 L1 / L2 / L3 规则决定（见 [[模板维护流程]]）。

package/template/wiki/wiki//345/244/215/347/233/230/344/270/216/346/235/203/345/250/201/350/265/204/344/272/247/344/277/256/350/256/242.md

@@ -2,7 +2,7 @@
 
 发布后或阶段性完成后做复盘判断：出现架构返工、验证返工、IMPORTANT / CRITICAL review finding 或人工确认延期时，落简体中文复盘并修订权威资产。
 
-复盘输入包括验证证据、审查报告、Ticket 证据与 Git checkpoint 记录（见 [[Fresh验证与独立审查]] 与 [[Ticket与流程状态]]）。复盘输出按 `docs/templates/retro-report-template.md` 记录，发现的问题回流到对应单一事实来源：流程语义问题修订生命周期映射或裁剪指南，词汇问题修订 `CONTEXT.md`，决策问题沉淀 ADR，技能问题进入 `writing-skills` 修订流程（见 [[模板维护流程]] 与 [[条件强制门禁]]）。
+复盘输入包括验证证据、审查报告、Ticket 证据与 Git checkpoint 记录（见 [[Fresh验证与独立审查]] 与 [[Ticket与流程状态]]）。复盘输出按 `docs/templates/retro-report-template.md` 记录，发现的问题回流到对应单一事实来源：流程语义问题修订生命周期映射或裁剪指南，词汇问题修订 `CONTEXT.md`，决策问题沉淀 ADR，技能问题进入 `maintaining-skills` 修订流程（见 [[模板维护流程]] 与 [[条件强制门禁]]）。
 
 复盘修订遵循影响面分析与条件强制门禁：命中触发条件才生成对应资产，未命中记录 `not-applicable`（见 [[影响面分诊与流程裁剪]]）。复盘发现的跨仓库问题（如 `create-yss-spec` 契约偏差）须同步到外部仓库责任边界（见 [[实现仓库与跨仓库契约]]）。
 

package/template/wiki/wiki//346/250/241/346/235/277/345/217/221/345/270/203/351/227/250/347/246/201/344/270/216/351/252/214/350/257/201.md

@@ -4,6 +4,6 @@
 
 `verify-template` 验证五类压力场景（生命周期、YSS Router、YSS UI、Matt × YSS 集成等），由 `scripts/verify-lifecycle-scenarios`、`scripts/verify-yss-router-scenarios`、`scripts/verify-yss-ui-scenarios`、`scripts/verify-matt-yss-integration-scenarios` 等脚本支撑。模板与外部 `create-yss-spec` 的跨仓库契约未完成集成验证时，不得声称可发布（见 [[模板维护流程]] 与 [[实现仓库与跨仓库契约]]）。
 
-模板维护硬门禁还包括：修改 skill、`AGENTS.md`、流程规则或模板时，必须使用 `writing-skills` 的 RED / GREEN / REFACTOR 思路，保留基线失败、压力场景和修订后验证证据；共享技能投影禁止分别手工修改（见 [[技能投影与锁定]]）。
+模板维护硬门禁还包括：创建、修改或退役 skill 时使用 `maintaining-skills`，并按 L1 / L2 / L3 执行对应验证与审查；共享技能投影禁止分别手工修改（见 [[技能投影与锁定]]）。
 
 任何"完成 / 可合并 / 可发布"结论必须基于 fresh verification（见 [[Fresh验证与独立审查]]），不接受"之前跑过"或实现者自述。模板发布前还需同步技能投影与派生文档、更新 `skills-lock.json`，并完成独立审查和 Git checkpoint。

package/template/wiki/wiki//346/250/241/346/235/277/347/273/264/346/212/244/346/265/201/347/250/213.md

@@ -4,6 +4,6 @@
 
 标准流程为：影响面分析 → 修改对应单一事实来源 → 同步技能投影和派生文档 → 执行压力场景与 `scripts/verify-template` → 独立审查和 Git checkpoint。影响面分析决定修改哪些权威资产：`AGENTS.md`、`CONTEXT.md`、生命周期映射、裁剪指南或 `skills-lock.json`。
 
-硬门禁包括：修改 skill、`AGENTS.md`、流程规则或模板时，必须使用 `writing-skills` 的 RED / GREEN / REFACTOR 思路，保留基线失败、压力场景和修订后验证证据；`.agents/skills` 是跨 Agent 共享技能的权威内容，各平台目录中的共享技能是生成投影，禁止分别手工修改（见 [[技能投影与锁定]]）；`scripts/verify-template` 是模板发布阻断门禁（见 [[模板发布门禁与验证]]）。
+硬门禁包括：创建、修改或退役 skill 时使用 `maintaining-skills`，并按 L1 / L2 / L3 执行对应验证与审查；`.agents/skills` 是跨 Agent 共享技能的权威内容，各平台目录中的共享技能是生成投影，禁止分别手工修改（见 [[技能投影与锁定]]）；`scripts/verify-template` 是模板发布阻断门禁（见 [[模板发布门禁与验证]]）。
 
