cc-devflow 4.3.0 → 4.4.1

package/.claude/skills/cc-roadmap/SKILL.md

@@ -0,0 +1,259 @@
+---
+name: cc-roadmap
+version: 4.3.1
+description: "Use when defining, resetting, or narrowing project direction, stage order, or backlog priority before a concrete requirement enters the PDCA loop."
+triggers:
+  - "帮我定路线图"
+  - "下一阶段先做什么"
+  - "backlog 太乱了"
+  - "项目方向散了"
+  - "roadmap this project"
+  - "what should we build next"
+  - "reset the roadmap"
+  - "prioritize the backlog"
+reads:
+  - "PLAYBOOK.md"
+  - "CHANGELOG.md"
+  - "assets/ROADMAP_TEMPLATE.md"
+  - "assets/BACKLOG_TEMPLATE.md"
+  - "assets/TRACKING_TEMPLATE.json"
+  - "references/roadmap-dialogue.md"
+writes:
+  - path: "devflow/ROADMAP.md"
+    durability: "durable"
+    required: true
+  - path: "devflow/BACKLOG.md"
+    durability: "durable"
+    required: true
+  - path: "devflow/roadmap-tracking.json"
+    durability: "durable"
+    required: false
+    when: "roadmap/backlog tracking is maintained through bundled helper scripts"
+entry_gate:
+  - "Read current roadmap, backlog, related capability specs, and surrounding repo context before proposing direction."
+  - "Confirm this is a project-direction problem, not a single requirement execution problem."
+  - "Do not decompose implementation tasks while the roadmap is still being decided."
+exit_criteria:
+  - "The next 1-3 stages are frozen with goal, why now, dependencies, exit signal, kill signal, and non-goals."
+  - "The first backlog items can naturally enter cc-plan without extra strategic guessing, including explicit capability links and expected spec delta."
+  - "The roadmap shows an explicit RM dependency graph so serial blockers and parallel-ready work are obvious."
+  - "The user-approved recommendation is explicit and grounded in current evidence."
+reroutes:
+  - when: "The user is already discussing one concrete requirement, bug, or execution task."
+    target: "cc-plan"
+recovery_modes:
+  - name: "re-scan-context"
+    when: "The current direction no longer matches repo reality, roadmap files, or the latest user constraint."
+    action: "Reload the roadmap sources, rewrite Context Snapshot, and recompute the recommended route before continuing."
+tool_budget:
+  read_files: 8
+  search_steps: 5
+  shell_commands: 4
+---
+
+# Roadmap
+
+> [PROTOCOL]: 变更时同步更新 `version`、`CHANGELOG.md`、相关模板/脚本引用，必要时写 migration note，然后检查 `CLAUDE.md`
+
+## Role
+
+`cc-roadmap` 只负责一件事：决定项目接下来 1-3 个阶段该推进哪几个 capability。
+
+它先尽可能收集真实上下文，再逼出真实用户、真实痛点、真实紧迫性，最后把这些现实压成一条能落地、能进入 `cc-plan` 的主线。
+
+## Read First
+
+1. `PLAYBOOK.md`
+2. `CHANGELOG.md`
+3. `assets/ROADMAP_TEMPLATE.md`
+4. `assets/BACKLOG_TEMPLATE.md`
+5. `references/roadmap-dialogue.md`
+
+## Use This Skill When
+
+- 新项目刚开始
