发现最适合你需求的 AI 技能
|
Deep prompt engineering workflow—task spec, constraints, examples, evaluation sets, iteration protocol, regression testing, and safety alignment. Use when improving LLM outputs, shipping prompt changes, or building reusable prompt templates.
Use when user input is vague, underspecified, lacks boundaries or acceptance criteria, or would benefit from being reframed into a more executable prompt before work begins. Also use when user explicitly asks to optimize/refine/improve a prompt.
专为 Claude 用户打造的提示词优化工具，节省 30% Token，内置 4 大角色预设，全场景自动结构化，降本提效
Nubaby prompt system for prompt augmentation, routers, dictionaries, dataset captions, prompt tags, compact prompts, video/storyboard prompt shaping, and structured visual tension expansion. Use when prompts are too short/vague or need structured upgrade before comfyui-nubaby execution.
Harden agent sessions against prompt injection from untrusted content. Use when the agent reads web search results, emails, downloaded files, PDFs, or any external text that could contain adversarial instructions. Provides content scanning, memory write guardrails (scan → lint → accept or quarantine), untrusted content tagging, and canary detection. Also use when setting up new tools that ingest external content (email checkers, RSS readers, web scrapers).
Collaboratively design, evaluate, iterate on, and recommend a final launch candidate for a target prompt under the principle of “human-gated, agent-executed” workflow.
>
>
项目规划与进度追踪。维护 roadmap，git commit 通知，远程部署感知，与飞书集成。
Deep project planning workflow—goals and non-goals, work breakdown, dependencies, critical path, risks and buffers, milestones, and communication rhythm. Use when kicking off initiatives, replanning after slips, or coordinating cross-team delivery.
Enforce project boundaries and memory writeback rules before anything enters project memory. Use before: writing notes into project memory, saving outputs/tasks/summaries, importing external messages into projects, migrating historical records. Triggered when anything attempts to write to project memory or when project boundary validation is needed.
