← 返回
AI智能
Promptify Skill
Optimize prompts for clarity and effectiveness. Use when user says "improve this prompt", "optimize my prompt", "make this clearer", or provides vague/unstructured prompts. Intelligently routes to sub-agents for codebase research, clarifying questions, or web search as needed.
优化提示词以提升清晰度和效果。适用于用户说“改进这个提示词”、“优化我的提示词”、“让这更清晰”,或提供模糊/无结构提示词时。智能调度至子代理进行代码库研究、澄清问题或网络搜索。
tolibear
AI智能
clawhub
v3.1.0 1 版本 99482 Key: 无需
#latest
概述
版本历史 (1)
安全
概述
Prompt Optimizer Transform prompts into clear, effective ones. Model-agnostic.
Modifiers (parse from ARGUMENTS) +ask → Force clarifying questions+deep → Force codebase exploration+web → Force web searchNo modifiers? Auto-detect what's needed.
Auto-Detection Triggers Trigger Signals --------- --------- codebase-researcher "this project", "our API", specific files/functions, "integrate", "extend", "refactor" clarifier Ambiguous ("make it better"), multiple interpretations, missing constraints, vague pronouns web-researcher "best practices", "latest", external APIs/libraries, framework patterns, year references
Agent Dispatch When agents needed:
Announce which and why Run in parallel via Task tool (agents/ directory) Synthesize findings Optimize with gathered context Core Contract (every prompt needs all four) Element If Missing --------- ------------ Role Add persona with expertise Task Make action specific Constraints Infer from context Output Specify format/structure
Process If image : Analyze, incorporate contextDetect type : coding/writing/analysis/creative/dataConvert output→process : "Write X" → "Analyze → Plan → Implement → Validate"Strip fluff : "please", "I want you to", filler, apologiesApply contract : Verify all 4 elementsAdd structure : XML tags for complex promptsType Focus Coding : Specs, edge cases, frameworkWriting : Tone, audience, lengthAnalysis : Criteria, depthCreative : Constraints, noveltyData : I/O format, edge casesOutput Optimized prompt in code block echo 'PROMPT' | pbcopy2-3 sentence explanation
版本历史
共 1 个版本
v3.1.0
当前
2026-03-28 10:56 安全 安全
安全检测
腾讯云安全 (Sanbu)
安全,无风险
查看报告
🔗 相关推荐
ai-intelligence
ivangdavila
自我反思+自我批评+自我学习+自组织记忆。智能体评估自身工作、发现错误并持续改进。
★ 1,350
📥 317,716
ai-intelligence
pskoett
捕获经验教训、错误和纠正,以实现持续改进。使用时机:(1)命令或操作意外失败;(2)用户纠正……
★ 4,056
📥 796,118
security-compliance
tolibear
在 Abstract 链上无头玩 Blinko(链上 Plinko),用于代理玩游戏、查统计、看排行榜、追踪蜂蜜奖励,完整处理提交‑揭示流程,含 API 认证、链上创建、模拟与结算。
★ 2
📥 1,779