+- 项目做到一半，方向开始发散
+- backlog 很多，但主线不清楚
+- 你需要决定接下来 1-3 个阶段先做什么
+
+如果用户已经在讨论一个明确 requirement、一个 bug 或一组实现任务，停止留在这里，转去 `cc-plan`。
+
+## Quick Start
+
+如果用户只给了一个模糊问题，先把它归到下面 3 类之一，再继续问：
+
+| 用户信号 | 先读成什么问题 | 默认路线形状 |
+|---------|---------------|-------------|
+| “不知道下一步做什么” | 主线不清 | `wedge-first` |
+| “后面几阶段都会重复碰同一底座” | 底座风险 | `platform-first` |
+| “增长/交付/信任卡住了” | 当前最大瓶颈 | `rescue-first` |
+
+先给一个**默认推荐**，再解释为什么，不要把用户扔进开放式战略讨论。
+
+## Harness Contract
+
+- Allowed actions: read current strategy files, repo context, and recent reality; compare route shapes; write `devflow/ROADMAP.md`, `devflow/BACKLOG.md`, and the optional `devflow/roadmap-tracking.json` sidecar used by bundled helpers as the shared roadmap/backlog truth source.
+- Forbidden actions: decompose implementation tasks, invent hidden context, or jump into `cc-plan` before the roadmap is approved.
+- Required evidence: every stage and backlog item must point back to explicit repo facts, user constraints, or observed market signals.
+- Reroute rule: once the conversation collapses to one concrete requirement, stop strategic expansion and hand off to `cc-plan`.
+
+## Entry Gate
+
+1. 如果 `devflow/ROADMAP.md` / `devflow/BACKLOG.md` 已存在，先读现状再重写。
+2. 先判断这是“项目方向问题”还是“单 requirement 执行问题”。
+3. 先做一次上下文扫描，不能跳过现有事实直接写愿景。
+4. 方向没被批准前，不准把 roadmap 偷偷下放成实现任务。
+
+## Context Sweep
+
+进入对话前，至少主动收这些上下文：
+
+1. 当前 `devflow/ROADMAP.md` / `devflow/BACKLOG.md` 的主线、版本、已停放事项。
+2. `devflow/specs/INDEX.md` 与相关 capability specs 的边界、状态、open gaps。
+3. `CLAUDE.md`、`README*`、`TODOS.md`、最近相关 docs / specs / plans。
+4. 最近相关提交、当前分支脏状态、正在进行中的 requirement。
+5. 真实 forcing functions：deadline、发布窗口、资源上限、依赖、distribution、adoption / trust / delivery 卡点。
+6. 当前项目最强的现实证据，以及仍然只能靠假设的空白。
+
+先把这些材料压成一个 `Context Snapshot`，再开始追问用户。
+
+## Session Protocol
+
+1. 先探索上下文，不靠默认上下文注入替代阅读。
+2. 先问现实，不先写愿景。
+3. 一次只推进一个关键未知点，不要一口气抛一串问题。
+4. 先写 `Context Snapshot`、证据、约束、非目标，再讨论阶段。
+5. 给出 2-3 种路线图形状，再明确推荐一种，并说明为什么其他路线现在不值得打。
+6. 只冻结 1-3 个阶段。每个阶段都必须有 goal、why now、dependencies、exit signal、kill signal、non-goals。
+7. 把 `RM` 之间的硬依赖压成显式 dependency graph，并标出 parallel-ready wave；不要把“最好按这个顺序做”伪装成 blocker。
+8. backlog 只保留会真的进入下一轮 `cc-plan` 的事项，每项都要带成功信号、下一决策、`Primary Capability`、`Secondary Capabilities`、`Expected Spec Delta`、`Depends On` 与 `Parallel With`。
+9. 用户没批准，不进入 `cc-plan`。
+
+## Route Selection Rule
+
+给出 2-3 条路线后，必须明确推荐其中一条。推荐格式至少回答这 4 件事：
+
+1. 为什么这条路线最符合当前证据
+2. 为什么另外两条现在不值得先打
+3. 这条路线最早会在哪个 signal 上赢
+4. 如果这个 signal 没出现，什么时候该止损
+
+推荐话术要像这样：
+
+> Recommendation: `wedge-first`, because the strongest current evidence is demand uncertainty, not platform pain. We should earn the right to build the base layer after Stage 1 proves pull.
+
+不要只写：
+
+- “建议先做 wedge-first”
+- “这条更合理”
+- “综合来看最优”
+
+## Ask
+
