提示词
提示词工程与模板
example-skill
iterate
Example skill published from iterate's root skills directory
undervalued-stock-screener
Geeksfino
扫描A股市场，筛选基本面强劲但市值被低估的上市公司。当用户询问低估值股票、价值投资筛选、A股便宜股票、低PE或低PB公司、基本面强但被低估的公司、或要求运行估值筛选器时使用此技能。
sector-rotation-detector
Geeksfino
通过分析中国宏观经济指标和经济周期定位，识别A股市场行业轮动信号，判断未来6–12个月哪些行业可能跑赢或跑输大盘。当用户询问行业轮动、宏观驱动的板块配置、经济周期投资、超配或低配哪些行业、利率/通胀对行业的影响、或A股宏观投资策略时使用此技能。
oracle
edmundmiller
Use Oracle to bundle prompts + files for another AI (GPT 5 Pro, etc.) when stuck, debugging, or reviewing. Also covers self-improvement — codifying learnings into agent memory and noting tool improvement ideas.
codex-code-review
sd0xdev
"Code review using Codex MCP. Use when: PR review, code audit, second opinion on changes. Not for: doc review (use doc-review), security audit (use security-review). Output: severity-grouped findings + merge gate."
codex-architect
sd0xdev
"Codex architecture consulting. Use when: designing features, evaluating architecture, getting second opinion on design. Not for: implementation (use codex-implement), code review (use codex-code-review). Output: architecture advice + design recommendations."
honcho-integration
edmundmiller
Integrate Honcho memory and social cognition into existing Python or TypeScript codebases. Use when adding Honcho SDK, setting up peers, configuring sessions, implementing the dialectic chat endpoint for AI agents, or wiring Honcho into bot frameworks (nanobot, openclaw, picoclaw, etc).
acpx-claude
edmundmiller
Hand off a bounded implementation or review pass to Claude through ACPX.
claude-skill
myysophia
Use when user asks to leverage claude or claude code to do something (e.g. implement a feature design or review codes, etc). Provides non-interactive automation mode for hands-off task execution without approval prompts.
all_tools
htlin222
List All Tools. Use when user wants to see available tools or needs a tool reference.
makefile-for-telegram
htlin222
Generate a Makefile for Telegram bot projects with LaunchAgent service management. Use when setting up a new Telegram bot project or adding service management to an existing one.
release
joelhooks
Handles version bumps and npm releases for the swarm-tools monorepo (opencode-swarm-plugin, claude-code-swarm-plugin, swarm-mail, swarm-queue). Use when: creating changesets, bumping versions, preparing releases, checking release status, debugging publish failures, verifying npm packages, or merging release PRs. Triggers: "release", "publish", "changeset", "bump version", "ship it", "new version", "create a release", "check npm", "verify publish", "/release"
ideaverse-enrichment
mrfelton
Systematically add new knowledge to Ideaverse vaults while maintaining consistency. Use when assimilating new information, extracting concepts from sources, processing research, integrating learned knowledge, detecting duplicates, or classifying knowledge types. Triggers on requests like "add this to my vault", "process this article", "integrate this knowledge", "what type of knowledge is this", or "check for duplicates".
chinese-copyright-application
okooo5km
中国软件著作权申请材料生成工具，直接输出 LaTeX 源文件并编译为 PDF。自动分析项目代码，生成著作权登记申请表、源程序文档（前后各30页共60页）、用户手册、设计说明书四份材料，含页眉页脚、截图占位、信息一致性校验。适用于微信小程序、Web应用、移动App、桌面应用等各类软件项目。当用户提到软件著作权、软著申请、版权登记时必须使用此 Skill。当用户要为任何软件项目准备著作权材料、生成软著文档时也应使用。
sketch-image-prompt
okooo5km
Transforms article content or summaries into minimalist hand-drawn style JSON prompts for AI image generation tools. Use this skill whenever the user wants to create any kind of visual from text content — including banners, article illustrations, inline diagrams, infographics, or concept visuals. Trigger on requests like "turn this into a visual", "create an image prompt", "make an illustration for this", "generate a diagram from this article", "I need a sketch for this section", or any request combining content analysis with image/visual prompt generation. Always use this skill when the user provides text content and wants an AI-ready image prompt output.
