By KonghaYao

Queries Langfuse traces, prompts, datasets and sessions, and analyzes local LLM gateway logs for requests, context growth, token use and cache hits.

KonghaYao/peri

Audits recent agent conversation history and turns repeated failures and successes into testable harness improvement proposals that later audits can check.

KonghaYao/peri

Runs commands, reads and edits files, and copies data on remote machines through a single-file Node script that wraps the system ssh and scp, in Chinese.

KonghaYao/peri

Sends a compact, redacted decision packet to a tool-free Opus advisor subagent when a task has high-risk trade-offs or stalled investigations, then weighs the answer.

KonghaYao/peri

Registers, lists and removes recurring agent tasks with five-field cron expressions, and sets safety rules so a schedule is created only when the user clearly asks.

KonghaYao/peri

Verifies and repairs a feature by using the real Peri terminal UI as a user would, looping verify, decide, fix and review until a fresh round shows no blockers.

KonghaYao/peri

Multi-agent workflow orchestration. An agent skill from KonghaYao/peri.

KonghaYao/peri

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。

KonghaYao/peri

A skill your agent uses when starting an issue, bugfix, feature, or refactor that benefits from an adaptive development workflow.

KonghaYao/peri

End-to-end delivery orchestration for explicitly requested, very large software changes that must be completely implemented and independently proven.

KonghaYao/peri

Peri 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。

KonghaYao/peri

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…

KonghaYao/peri

Teach the agent when and how to use the artifact tool: what content belongs in artifacts, when to upload/update, and the SearchExtraTools + ExecuteExtraTool invocation flow for the deferred artifact…

KonghaYao/peri

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。

KonghaYao/peri

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。

KonghaYao/peri

Long-running goal tracking. An agent skill from KonghaYao/peri.

KonghaYao/peri

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. An agent skill from KonghaYao/peri.

KonghaYao/peri

You 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.

KonghaYao/peri

Use programmatic tool calling to discover extra tools, compose multiple tool calls in ESM code, and return a compact JSON-compatible result.

KonghaYao/peri