+至少要逼清这 5 件事：
+
+1. 这个项目真正服务谁
+2. 用户今天用什么笨办法解决
+3. 为什么他们会立刻想要这个东西
+4. 最窄但最有穿透力的第一阶段是什么
+5. 未来 6-12 个月，产品会长成什么样
+
+同时尽量补齐这些落地上下文：
+
+6. 当前最强证据是什么，哪些只是想象
+7. deadline / team / budget / dependency / distribution 的硬约束是什么
+8. 当前最大的 adoption、trust、delivery 卡点是什么
+9. 这个 roadmap 成功与失败各自用什么信号判断
+
+## Approval Gates
+
+1. 没有 `Context Snapshot`，不准给路线推荐。
+2. 没有 2-3 条路线对比，不准直接拍脑袋定主线。
+3. 没有 exit signal / kill signal / non-goals，不算阶段冻结。
+4. 没有明确成功信号和下一决策，不准把事项放进 `Ready For Req-Plan`。
+5. 没有 `RM dependency graph` 或 parallel-ready wave，不准宣称事项可以并发推进。
+6. 没有用户批准，不准把 roadmap item 下放到 `cc-plan`。
+
+## Review Loop
+
+写完 `devflow/ROADMAP.md` / `devflow/BACKLOG.md` 后，至少完成这 6 个检查：
+
+1. Placeholder scan：不能有 TBD、TODO、`[NEEDS CONTEXT]` 之类的逃避词。
+2. Evidence scan：每个阶段是否都能指回某个现实证据，而不是空洞愿景。
+3. Causality scan：Stage 2 是否真的建立在 Stage 1 的胜利条件之上。
+4. Feasibility scan：阶段目标与团队容量、依赖、distribution 约束是否接得上。
+5. Graph scan：`Depends On` 是否只包含硬阻塞，图里有没有环，parallel-ready wave 是否真的共享同一前置。
+6. Spec scan：每个 roadmap item 是否都落到某个 capability，而不是悬空需求。
+7. Handoff scan：第一批 roadmap item 是否已经自然长成可进入 `cc-plan` 的对象。
+
+## Output
+
+- `devflow/ROADMAP.md`
+- `devflow/BACKLOG.md`
+- `devflow/roadmap-tracking.json` when helper automation needs a shared roadmap/backlog truth source
+
+## Good Output
+
+一个高质量 roadmap 交付后，用户应该一眼看懂：
+
+1. 现在先打哪一仗
+2. 为什么不是另外两仗
+3. 哪个 signal 说明这一仗赢了
+4. 哪些 backlog 项已经真的 ready for `cc-plan`
+5. 哪些 `RM` 必须串行，哪些已经可以并行开会话
+
+## Versioning
+
+`cc-roadmap` 自身使用 semver：
+
+- `patch`：措辞、模板字段说明、非契约性澄清
+- `minor`：新增兼容字段、上下文收集规则、评审规则、输出结构增强
+- `major`：改变 `devflow/ROADMAP.md` / `devflow/BACKLOG.md` 的核心契约、阶段模型或 handoff 预期
+
+每次修改都必须：
+
+1. 更新本文件 frontmatter 的 `version`
+2. 更新 `CHANGELOG.md`
+3. 如果会影响已有 `devflow/ROADMAP.md` / `devflow/BACKLOG.md` 使用方式，在 `CHANGELOG.md` 写清 migration note
+
+## Bundled Resources
+
+- 变更记录：`CHANGELOG.md`
+- 模板：`assets/ROADMAP_TEMPLATE.md`
+- 模板：`assets/BACKLOG_TEMPLATE.md`
+- 结构化 tracking 模板：`assets/TRACKING_TEMPLATE.json`
+- 对话骨架：`references/roadmap-dialogue.md`
+- 条目定位：`scripts/locate-roadmap-item.sh`
+- tracking 渲染器：`scripts/roadmap-tracking.js`
+- 进度回写：`scripts/sync-roadmap-progress.sh`
+- 版本递增：`scripts/bump-skill-version.sh`
+
+## Exit Criteria
+
+- 中长期方向清楚
+- 核心上下文、证据和硬约束已经显式记录
+- 阶段目标与优先级清楚
+- 第一批 requirement 从 roadmap 里自然长出来
+- 下一步唯一答案是把某个 roadmap item 放进 `cc-plan`
+
+## Working Rules
+
+1. 先收上下文，再收意见。
+2. 没有现实证据时必须明确写成 assumption，而不是偷偷当事实。
+3. `devflow/ROADMAP.md` 是方向真相源，`devflow/BACKLOG.md` 是进入下一轮规划的缓冲区。
+4. 决策理由必须保留下来，方便以后重跑时比较版本差异。
+5. 不要为了显得完整而写 6 个阶段，能打赢下一仗比画完整战争图更重要。
+
+## Do Not
+
+- 不在这里拆实现任务
+- 不把 roadmap 写成愿望清单
+- 不讨论 20 个阶段，只定最重要的 1-3 步
+- 不靠默认上下文注入替代思考
+- 不把没有证据支撑的猜测包装成战略
+- 不让 backlog 变成“以后再说”的垃圾堆
+
+## Companion Files
+
+- 深入剧本：`PLAYBOOK.md`
+- 路线图对话：`references/roadmap-dialogue.md`