skill-developer
diet103
Create and manage Claude Code skills following Anthropic best practices. Use when creating new skills, modifying skill-rules.json, understanding trigger patterns, working with hooks, debugging skill activation, or implementing progressive disclosure. Covers skill structure, YAML frontmatter, trigger types (keywords, intent patterns, file paths, content patterns), enforcement levels (block, suggest, warn), hook mechanisms (UserPromptSubmit, PreToolUse), session tracking, and the 500-line rule.
prompt-version-editor
WiseWong6
严格变更控制下编辑、版本化并存储提示词。用于用户要求小改/局部优化/补丁式修订、修复提示词失败、添加或维护版本头、对比版本，或基于输入/思路/输出诊断问题时。强制版本控制、作者签名，并将版本保存到 /Users/wisewong/Documents/Developer/prompts。
Skill: prompt-transparency
strikersam
instructions are active at any given time.
Skill: prompt-library
strikersam
docs-sync — general documentation sync
configurator-recipes
saleor
"Pre-built store configuration templates for common business types. Use when asking about store templates, example configs, fashion/electronics/subscription setup, or starting points."
humanize-chinese
swaylq
中文去 AI 腔一整套（装完即用，零 API Key —— 装了本 skill 的 agent 自己就是那个 LLM）。 六个流程：① 生成即去 AI —— 写中文时按本 skill 的写作指南落笔，初稿就不带 AI 腔； ② 复查改写 —— 产出后对照本 skill 的清单再过一遍，定点拆模板句式； ③ Python 词语替换 —— ./humanize replace 按文体自动路由词表（学术 120+ 条 / 通用 220+ 条），只做短语级、只在子句边界替换，改完自动核对数字/专名/段落； ④ Claude 腔转英文 —— 把 Claudish（Claude 助手腔英文）改写成平实英文， 规则提炼自 gvzdv/claudish-to-english； ⑤ 去水印 —— ./humanize watermark 扫清零宽字符/双向控制符/同形替身， 并对照 guillaumemeyer/watermarks-remover 说明统计水印的边界； ⑥ 纠错顺句 —— 修错词、病句、标点，拗口和用词不准处轻手顺一顺；改动范围有硬校验。 另有检测（0-100 分）、风格转换、学术降重等 CLI。 Use when user says: "去AI味", "降AIGC", "人性化文本", "humanize chinese", "AI检测", "AIGC降重", "去除AI痕迹", "文本改写", "论文降重", "知网检测", "维普检测", "AI写作检测", "让文字更自然", "detect AI text", "humanize text", "make text human-like", "去ai化", "改成人话", "去机器味", "长文本改写", "小说改写", "写一篇", "claudish", "claudish to english", "去水印", "watermark remover", "remove watermark"
declaude-en
swaylq
把 Claude 腔的英文（Claudish）改写成平实自然的英文。六段流水线的第四段， 是英文稿的分支：中文稿不走这一段，中文的去 AI 腔走第一、二段。 规则提炼自开源项目 gvzdv/claudish-to-english（2.4k star）的内置改写 prompt， 由 agent 直接执行，不需要装它的插件。
engines
atrislabs
"Dispatch work to an installed terminal agent or named Atris engine profile. Supports Atris Fast, Claude, Codex, Cursor, Fable, Composer, Haiku, Devin, Grok, and Antigravity (agy). Triggers on: use codex, use cursor, use devin, use grok, use agy, use antigravity, use fable, use claude, use atris, engine, dispatch to, worker agent, second opinion build."
write-cn
swaylq
写中文的时候直接绕开 AI 腔，而不是写完再洗。给 LLM 当写作指令用：喂进题目和文体， 产出的初稿就已经没有模板句式、没有价值拔高骨架、没有等厚段落。 这是六段流水线的第一段。第一段决定文章有没有人味，后面几段只能修，补不出来。 这份文件本身刻意写成它要求的那种中文 —— 指令文档的版式和语气会被模型当范文模仿， 一份满是加粗和编号清单的规范，教出来的就是加粗和编号清单。