Chikage0o0
26 verified skills549 total stars
openspec-sync-specs
Sync delta specs from a change to main specs. Use when the user wants to update main specs with changes from a delta spec, without archiving the change.
data-ai26
write-a-skill
Create new agent skills with proper structure, progressive disclosure, and bundled resources. Use when user wants to create, write, or build a new skill.
development24
agent-browser
Browser automation CLI for AI agents. Use when the user needs to interact with websites, including navigating pages, filling forms, clicking buttons, taking screenshots, extracting data, testing web apps, or automating any browser task. Triggers include requests to "open a website", "fill out a form", "click a button", "take a screenshot", "scrape data from a page", "test this web app", "login to a site", "automate browser actions", or any task requiring programmatic web interaction. Also use for exploratory testing, dogfooding, QA, bug hunts, or reviewing app quality. Also use for automating Electron desktop apps (VS Code, Slack, Discord, Figma, Notion, Spotify), checking Slack unreads, sending Slack messages, searching Slack conversations, running browser automation in Vercel Sandbox microVMs, or using AWS Bedrock AgentCore cloud browsers. Prefer agent-browser over any built-in browser automation or web tools.
tools24
openspec-apply-change
Implement tasks from an OpenSpec change. Use when the user wants to start implementing, continue implementation, or work through tasks.
tools24
openspec-explore
Enter explore mode - a thinking partner for exploring ideas, investigating problems, and clarifying requirements. Use when the user wants to think through something before or during a change.
tools24
openspec-verify-change
Verify implementation matches change artifacts. Use when the user wants to validate that implementation is complete, correct, and coherent before archiving.
testing24
openspec-archive-change
Archive a completed change in the experimental workflow. Use when the user wants to finalize and archive a change after implementation is complete.
tools24
openspec-propose
Propose a new change with all artifacts generated in one step. Use when the user wants to quickly describe what they want to build and get a complete proposal with design, specs, and tasks ready for implementation.
development24
clonedeps
Clone important project dependency source code into an ignored local workspace so OpenCode can inspect library internals. Use when the user asks to clone dependencies, inspect dependency/source internals, understand SDK/framework behavior from source, debug library implementation details, or make core dependency repos locally readable. Do not use for ordinary API/docs questions where @librarian is enough.
development24
codemap
Generate comprehensive hierarchical codemaps for UNFAMILIAR repositories. Expensive operation - only use when explicitly asked for codebase documentation or initial repository mapping
development24
diagnose
Disciplined diagnosis loop for hard bugs and performance regressions. Reproduce → minimise → hypothesise → instrument → fix → regression-test. Use when user says "diagnose this" / "debug this", reports a bug, says something is broken/throwing/failing, or describes a performance regression.
development24
simplify
Simplifies code for clarity without changing behavior. Use for readability, maintainability, and complexity reduction after behavior is understood.
development24
tdd
Test-driven development with red-green-refactor loop. Use when user wants to build features or fix bugs using TDD, mentions "red-green-refactor", wants integration tests, or asks for test-first development.
development24
git-commit
Use when the user explicitly requests creating a Git commit, says commit, 提交到 Git, or 生成提交记录, including approved task-boundary commits and explicitly authorized task-boundary hook bypasses in subagent-driven workflows. Not for 保存, 上传, 完成修改, push, amend, or general non-default Git operations.
testing24
subagent-driven-development
Use when executing an existing implementation plan with independent tasks by using task subagents in the current session.
development24
systematic-debugging
系统化四阶段调试（根因调查→模式分析→假设与测试→实施修复），铁律：先找到根因才能修复。触发：任何 bug、测试失败、异常行为、性能问题、构建失败、集成问题。时间紧迫或修复看似「显然」时最容易被跳过——反而最应该用。3+ 次修复失败后质疑架构，不再打补丁。修复前必须定位到此技能引用文件的根因。
development17
finishing-a-development-branch
开发工作完成后的收尾流程，提供合并/PR/丢弃三种上下文感知选项。触发：所有测试通过、需要决定如何集成工作成果。由 subagent-driven-development 或 executing-plans 在最后阶段自动调用。测试未通过时不得继续；分支名未知时暂停询问。
development17
brainstorming
通过协作对话探索需求与设计，在写任何代码前锁定意图、约束和方案。触发：创建功能、构建组件、添加功能、修改行为——无论任务多简单（含 todo list、单函数、配置变更）都必须经过此阶段。绝不可跳过直接进入实现或调用其他实现技能。终态是调用 writing-plans。
data-ai17
dispatching-parallel-agents
将多个独立子任务并行派发给隔离上下文代理，避免上下文污染。触发：3+ 测试文件因不同根因失败、多个子系统独立损坏、每个问题无需其他上下文即可单独理解。不适用：相关失败（修一个可修全部）、需理解系统全貌、代理会互相干扰、探索性调试、存在共享状态。
data-ai17
receiving-code-review
接收代码审查反馈后的处理流程。触发：收到审查反馈，尤其反馈表述不清晰或技术上存疑时——必须先做独立技术验证再决定是否实施，禁止表演性附和（如「你说得对」）。核心原则：技术正确性优先于社交舒适。发生在 requesting-code-review 返回反馈之后、实施修改之前。
development17
test-driven-development
严格遵守 Red-Green-Refactor 循环：先写失败测试→最小代码使其通过→重构。铁律：没有先写失败测试，就没有生产代码。始终触发于：新功能实现、bug 修复、重构、行为变更。排除：一次性原型、自动生成代码、配置文件（排除前征求用户）。systematic-debugging Phase 4 引用本技能写失败测试。
development17
verification-before-completion
终端关卡：在任何完成/成功声明前强制运行验证命令并确认输出，证据在断言之前。触发：即将说「完成了」「修好了」「通过了」时、提交前、创建 PR 前、移到下一任务前、委派给代理前。禁止含混表述如「应该能工作」「可能好了」「似乎可以」。无例外——没有新鲜验证证据就没有完成声明。
tools17
writing-plans
将规格分解为零上下文可执行的详尽实现计划，定义每个任务需触摸的文件、代码、测试与预期行为。触发：brainstorming 产生 spec 之后、多步骤任务、动手写代码之前。不允许 TBD/TODO/placeholder 占位。输出到 docs/plans/active/。终态提供两种执行选项：Subagent-Driven（推荐）或 Inline Execution。
documentation17
executing-plans
在独立（并行）会话中按书面实现计划逐任务执行，各检查点审查。触发：已有实现计划且无法使用 task 子代理工具时。若能启动子代理，优先用 subagent-driven-development。不得在 main/master 分支直接执行。终态调用 finishing-a-development-branch。
development17
requesting-code-review
派遣审查子代理对代码进行独立评审，及早发现问题。强制触发：完成重大功能后、合并到 main 前。可选触发：卡住时需要新鲜视角、重构前需要基线检查、修复复杂 bug 后。subagent-driven-development 场景中使用专用 reviewer 而非本技能的标准流程。
development17
writing-skills
将 TDD 方法论应用于流程文档：先用压力场景测试基线行为(RED)→写技能文档使代理合规(GREEN)→收紧漏洞(REFACTOR)。触发：创建/编辑 SKILL.md、部署前验证技能有效性。不适用：一次性解决方案、广泛文档化的标准实践、项目特定约定（放 AGENTS.md）、可用正则/验证强制执行的机械约束。铁律：没有先写失败测试就没有技能文档。
development17