package/.claude/skills/cc-roadmap/assets/BACKLOG_TEMPLATE.md

@@ -0,0 +1,45 @@
+# BACKLOG
+
+## Backlog Meta
+
+- Roadmap version:
+- Skill version:
+- Last synced:
+- Current focus stage:
+- Tracking source: `devflow/roadmap-tracking.json`
+
+## Queue
+
+| RM-ID | Title | Source Stage | Priority | Primary Capability | Secondary Capabilities | Capability Gap | Expected Spec Delta | Evidence | Depends On | Parallel With | Unknowns | Next Decision | Ready |
+|------|-------|--------------|----------|--------------------|------------------------|----------------|---------------------|----------|------------|---------------|----------|---------------|-------|
+| RM-001 |  | Stage 1 | P1 | cap-example | - |  |  |  | - | - |  |  | No |
+
+## Dependency Handoff
+
+- Serial spine:
+- Parallel-ready next wave:
+- Notes on blockers:
+
+## Ready For Req-Plan
+
+- RM-001:
+  - Primary Capability:
+  - Secondary Capabilities:
+  - Why now:
+  - Success signal:
+  - Entry constraints:
+  - Capability gap:
+  - Expected spec delta:
+  - Open risks:
+  - First planning question:
+  - Required context to load:
+  - Depends On:
+  - Parallel With:
+  - Why this is ready now:
+
+## Parked
+
+- RM-XXX:
+  - Reason parked:
+  - Trigger to reopen:
+  - Missing evidence:

package/.claude/skills/cc-roadmap/assets/ROADMAP_TEMPLATE.md

@@ -0,0 +1,153 @@
+# ROADMAP
+
+## Roadmap Meta
+
+- Roadmap version:
+- Skill version:
+- Status:
+- Last updated:
+- Owner / decider:
+- Current focus stage:
+- Confidence:
+- Supersedes roadmap version:
+
+## Context Snapshot
+
+- Product / repo:
+- Project stage:
+- Users:
+- Pain:
+- Existing workaround:
+- Strongest demand evidence:
+- Why now:
+- Distribution path:
+- Deadline / forcing function:
+- Team / capacity:
+- Hard constraints:
+- Adoption / trust bottleneck:
+- Known unknowns:
+- Relevant capabilities:
+
+## Evidence Ledger
+
+| Signal | Evidence | Confidence | Source | Why it matters |
+|--------|----------|------------|--------|----------------|
+| Demand |  | High / Med / Low |  |  |
+| Timing |  | High / Med / Low |  |  |
+| Feasibility |  | High / Med / Low |  |  |
+| Distribution |  | High / Med / Low |  |  |
+
+## Route Options
+
+| Shape | Why this could work | Why this may fail | Decision |
+|-------|---------------------|-------------------|----------|
+| wedge-first |  |  | Recommended / Rejected |
+| platform-first |  |  | Rejected |
+| rescue-first |  |  | Rejected |
+
+## Recommended Route
+
+- Recommendation:
+- Why this route wins now:
+- Why the rejected routes lose now:
+- First signal to watch:
+- Kill signal / stop condition:
+
+## Product Thesis
+
+- Users:
+- Pain:
+- Why now:
+- Strategic wedge:
+- Product promise:
+- What we refuse to build yet:
+- 6-12 month pull:
+
+## Stage Overview
+
+| Stage | Goal | Why now | Primary capabilities | Dependencies | Exit signal | Kill signal | Non-goals |
+|-------|------|---------|----------------------|--------------|-------------|-------------|-----------|
+| Stage 1 |  |  |  |  |  |  |  |
+| Stage 2 |  |  |  |  |  |  |  |
+| Stage 3 |  |  |  |  |  |  |  |
+
+## Stage Detail
+
+### Stage 1
+
+- Goal:
+- Users unlocked:
+- Why this stage exists:
+- Entry assumptions:
+- Deliverables:
+- Dependencies:
+- Win condition:
+- Key risks:
+- Kill signal:
+- What must stay out:
+- Candidate roadmap items:
+
+### Stage 2
+
+- Goal:
+- Users unlocked:
+- Why this stage exists:
+- Entry assumptions:
+- Deliverables:
+- Dependencies:
+- Win condition:
+- Key risks:
+- Kill signal:
+- What must stay out:
+- Candidate roadmap items:
+
+### Stage 3
+
+- Goal:
+- Users unlocked:
+- Why this stage exists:
+- Entry assumptions:
+- Deliverables:
+- Dependencies:
+- Win condition:
+- Key risks:
+- Kill signal:
+- What must stay out:
+- Candidate roadmap items:
+
+## RM Dependency Graph
+
+```mermaid
+flowchart LR
+  RM_001["RM-001 ..."] --> RM_002["RM-002 ..."]
+  RM_001 --> RM_003["RM-003 ..."]
+  RM_003 --> RM_004["RM-004 ..."]
+```
+
+- Dependency rule: `Depends On` only lists hard blockers.
+- Serial spine:
+- Parallel-ready branches:
+
+## Parallel Waves
+
+| Wave | Ready when | Items | Why parallel |
+|------|------------|-------|--------------|
+| Wave 1 |  |  |  |
+| Wave 2 |  |  |  |
+
+## Decision Notes
+
+- Rejected path A:
+- Rejected path B:
+- Open assumptions to verify next:
+- What changed in this version:
+
+## Implementation Tracking
+
+- Tracking source: `devflow/roadmap-tracking.json`
+
+<!-- roadmap-tracking:start -->
+| RM-ID | Item | Stage | Priority | Primary Capability | Secondary Capabilities | Expected Spec Delta | Depends On | Status | REQ | Progress |
+|------|------|-------|----------|--------------------|------------------------|---------------------|------------|--------|-----|----------|
+| RM-001 |  | Stage 1 | P1 | cap-example | - | tighten current truth | - | Planned | - | 0% |
+<!-- roadmap-tracking:end -->