 模板与外部 `create-yss-spec` 的跨仓库契约未完成集成验证时，不得声称可发布；发布顺序与责任边界以 raw 源 `create-yss-spec-contract.md` 为准（见 [[实现仓库与跨仓库契约]]）。模板改动后需运行 `scripts/sync-skills`、`scripts/update-skill-lock` 与 `scripts/verify-template`。

package/template.manifest.json

@@ -33,5 +33,17 @@
   ],
   "exampleDocPaths": [
     "docs/discovery/IDEATION.md"
+  ],
+  "initExcludeRootEntries": [
+    "scripts",
+    "wiki"
+  ],
+  "initExcludeRootFiles": [
+    ".gitignore",
+    ".nvmrc",
+    "yss-public-skills.json"
+  ],
+  "initExcludePaths": [
+    ".github"
   ]
 }

package/template.snapshot.json

@@ -3,14 +3,14 @@
   "templateName": "yss-spec-project-template",
   "templateSource": "github:iloveZzz/yss-spec-project-template",
   "templateRepository": "https://github.com/iloveZzz/yss-spec-project-template.git",
-  "requestedRef": "772758e064889829576d55fd20b17421d98982a8",
-  "templateCommit": "772758e064889829576d55fd20b17421d98982a8",
+  "requestedRef": "235a4bff79a13dfa1614948a5a266c1679b276d1",
+  "templateCommit": "235a4bff79a13dfa1614948a5a266c1679b276d1",
   "encodedPaths": {
     ".codex/skills/data-analytics/.gitignore": ".codex/skills/data-analytics/__yss_dotfile__.gitignore",
     ".codex/skills/product-design/.npmignore": ".codex/skills/product-design/__yss_dotfile__.npmignore",
     ".codex/skills/product-design/templates/prototype/.npmrc": ".codex/skills/product-design/templates/prototype/__yss_dotfile__.npmrc",
     ".gitignore": "__yss_dotfile__.gitignore"
   },
-  "snapshotHash": "75a23afd5b5fd4f063e133e7c397d537ad94db407826f480c138b7f9a912a6c1",
-  "generatedAt": "2026-08-18T08:42:21.882Z"
+  "snapshotHash": "f1e5fc00ea9efeb108ead6469a173c9a88a7ce05b11e3fede07fe4e7526efb3a",
+  "generatedAt": "2026-08-21T08:34:22.978Z"
 }

package/template/.agents/skills/batch-grill-me/SKILL.md

@@ -1,15 +0,0 @@
----
-name: batch-grill-me
-description: A relentless interview that asks every frontier question at once, round by round.
-disable-model-invocation: true
----
-
-Interview the user relentlessly until you reach a shared understanding. Map this as a **design tree**: every decision branches into the decisions that hang off it.
-
-Work the tree in **rounds**. The **frontier** is every decision whose prerequisites are already settled — the questions you can ask *now* without guessing at answers you haven't heard yet. Ask the whole frontier in one round: number each question and give your recommended answer. Then wait for the user's answers before the next round.
-
-Each round the user answers reshapes the tree — settled decisions push the frontier outward and unblock questions that depended on them. Recompute the frontier and ask the next round. A question whose answer depends on another question still open in this round belongs to a *later* round, not this one.
-
-Finding *facts* is your job, never the user's. When a frontier question needs a fact from the environment (filesystem, tools, etc.), dispatch a sub-agent to find it — don't ask the user for anything you could look up yourself. Don't block on it: a running exploration is an unsettled prerequisite, so only the questions downstream of it wait for the sub-agent to report — ask the rest of the frontier now. The *decisions* are the user's — put each to them and wait.
-
-The session is done when the frontier is empty: every branch of the design tree visited, nothing left silently assumed. Do not act on it until the user confirms you have reached a shared understanding.

package/template/.agents/skills/batch-grill-me/agents/openai.yaml

@@ -1,5 +0,0 @@
-interface:
-  display_name: "Batch Grill Me"
-  short_description: "Sharpen a plan a round of questions at a time"
-policy:
-  allow_implicit_invocation: false

package/template/.agents/skills/claude-handoff/SKILL.md

@@ -1,18 +0,0 @@
----
-name: claude-handoff
-description: Hand the current conversation off to a fresh background agent that picks up the work immediately.
-argument-hint: "What will the next session be used for?"
-disable-model-invocation: true
----
-
-Write a handoff summary of the current conversation so a fresh agent can continue the work. Instead of saving it, launch a background agent seeded with the summary as its prompt: `claude --bg --name "<descriptive name>" "<handoff summary>"`. It starts in the current working directory and returns immediately; the user manages it with `claude agents`.
-
-Always pass `-n`/`--name` with a descriptive name (e.g. `--name "Fix login bug"`) — it sets the display name shown in the job list, session picker, and terminal title.
-
-Include a "suggested skills" section in the summary, which suggests skills that the agent should invoke.
-
-Do not duplicate content already captured in other artifacts (PRDs, plans, ADRs, issues, commits, diffs). Reference them by path or URL instead.
-
-Redact any sensitive information, such as API keys, passwords, or personally identifiable information — the summary becomes the agent's prompt.
-
-If the user passed arguments, treat them as a description of what the next session will focus on and tailor the summary accordingly.

