utility-pm-changelog-curator
关于
This skill automatically generates CHANGELOG entries from git commit history using a specialized sub-agent. It works natively in Claude Code with the pm-skills plugin and falls back to inline execution in other development environments. The tool enforces documentation hygiene rules and produces structured output with audit-ready justifications while checking repository state.
快速安装
Claude Code
推荐npx skills add product-on-purpose/pm-skills -a claude-code/plugin add https://github.com/product-on-purpose/pm-skillsgit clone https://github.com/product-on-purpose/pm-skills.git ~/.claude/skills/utility-pm-changelog-curator在 Claude Code 中复制并粘贴此命令以安装该技能
技能文档
PM Changelog Curator (Dispatch Skill)
Cross-client dispatch wrapper for the pm-changelog-curator sub-agent. Detects runtime; dispatches to the native sub-agent on Claude Code; reads subagents/pm-changelog-curator.md and executes inline on non-Claude clients.
When to Use
- You are preparing a release and want a CHANGELOG draft from git log between two tags
- You are running on a non-Claude AI client without native pm-changelog-curator sub-agent support
- You want a draft that respects pm-skills CHANGELOG hygiene rules (no internal-notes references, no em-dashes, public paths only) without manually applying them
When NOT to Use
- You want to commit CHANGELOG entries directly (this skill produces a draft for review, not a commit)
- You want to review a PM artifact -> use
utility-pm-criticinstead - You want a repo-wide governance audit -> use
utility-pm-skill-auditor - You want a full guided release flow -> use
utility-pm-release-conductor(which chains to this skill at gate G2)
Instructions
Runtime detection step. Determine which AI client is invoking this skill.
If you are running in Claude Code with the pm-skills plugin installed
Invoke @agent-pm-changelog-curator with the user's arguments. Pass --since-tag, --target-version, --committed-only from $ARGUMENTS if present. Return the sub-agent's draft to the user.
If you are running in any other AI client
Codex CLI, Cursor, Windsurf, Copilot, Gemini CLI, or any other client without native pm-skills plugin sub-agent support:
- Read the canonical sub-agent definition at
subagents/pm-changelog-curator.md - Execute the system prompt body in that file as your operating instructions
- Run the 8-step drafting flow documented in the sub-agent definition (establish range -> read hygiene rules -> check working tree -> enumerate commits -> classify -> group -> rewrite -> determine target version -> emit draft)
- Apply
--since-tag,--target-version, and--committed-onlyarguments from$ARGUMENTS - Return the layered output per master plan D26 (full CHANGELOG draft + Status Summary + Status YAML)
Cross-Client Notes
The dispatch skill requires the AI client to:
- Execute Bash for
git log,git describe, andgit statusinvocations - Read CLAUDE.md hygiene rules and existing CHANGELOG.md format reference
- Read the canonical sub-agent definition file
- Treat the agent body as operating instructions
Per master plan D30, dispatch skill availability is CONDITIONAL on Phase 2 GATE B spike outcomes. If any of the above is unreliable on a specific client, that client falls back to manual git log + manual CHANGELOG drafting (which negates most of the dispatch skill's value but at least gives the user the canonical hygiene-rule reference).
Reference Files
- Canonical sub-agent definition:
subagents/pm-changelog-curator.md - Behavioral spec:
docs/internal/release-plans/v2.16.0/spec_pm-changelog-curator.md - CHANGELOG hygiene rules source:
CLAUDE.md(repo root) - Existing CHANGELOG.md format:
CHANGELOG.md(root); v2.15.1 + v2.15.2 entries are canonical exemplars - Runtime components catalog:
docs/reference/runtime-components.md - Output template:
references/TEMPLATE.md - Worked example:
references/EXAMPLE.md
GitHub 仓库
相关推荐技能
content-collections
元Content Collections 是一个 TypeScript 优先的构建工具,可将本地 Markdown/MDX 文件转换为类型安全的数据集合。它专为构建博客、文档站和内容密集型 Vite+React 应用而设计,提供基于 Zod 的自动模式验证。该工具涵盖从 Vite 插件配置、MDX 编译到生产环境部署的完整工作流。
polymarket
元这个Claude Skill为开发者提供完整的Polymarket预测市场开发支持,涵盖API调用、交易执行和市场数据分析。关键特性包括实时WebSocket数据流,可监控实时交易、订单和市场动态。开发者可用它构建预测市场应用、实施交易策略并集成实时市场预测功能。
creating-opencode-plugins
元该Skill帮助开发者创建OpenCode插件,用于接入命令、文件、LSP等25+种事件。它提供了插件结构、事件API规范和JavaScript/TypeScript实现模式,适合需要拦截操作、扩展功能或自定义事件处理的场景。开发者可通过它快速构建响应式模块来增强OpenCode AI助手的能力。
sglang
元SGLang是一个专为LLM设计的高性能推理框架,特别适用于需要结构化输出的场景。它通过RadixAttention前缀缓存技术,在处理JSON、正则表达式、工具调用等具有重复前缀的复杂工作流时,能实现极速生成。如果你正在构建智能体或多轮对话系统,并追求远超vLLM的推理性能,SGLang是理想选择。