package/.claude/skills/cc-roadmap/assets/TRACKING_TEMPLATE.json

@@ -0,0 +1,48 @@
+{
+  "version": 2,
+  "lastSyncedAt": "2026-04-19",
+  "backlogMeta": {
+    "roadmapVersion": "roadmap.v1",
+    "skillVersion": "4.3.1",
+    "currentFocusStage": "Stage 1"
+  },
+  "dependencyHandoff": {
+    "serialSpine": "RM-001",
+    "parallelReadyNextWave": "-",
+    "notesOnBlockers": "-"
+  },
+  "items": [
+    {
+      "rmId": "RM-001",
+      "item": "",
+      "stage": "Stage 1",
+      "priority": "P1",
+      "primaryCapability": "cap-example",
+      "secondaryCapabilities": [],
+      "expectedSpecDelta": "tighten current truth",
+      "dependsOn": [],
+      "status": "Planned",
+      "req": "",
+      "progress": "0%",
+      "backlog": {
+        "capabilityGap": "",
+        "evidence": "",
+        "parallelWith": [],
+        "unknowns": "",
+        "nextDecision": "",
+        "ready": false,
+        "whyNow": "",
+        "successSignal": "",
+        "entryConstraints": "",
+        "openRisks": "",
+        "firstPlanningQuestion": "",
+        "requiredContextToLoad": "",
+        "whyReadyNow": "",
+        "parked": false,
+        "parkedReason": "",
+        "triggerToReopen": "",
+        "missingEvidence": ""
+      }
+    }
+  ]
+}

package/.claude/skills/cc-roadmap/references/roadmap-dialogue.md

@@ -0,0 +1,37 @@
+# Roadmap Dialogue
+
+## Order
+
+0. 先做 `Context Snapshot`：现有 roadmap / backlog、文档、最近提交、forcing functions
+1. 用户是谁
+2. 今天靠什么笨办法活着
+3. 最强需求证据是什么
+4. 为什么现在必须解决
+5. deadline / capacity / dependency / distribution 约束是什么
+6. 当前最大的 adoption / trust / delivery 卡点是什么
+7. 最窄突破口是什么
+8. 6-12 个月后会长成什么
+9. 给出 2-3 条路线图形状并明确推荐
+10. 冻结 1-3 个阶段，写 exit signal / kill signal / non-goals
+11. 画出 `RM dependency graph`，标出串行主链和 parallel-ready wave
+12. 标出哪些事项真的 ready for `cc-plan`
+
+## Question Rules
+
+- 一次只推进一个关键未知点
+- 没证据时明确写 assumption
+- 用户没批准前，不把事项偷下放成 requirement
+
+## Route Shapes
+
+- `wedge-first`: 先用一个窄切口打穿真实需求
+- `platform-first`: 先做后面几阶段都会反复复用的底座
+- `rescue-first`: 先解决 adoption、trust、delivery 里最大的卡点
+
+## Output Rules
+
+- 只定 1-3 个阶段
+- 每个阶段都要有 exit signal、kill signal、non-goals
+- `RM` 必须带 `Depends On`，并在 roadmap 里显式画出 dependency graph
+- backlog 只收下一轮真会进入 `cc-plan` 的事项
+- ready 项必须带成功信号、下一决策、`Depends On`、`Parallel With`

