Directory
All AI skills. 6,133 and counting.
6,133 skills
Garry Tan
Gstack
Garry Tanplan-eng-review
Eng manager-mode plan review. (gstack)
Composioraffle-winner-picker
Picks random winners from lists, spreadsheets, or Google Sheets for giveaways, raffles, and contests. Ensures fair, unbiased selection with transparency.
Ryze-AI-Adgentrank-tracking
Rank tracking without a tracker subscription — position movers between any two periods from real Search Console data. Use when asked "how are my rankings", "what moved this week/month"…
dzhngratchet-files
Ratchet source file size so every file stays small enough for an agent to read whole: find every file over a token budget, split oversized files by concept, and set up the pre-commit…
muratcankoylanreasoning-trace-optimizer
Debug and optimize AI agents by analyzing reasoning traces, context degradation, tool confusion, instruction drift, repeated task failures, and performance regressions.
brycewang-stanfordresearch-proposal
Generate academic research proposals for PhD applications. Use when user asks to "write a research proposal", "create PhD proposal", "generate research plan", "撰写研究计划", "写博士申请", "doctoral…
Garry Tan
Gstack
Garry Tanretro
Weekly engineering retrospective. (gstack)
muratcankoylanself-improvement-loops
This skill should be used when the harness, scaffold, workflow, or optimizer itself is the optimization target: recursive self-improvement (RSI) loops, meta-harnesses, self-improving…
muratcankoylanself-managed-context
This skill should be used when a model gets read-write control over its own live context window instead of a harness-scheduled compaction policy: the context exposed as an editable file the…
Ryze-AI-Adgentseo-audit
Full SEO audit of a site from its real Search Console + GA4 data — indexation health, CTR anomalies, decaying pages, striking-distance keywords, quick wins. Use when asked to "audit my…
Ryze-AI-Adgentseo-vs-ads
Find money leaking between search ads and SEO — queries you pay for while already ranking organically, and paid queries with no organic coverage. Use when asked "am I paying for clicks I'd…
zenstory-aishort-drama-develop
将中文小说、短剧或漫剧想法、梗概、改编材料、已有系列笔记或多集完整剧本发展成可追溯的改编方案、戏剧方向、创作简报、导演阐述、故事引擎与分集地图，并按题材与制作形态（画风）选择写法。用户提出“导入小说做短剧”“从多集整稿生成/补分集地图”“开发短剧/漫剧”“做故事设定/系列大纲/分集规划”“写导演阐述”“这个题材怎么写”“定画风/制作形态”…
zenstory-aishort-drama-edit
将已生成的短剧镜头剪成成片，记录入出点、镜序、声音、字幕与交付规格。用于套剪、加字幕、统一响度、调整节奏或导出精修素材；需要补素材或修改故事时转回对应创作阶段。
zenstory-aishort-drama-image-prompts
为短剧人物、造型、地点、道具和状态编写或修改可直接复制的图片提示词 Markdown。用户提到角色设定图、三视图、参考图、场景板、道具图、风格帧、Look Development、状态变体或局部编辑提示词时使用；不生成图片，也不调用供应商。
zenstory-aishort-drama-knowhow
维护者专用的短剧 know-how 学习、验证与生命周期治理。仅在维护者明确要求从其当前会话提供的授权只读文本源学习完整短剧项目链，并把私有观察逐步转成去标识、去复刻、经盲测与独立审查的公共 reference、rubric 或 synthetic fixture 候选时使用；不用于普通创作、公开运行时取数、媒体生成或粗略数据分析。
zenstory-aishort-drama-novel-analyze
把长篇小说、连载网文或多集散稿拆成可追溯的原著分析：章节索引、改编价值快评、逐章功能提取、剧情单元与节奏聚合、人物与设定归并，最后给出改编价值判定与分集候选，交给 $short-drama-develop 立契约。用户说“导入这本小说”“拆这本书”“分析原著”“这本书能不能改短剧”“先看看值不值得拆”“把长篇拆成分集候选”，或直接给出小说…
zenstory-aishort-drama-produce
在创作者明确确认后，执行短剧项目的图片、视频、TTS/配音或时间线音乐生产任务，并把结果与精简运行记录存回项目。用户说“生成这张图/这段视频/这句配音/这段配乐”“开始跑图/跑视频/合成语音/生成音乐”“把已确认提示词送去生产”，或要求批量执行已确认媒体任务时使用；不负责创作提示词、镜头、台词、歌词或声音身份，也绝不把预览、继续、预算说明或既有接受状态当作本次付费生产确认。
zenstory-aishort-drama-review
审查短剧项目中的原著分析、故事、剧本、视觉设定、图片提示词、分镜、冻结关键帧、视频提示词和已有媒体。用户提出“审稿/检查剧本”“检查资产或连续性”“检查图片/视频提示词”“检查原著分析”“审查模板感”“根据生产观察做项目校准”时使用；只写审查问题、结论和修订要求，不代替负责人修改来源文件。
zenstory-aishort-drama-storyboard
把中文短剧剧本和视觉设定写成有戏剧职责、连续性边界与冻结关键帧提示词的分镜 Markdown。用户提出“拆分镜/设计镜头/做镜头表”“场次视觉计划/调度故事板”“比较导演方案”“写首帧/关键帧提示词”或检查轴线、站位、视线、持物连续性时使用；不生成媒体。
