AgentStack
jnMetaCode avatar

jnMetaCode

36 listings · 0 installs

Open-source publisher. Listings imported from github.com/jnMetaCode — credited to the original author with their license.

↗ github.com/jnMetaCode
36 results
Self-run
SKILL

Chinese Commit Conventions

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。

0
4
Free
Self-run
SKILL

Systematic Debugging

遇到任何 bug、测试失败或异常行为时使用,在提出修复方案之前执行

0
5
Free
Self-run
SKILL

Using Git Worktrees

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

0
4
Free
Self-run
SKILL

Workflow Runner

在 Claude Code / OpenClaw / Cursor 中直接运行 agency-orchestrator YAML 工作流——无需 API key,使用当前会话的 LLM 作为执行引擎。当用户提供 .yaml 工作流文件或要求多角色协作完成任务时触发。

0
4
Free
Self-run
SKILL

Writing Plans

当你有规格说明或需求用于多步骤任务时使用,在动手写代码之前

0
5
Free
Self-run
SKILL

Test Driven Development

在实现任何功能或修复 bug 时使用,在编写实现代码之前

0
5
Free
Self-run
SKILL

Chinese Documentation

中文文档排版参考——中英文空格、全半角标点、术语保留、链接格式、中文文案排版指北约定。仅在用户显式 /chinese-documentation 时调用,不要根据上下文自动触发。

0
5
Free
Self-run
SKILL

Receiving Code Review

收到代码审查反馈后、实施建议之前使用,尤其当反馈不明确或技术上有疑问时——需要技术严谨性和验证,而非敷衍附和或盲目执行

0
4
Free
Self-run
SKILL

Executing Plans

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

0
4
Free
Self-run
SKILL

Using Superpowers

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

0
4
Free
Self-run
SKILL

Chinese Code Review

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。

0
4
Free
Self-run
SKILL

Chinese Git Workflow

国内 Git 平台配置参考——Gitee、Coding.net、极狐 GitLab、CNB 的 SSH/HTTPS/凭据/CI 接入差异与镜像同步配置。仅在用户显式 /chinese-git-workflow 时调用,不要根据上下文自动触发。

0
5
Free
Self-run
SKILL

Requesting Code Review

完成任务、实现重要功能或合并前使用,用于验证工作成果是否符合要求

0
4
Free
Self-run
SKILL

Mcp Builder

MCP 服务器构建方法论 — 系统化构建生产级 MCP 工具,让 AI 助手连接外部能力

0
5
Free
Self-run
SKILL

Writing Skills

当创建新技能、编辑现有技能或在部署前验证技能是否有效时使用

0
5
Free
Self-run
SKILL

Subagent Driven Development

当在当前会话中执行包含独立任务的实现计划时使用

0
4
Free
Self-run
MCP

Skillet

skillet — a package manager for AI agent skills (SKILL.md). Find, install, version & share skills from a Git-backed registry. Zero infra, MCP-native, reproducible.

0
4
Free
Self-run
MCP

Superpowers Zh

🦸 AI 编程超能力 · 中文增强版 — superpowers(116k+ ⭐)完整汉化 + 6 个中国原创 skills,让 Claude Code / Copilot CLI / Hermes Agent / Cursor / Windsurf / Kiro / Gemini CLI 等 16 款 AI 编程工具真正会干活

0
14
Free
Self-run
SKILL

Pr Description

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.

0
5
Free
Self-run
SKILL

Changelog

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…".

0
3
Free
Self-run
SKILL

Self Evolve

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".

0
4
Free
Self-run
SKILL

Test Writing

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.

0
6
Free
Self-run
SKILL

Systematic Debugging

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.

0
3
Free
Self-run
SKILL

Conventional Commits

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

0
3
Free
Self-run
SKILL

Engram Memory

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".

0
4
Free
Self-run
SKILL

Tracelet Instrument

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.

0
2
Free
Self-run
SKILL

Incident Postmortem

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.

0
4
Free
Self-run
SKILL

Repo Onboarding

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?".

0
5
Free
Self-run
MCP

Agency Orchestrator

🚀 One sentence → multi-AI-role collaboration → complete plan in minutes. Built on the agency-agents role library (216+ experts), zero-code YAML, web Studio + desktop app, 10 LLM providers (7 free). 基于 agency-agents 专家库,一句话调度多个 AI 专家自动协作,几分钟交付完整方案。

0
11
Free
Self-run
MCP

Shellward

AI 应用合规网关 · 一行命令体检 AI 项目的「数据出境 / 硬编码密钥 / 个人信息暴露」(网安法·PIPL·等保2.0·数据出境·AI标识),并给出境内模型替代建议;可作运行时防护拦截注入与数据外泄 · 中文优先 · 零依赖 · 开源

0
5
Free
Self-run
SKILL

Shortfilm Prompt

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.

0
7
Free
Self-run
SKILL

Finishing A Development Branch

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

0
4
Free
Self-run
SKILL

Brainstorming

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。

0
5
Free
Self-run
SKILL

Verification Before Completion

在宣称工作完成、已修复或测试通过之前使用,在提交或创建 PR 之前——必须运行验证命令并确认输出后才能声称成功;始终用证据支撑断言

0
4
Free
Self-run
SKILL

Hello World

A tiny example skill that greets the user — use it to verify skillet installs work.

0
2
Free
Self-run
SKILL

Dispatching Parallel Agents

当面对 2 个以上可以独立进行、无共享状态或顺序依赖的任务时使用

0
6
Free
You've reached the end · 36 loaded