package/.claude/skills/cc-roadmap/scripts/bump-skill-version.sh

@@ -0,0 +1,103 @@
+#!/usr/bin/env bash
+
+set -euo pipefail
+
+# ------------------------------------------------------------
+# roadmap skill semver helper
+# - bump SKILL.md frontmatter version
+# - prepend CHANGELOG.md entry
+# ------------------------------------------------------------
+
+usage() {
+  cat <<'EOF'
+Usage:
+  bump-skill-version.sh --type patch|minor|major --message "change summary" \
+    [--skill-file SKILL.md] [--changelog CHANGELOG.md] [--date YYYY-MM-DD]
+EOF
+}
+
+TYPE=""
+MESSAGE=""
+SKILL_FILE="SKILL.md"
+CHANGELOG_FILE="CHANGELOG.md"
+DATE="$(date +%Y-%m-%d)"
+
+while [[ $# -gt 0 ]]; do
+  case "$1" in
+    --type) TYPE="$2"; shift 2 ;;
+    --message) MESSAGE="$2"; shift 2 ;;
+    --skill-file) SKILL_FILE="$2"; shift 2 ;;
+    --changelog) CHANGELOG_FILE="$2"; shift 2 ;;
+    --date) DATE="$2"; shift 2 ;;
+    -h|--help) usage; exit 0 ;;
+    *) echo "Unknown arg: $1" >&2; usage; exit 1 ;;
+  esac
+done
+
+if [[ -z "$TYPE" || -z "$MESSAGE" ]]; then
+  usage
+  exit 1
+fi
+
+if [[ ! -f "$SKILL_FILE" ]]; then
+  echo "Skill file not found: $SKILL_FILE" >&2
+  exit 1
+fi
+
+CURRENT_VERSION="$(awk '/^version: / { print $2; exit }' "$SKILL_FILE")"
+
+if [[ -z "$CURRENT_VERSION" ]]; then
+  echo "No version field found in $SKILL_FILE" >&2
+  exit 1
+fi
+
+IFS='.' read -r MAJOR MINOR PATCH <<<"$CURRENT_VERSION"
+
+case "$TYPE" in
+  patch)
+    PATCH=$((PATCH + 1))
+    ;;
+  minor)
+    MINOR=$((MINOR + 1))
+    PATCH=0
+    ;;
+  major)
+    MAJOR=$((MAJOR + 1))
+    MINOR=0
+    PATCH=0
+    ;;
+  *)
+    echo "Unsupported bump type: $TYPE" >&2
+    exit 1
+    ;;
+esac
+
+NEXT_VERSION="${MAJOR}.${MINOR}.${PATCH}"
+
+TMP_SKILL="$(mktemp)"
+awk -v next_version="$NEXT_VERSION" '
+  BEGIN { done = 0 }
+  {
+    if (!done && $0 ~ /^version: /) {
+      print "version: " next_version
+      done = 1
+      next
+    }
+    print
+  }
+' "$SKILL_FILE" > "$TMP_SKILL"
+mv "$TMP_SKILL" "$SKILL_FILE"
+
+if [[ ! -f "$CHANGELOG_FILE" ]]; then
+  printf '# Roadmap Skill Changelog\n\n' > "$CHANGELOG_FILE"
+fi
+
+TMP_CHANGELOG="$(mktemp)"
+{
+  sed -n '1p' "$CHANGELOG_FILE"
+  printf '\n## v%s - %s\n\n- %s\n' "$NEXT_VERSION" "$DATE" "$MESSAGE"
+  sed -n '2,$p' "$CHANGELOG_FILE"
+} > "$TMP_CHANGELOG"
+mv "$TMP_CHANGELOG" "$CHANGELOG_FILE"
+
+echo "Bumped roadmap skill: ${CURRENT_VERSION} -> ${NEXT_VERSION}"