Claude Skills by KonghaYao

github.com/KonghaYao

18 skillsA× 16C× 1D× 10 installs0 views

Advisor ConsultationAUse when the user asks for an advisor, Opus second opinion, optimal approach, design critique, or when a task has unresolved high-risk trade-offs, repeated failed investigations, cross-boundary contracts, security implications, or uncertainty that repository evidence cannot yet resolve.ai-agentsrustgoVotes: 0GitHub stars: 226
Agent Task EvaluatorA评价和分组 Agent 历史任务的交付、验证、约束、用户反馈与执行策略，编排独立评审并从证据形成提示词改进假设和验证实验。用于任务做得好不好、任务有效性、优秀任务分组、从任务成败改进 Agent 提示词；工具错误统计本身不需要启动任务评价。ai-agentsVotes: 0GitHub stars: 226
Auto ConvergeA通过外部对标+对抗迭代让规则/技能/SKILL.md 收敛到可执行状态。当用户说"打磨这个 skill""收敛规则""这个 skill 写出来不 work，帮我调" "怎么让 agent 严格按规则执行"时触发。也适用于任何需要把一份规则文档从"写完了但 agent 不遵守" 变成"agent 能稳定执行"的场景。ai-agentsgitapiVotes: 0GitHub stars: 226
Auto Data ResearcherA从 SQLite、JSONL、日志或历史会话中研究行为模式，核验数据质量、统计口径与案例证据，产出可复现的分析和可验证的改进候选。用于分析历史数据、比较行为变化、提炼系统或用户使用规律；单纯文章润色不需要启动研究流程。ai-agentssqlVotes: 0GitHub stars: 226
Auto DevflowAUse when starting an issue, bugfix, feature, or refactor that benefits from an adaptive development workflow. Select lite, normal, pro, max, or ultra from task complexity and risk, then use only the coordination, review, and verification phases that the task actually needs.ai-agentsgocode-reviewVotes: 0GitHub stars: 226
Blog WriterAPeri 项目博客写作风格指南。当用户说"写博客"、"写文章"、"出稿"、 "按风格写"、"博客"时触发。也适用于用户丢过来素材说"帮我写篇博客"的场景。覆盖项目介绍、技术复盘、架构讨论、性能优化、架构设计等类型。ai-agentspythonrustVotes: 0GitHub stars: 226
Skills DirectorySkills Directory Look up any of 103,619 scanned skills — grade, score, and every finding. Free.Check a skill
Codebase IndexA代码库速查索引库 —— docs/code-index/ 下每个 crate 一个速查表文件，把「我想做什么」映射到具体文件、入口函数与一句话关键逻辑。当用户想定位或修改某个行为（"怎么改 compact 的触发阈值"、"keepgoing 判定在哪"、"加个 deferred 工具改哪里"、"事件链路怎么走"）、想快速了解某个模块的结构、或要求重建/更新代码索引时使用。用户没提"索引"二字但任务是找代码位置、改某个逻辑、理清调用链时，也应先查索引，而不是直接全库搜索。ai-agentsgoVotes: 0GitHub stars: 226
Heavy Verify LoopARuns a user-level verification and repair loop against the real Peri TUI using ./dev.sh, tmux, logs, E2E helpers, and Advisor/Coder/Reviewer subagents. Use when a feature must be exercised as a real user and repeatedly repaired until fresh end-to-end evidence shows no blocking problems.ai-agentsrustgoVotes: 0GitHub stars: 226
LangfuseC查询或操作 Langfuse traces、prompts、datasets、scores、sessions，查阅 Langfuse 文档与 SDK 用法；也用于分析本地 llm-gateway 请求/响应日志、查看 LLM 请求、追踪 session、对比上下文、排查 token 用量及缓存命中率。根据数据来源选择 Langfuse API 或本地网关日志脚本；本地分析无需 Langfuse 凭据。ai-agentstypescriptbashVotes: 0GitHub stars: 226
Learn From HistoryA审计近期对话历史，把重复失败与成功模式转成可证伪的 harness 改进契约，并在后续审计中归因。用户要求总结历史对话、回顾近期 agent 表现、从历史中学习或寻找可自动化改进时使用。developmentpythonbashVotes: 0GitHub stars: 226
Project MaturityA对任意项目进行全面的成熟度评估扫描。当用户说"检查项目成熟度"、"项目评估"、 "maturity assessment"、"代码质量扫描"、"项目健康度"、"项目体检"、 "scan project maturity"、"项目有多成熟"时触发。适用场景：接手新项目前的摸底、发布前的质量审查、技术尽调、团队内部代码健康度盘点。developmentjavascripttypescriptVotes: 0GitHub stars: 226
Ssh CliDExecute commands and manage files on remote machines over SSH via a zero-dependency Node CLI (ssh-cli.js). Use when the user needs to run commands, read/write/edit files, or diagnose connectivity on a remote host, or asks for anything "on the server / remote machine / dev box".ai-agentsshellbashVotes: 0GitHub stars: 226
CronAScheduled tasks (cron). Use when the user asks for recurring, periodic, or scheduled tasks — reminders, periodic reports, or anything that should run at a fixed interval ("every day at 9am", "每 5 分钟", "every Monday"). Also use when managing existing scheduled tasks via mcp__cron__cron_list / mcp__cron__cron_remove.ai-agentsexpressgitVotes: 0GitHub stars: 226
GoalALong-running goal tracking. Use when the user gives a complex task requiring multiple steps to complete. Triggers: "goal", "keep going until done", "don't stop until X".ai-agentsgoVotes: 0GitHub stars: 226
MultitaskAYou are the coordinator: every workstream leaves your hands and belongs to exactly one owner launched through `Agent`, and coordination is the only work that stays with you. In force for the rest of the session once loaded.ai-agentsgoVotes: 0GitHub stars: 226
Ultra AdlcAEnd-to-end delivery orchestration for explicitly requested, very large software changes that must be completely implemented and independently proven. Use when the user invokes "ultra-adlc" or asks for an Ultra-ADLC-scale full delivery; do not use for ordinary features, small fixes, reviews, or ad hoc parallel work.developmentjavascriptrustVotes: 0GitHub stars: 226
UltracodeAMulti-agent workflow orchestration. Use when the user says "ultracode", "workflow", "parallel agents", "pipeline", or asks to orchestrate multiple agents for complex tasks. Also use when the user wants to break work into phases or parallel streams.ai-agentsjavascriptjavaVotes: 0GitHub stars: 226
Use ArtifactsATeach the agent when and how to use the artifact tool: what content belongs in artifacts, when to upload/update, and how to call it directly as `artifact`.ai-agentsgoVotes: 0GitHub stars: 226