AI Agent Skills

把当前对话转化为一份规格说明，并发布到项目工单跟踪器——无需访谈，只是综合你们已经讨论过的内容。

把一个计划、规格说明或当前对话拆分成一组曳光弹式工单，每张声明它的阻塞边，发布到所配置的跟踪器——在本地为每张工单一个文件、边以文字形式，或在真实跟踪器上为原生阻塞链接。

让工单和外部 PR 在一套分诊角色的状态机中流转——分类、验证、必要时拷问，并写出可供 agent 处理的简报。

把一大块工作——超出单个 agent 会话所能容纳的量——规划为工单跟踪器上一张由决策工单构成的共享地图，逐个解决它们，直到通往目的地的路径变得清晰。

Own the whole marketing content pipeline for this codebase — set itself up, scan the product for what actually works, write the copy, enforce the rules mechanically, and…

>-

Clone viral TikTok UGC app-ad hooks with your own AI actor and app demo. Use when the user wants to recreate a viral TikTok ad, build a TikTok account around one consist…

Use when user says "paleo mode", "save tokens", "be brief", "terse", "compress output", or says "paleo". Switch agent to terse replies that cut output tokens ~50-70% (me…

Use when you want automatic token-saving without manual skill selection. Auto-detects long sessions (>15 turns), high token usage, or bulky context — then auto-enables p…

Use when user says "budget", "token limit", "stay under N tokens", or wants per-task token caps. Enforce a hard token budget per task/response — track estimate, stop bef…

Use when user says "compress conversation", "condense chat", "summarize history", "too long context", or a session has many old turns. Condense prior conversation turns…

Use when user says "compact json", "minify output", "tight structured", or the agent must emit JSON / structured data. Strip insignificant whitespace, collapse long arra…

Use when user says "summarize output", "condense this", "tldr", or a tool result / log / file dump / long stdout is large. Reduce long content (tool output, logs, diffs,…

Use when context window is large / token cost high / long session. Proactively trim, summarize, or drop stale content to save context tokens without losing the task stat…

Create one new skill end to end - asks about purpose, trigger phrases, tools and context, then writes .claude/skills/<name>/SKILL.md with valid frontmatter and registers…

Close a work session - asks what was completed, what was learned and what comes next, then updates dashboard, todo, learnings, errors and writes memory/daily/YYYY-MM-DD.…