jnMetaCode

当在当前会话中执行包含独立任务的实现计划时使用

在开始任何对话时使用——确立如何查找和使用技能，要求在任何响应（包括澄清性问题）之前调用 Skill 工具

当你有一份书面实现计划需要在单独的会话中执行，并设有审查检查点时使用

在任何创造性工作之前必须使用此技能——创建功能、构建组件、添加功能或修改行为。在实现之前先探索用户意图、需求和设计。

当实现完成、所有测试通过、需要决定如何集成工作时使用——通过提供合并、PR 或清理等结构化选项来引导开发工作的收尾

当需要开始与当前工作区隔离的功能开发，或在执行实现计划之前使用——通过原生工具或 git worktree 回退机制确保隔离工作区存在

中文 review 沟通参考——话术模板、分级标注（必须修复/建议修改/仅供参考）、国内团队常见反模式应对。仅在用户显式 /chinese-code-review 时调用，不要根据上下文自动触发。

中文 commit 与 changelog 配置参考——Conventional Commits 中文适配、commitlint/husky/commitizen 中文模板、conventional-changelog 中文配置。仅在用户显式 /chinese-commit-conventions 时调用，不要根据上下文自动触发。

Make the agent improve with every task — review the run, distill lessons into durable memory, and reinforce what worked. Use at the end of any non-trivial task, or when the user asks the agent to "learn from this".

Write a blameless, actionable incident postmortem from the raw facts. Use after an outage/incident, or when asked to write up "what happened" for the team.

Write a reviewer-first pull-request description from the actual branch diff. Use when opening a PR or asked to write/improve a PR description.

Root-cause a bug with a hypothesis-driven loop instead of shotgun edits. Use when a bug isn't obvious after the first look, or when asked to "find out why" something fails.

Write tests that catch real regressions — behavior-focused, minimal mocking, edge cases chosen from the code's actual branches. Use when adding tests for new code or backfilling tests for a fix.

Generate or update a CHANGELOG.md in Keep a Changelog format from real git history. Use when cutting a release, tagging a version, or asked "what changed since…".

Write precise Conventional Commits messages from the actual staged diff. Use whenever committing code or asked to write/fix a commit message.

Systematically map an unfamiliar codebase before changing it — entry points, build/test loop, conventions, data flow. Use when starting work in a repo you haven't seen, or asked "how does this codebase work?".

Give the agent durable, local memory with engram — recall past decisions before answering, and persist new decisions, preferences and facts as they happen. Use when work spans sessions or the user says "remember".

Instrument an AI agent or LLM app with OpenTelemetry and watch its runs live in tracelet (local DevTools). Use when asked to add tracing/observability to an agent, or to debug what an agent actually did.

Capture decisions and facts as durable notes; use when the user makes a decision worth remembering.

多角色 YAML 工作流执行引擎——解析 workflow YAML，加载 agency-agents-zh 角色，按 DAG 顺序执行

Draft user-facing release notes from a git log range. Trigger when the user asks for "release notes", "changelog entry", or "what shipped this week" with a git ref range. Output is markdown sections grouped by Features / Fixes / Breaking with PR links.

Generate cinematic AI shortfilm prompts (works with Seedance 2.0, Xiaoyunque, Sora, Kling, Jimeng, Veo) using the 5-stage structure from Mx-Shell's Zombie Scavenger. Trigger when the user wants transformation sequences, multi-shot narrative shorts, weapon-charge/combat segments, emotional family/pet/farewell narratives (催泪/亲情/萌宠/离别), or any cinematic video prompt.

OpenClaw 安全部署指南 / Security deployment guide — help users secure their OpenClaw installation