zenstory-aishort-drama-video-prompts
把短剧分镜和冻结关键帧写成可直接复制的视频提示词 Markdown，也可按用户要求写时间线配乐/主题曲意图。用户提到文生/图生视频动作、人物表演、运镜、口型、环境运动、镜头时长、起止状态、把分镜转成视频提示词或写配乐提示词时使用；不生成媒体、不创作歌词、不改分镜边界。
zenstory-aishort-drama-write
编写或修订可拍摄的中文短剧、漫剧单集 Markdown 剧本，也负责保留作者原文并规范化现成剧本。用户提出“写/改一集短剧”“把大纲写成剧本”“优化场景/对白”“去模板感”“去 AI 味润色”“续写下一集”或提供剧本要求进入后续制作时使用；不负责资产、分镜、媒体提示词或终审。
muratcankoylanskill-template
Template for creating new Agent Skills for context engineering. Use this template when adding new skills to the collection.
tech-leads-clubsubagent-creator
Guide for creating AI subagents with isolated context for complex multi-step workflows. Use when users want to create a subagent, specialized agent, verifier, debugger, or orchestrator that…
Composiotailored-resume-generator
Analyzes job descriptions and generates tailored resumes that highlight relevant experience, skills, and achievements to maximize interview chances
ai-evals-coursevalidate-evaluator
Calibrate an LLM judge against human labels using data splits, TPR/TNR, and bias correction. Use after writing a judge prompt (write-judge-prompt) when you need to verify alignment before…
ai-evals-coursewrite-judge-prompt
Design LLM-as-Judge evaluators for subjective criteria that code-based checks cannot handle. Use when a failure mode requires interpretation (tone, faithfulness, relevance, completeness)…
dzhngxiaohei-illustrations
Generate Ian-style Xiaohei illustrations for articles, posts, blogs, Notion documents, workflows, methods, processes, structures, states, metaphors, and opinions. Use when the user asks for…
ReScienceLab
Opc Skills
ReScienceLabadd-new-opc-skill
Checklist and automation guide for adding a new skill to the OPC Skills project. Ensures all required files, metadata, logos, and listings are created before release. Use when adding a new…
Cloudflare
Skills
Cloudflareagents-sdk
Build, debug, or review Cloudflare Agents SDK applications using the agents package.
Google DeepMind
Science Skills
Google DeepMindalphagenome-variant-impact-score
Score, annotate, and analyze the functional impact of genetic variants using AlphaGenome Variant Impact (AVI) scores. Query variants in chr:pos:ref>alt format, annotate VCF/tabular…
AgriciDanielblog-audit
Full-site blog health assessment scanning all blog files for quality scores, orphan pages, topic cannibalization, stale content, and AI citation readiness. Runs canonical batch analysis…
AgriciDanielblog-brief
Create a content brief for ONE planned post: target and secondary keywords, search intent, template choice, competitor gaps from the live SERP, sourced statistics to include, section plan…
AgriciDanielblog-calendar
Build a dated monthly or quarterly editorial calendar: which posts to publish or review when, content mix, templates, distribution timing, and a material-change review queue. Use when the…
AgriciDanielblog-decay
Compare two Google Search Console page exports (current vs previous period) to flag pages whose clicks or impressions fell by a chosen threshold, with a triage hint (refresh, query shift…
AgriciDanielblog-geo
Audit one blog post file for AI-citation readiness (self-contained, sourced passages, entity clarity, structure, crawler access) and score it with an internal 0-100 heuristic plus…
AgriciDanielblog-locale-audit
Read-only audit of a folder of existing multilingual blog posts: translation coverage, parity, hreflang and canonical consistency, meta-tag parity, and stale translations, with a…