package/template/.agents/skills/claude-handoff/agents/openai.yaml

@@ -1,5 +0,0 @@
-interface:
-  display_name: "Claude Handoff"
-  short_description: "Hand off to a background agent"
-policy:
-  allow_implicit_invocation: false

package/template/.agents/skills/git-guardrails-claude-code/SKILL.md

@@ -1,95 +0,0 @@
----
-name: git-guardrails-claude-code
-description: Set up Claude Code hooks to block dangerous git commands (push, reset --hard, clean, branch -D, etc.) before they execute. Use when user wants to prevent destructive git operations, add git safety hooks, or block git push/reset in Claude Code.
----
-
-# Setup Git Guardrails
-
-Sets up a PreToolUse hook that intercepts and blocks dangerous git commands before Claude executes them.
-
-## What Gets Blocked
-
-- `git push` (all variants including `--force`)
-- `git reset --hard`
-- `git clean -f` / `git clean -fd`
-- `git branch -D`
-- `git checkout .` / `git restore .`
-
-When blocked, Claude sees a message telling it that it does not have authority to access these commands.
-
-## Steps
-
-### 1. Ask scope
-
-Ask the user: install for **this project only** (`.claude/settings.json`) or **all projects** (`~/.claude/settings.json`)?
-
-### 2. Copy the hook script
-
-The bundled script is at: [scripts/block-dangerous-git.sh](scripts/block-dangerous-git.sh)
-
-Copy it to the target location based on scope:
-
-- **Project**: `.claude/hooks/block-dangerous-git.sh`
-- **Global**: `~/.claude/hooks/block-dangerous-git.sh`
-
-Make it executable with `chmod +x`.
-
-### 3. Add hook to settings
-
-Add to the appropriate settings file:
-
-**Project** (`.claude/settings.json`):
-
-```json
-{
-  "hooks": {
-    "PreToolUse": [
-      {
-        "matcher": "Bash",
-        "hooks": [
-          {
-            "type": "command",
-            "command": "\"$CLAUDE_PROJECT_DIR\"/.claude/hooks/block-dangerous-git.sh"
-          }
-        ]
-      }
-    ]
-  }
-}
-```
-
-**Global** (`~/.claude/settings.json`):
-
-```json
-{
-  "hooks": {
-    "PreToolUse": [
-      {
-        "matcher": "Bash",
-        "hooks": [
-          {
-            "type": "command",
-            "command": "~/.claude/hooks/block-dangerous-git.sh"
-          }
-        ]
-      }
-    ]
-  }
-}
-```
-
-If the settings file already exists, merge the hook into existing `hooks.PreToolUse` array — don't overwrite other settings.
-
-### 4. Ask about customization
-
-Ask if user wants to add or remove any patterns from the blocked list. Edit the copied script accordingly.
-
-### 5. Verify
-
-Run a quick test:
-
-```bash
-echo '{"tool_input":{"command":"git push origin main"}}' | <path-to-script>
-```
-
-Should exit with code 2 and print a BLOCKED message to stderr.

package/template/.agents/skills/git-guardrails-claude-code/agents/openai.yaml

@@ -1,3 +0,0 @@
-interface:
-  display_name: "Git Guardrails for Claude Code"
-  short_description: "Block dangerous git commands"

package/template/.agents/skills/git-guardrails-claude-code/scripts/block-dangerous-git.sh

@@ -1,25 +0,0 @@
-#!/bin/bash
-
-INPUT=$(cat)
-COMMAND=$(echo "$INPUT" | jq -r '.tool_input.command')
-
-DANGEROUS_PATTERNS=(
-  "git push"
-  "git reset --hard"
-  "git clean -fd"
-  "git clean -f"
-  "git branch -D"
-  "git checkout \."
-  "git restore \."
-  "push --force"
-  "reset --hard"
-)
-
-for pattern in "${DANGEROUS_PATTERNS[@]}"; do
-  if echo "$COMMAND" | grep -qE "$pattern"; then
-    echo "BLOCKED: '$COMMAND' matches dangerous pattern '$pattern'. The user has prevented you from doing this." >&2
-    exit 2
-  fi
-done
-
-exit 0