claims-drafting
wanshuiyin
Draft patent claims for an invention. Use when user says \"撰写权利要求\", \"draft claims\", \"写权利要求书\", \"claim drafting\", or wants to create patent claims. The core skill o…
15.6KGitHub
OPENAGENTSKILL / DIRECTORY
AI Agent Skills
Find a skill for your next task. Explore tools for Codex, Claude Code, Cursor and more.
Results · “ocr-python”
113–128 / 195
More filters · 1
Candidates in this shortlist, not the full registry. GitHub stars belong to repositories, not individual skills.
Results: 195
ablation-planner
wanshuiyin
Use when main results pass result-to-claim (claim_supported=yes or partial) and ablation studies are needed for paper submission.
15.6KGitHub
think
AgriciDaniel
Apply the Fable-derived 10-stage OBSERVE, OBSERVE, LISTEN, THINK, CONNECT, CONNECT, FEEL, ACCEPT, CREATE, GROW loop to consequential or ambiguous reasoning and decisions…
14.5KGitHub
Forge Film
F-R-L
Multi-model DAG-driven parallel AI film generation — parallel speedup scales with scene independence; Generate film scenes simultaneously instead of one by one; "把影视生成的执…
AutomationSkill source unconfirmed
647GitHub
hive.context-preservation
aden-hive
Proactively extract critical values from tool results into working notes before automatic context pruning destroys them.
11KGitHub
hive.note-taking
aden-hive
Maintain a free-form scratchpad of decisions, extracted values, and open questions so context pruning doesn't lose anything you still need.
11KGitHub
Autopy
autopilot-rs
A simple, cross-platform GUI automation module for Python and Rust.
AutomationSkill source unconfirmed
980GitHub
Semi Auto Image Annotation Tool
virajmavani
Anno-Mage: A Semi Automatic Image Annotation Tool which helps you in annotating images by suggesting you annotations using user-defined labels
AutomationSkill source unconfirmed
592GitHub
hunt-captcha-bypass
elementalsouls
Hunt CAPTCHA Bypass — 6 distinct patterns: (1) CAPTCHA field simply omitted from the request (server-side validation absent), (2) CAPTCHA token replayed from a solved ch…
4KGitHub
geo-content
zubair-trabzada
Content quality and E-E-A-T assessment for AI citability — evaluate experience, expertise, authoritativeness, trustworthiness, and content structure
10.1KGitHub
screen-detox
kangarooking
当用户刷手机/短视频/社交媒体上瘾、感觉空虚、想戒断多巴胺零食时调用。 核心理念: 所有屏幕活动与更少幸福相关(作者断言无例外); 屏幕=用长期后果换短期快感的多巴胺零食; 用习惯替换五步戒断。 不适用于: 工作需要屏幕的职业场景(区分工作屏幕与消费屏幕)。 Triggers: 刷手机/上瘾/短视频/社交媒体/多巴胺/戒断/屏幕时间/s…
9.3KGitHub
happiness-skill
kangarooking
当用户问「怎么才能更幸福/为什么得到了还不满足/怎么减少焦虑」时调用。 核心理念: 幸福是缺憾感清空的默认状态, 是可训练的技能; 欲望是与自己的契约(得到前不快乐), 同时只留一个重大欲望; 活在当下。 不适用于: 临床抑郁等需要专业治疗的场景(本书方法不能替代医疗)。 Triggers: 幸福/不快乐/欲望/焦虑/知足/活在当下/h…
9.3KGitHub
reading-metaskill
kangarooking
当用户想养成阅读习惯、问「读什么书/怎么读」「如何学习新领域/怎么入门某学科」时调用。 核心理念: 阅读是终极元技能; 读你所爱直到爱上阅读, 没有读完义务; 读原著与经典优先; 以教促学; 每天1-2小时即可进入极少数人行列。 不适用于: 具体某本书的书评、考试备考资料选择。 Triggers: 阅读/读书/怎么学习/入门/原著/书单…
9.3KGitHub
monkey-mind-meditation
kangarooking
当用户脑子停不下来、焦虑反刍、想学冥想/提升专注力时调用。 核心理念: 内心独白(心猴)是失控程序不是"我"; 用调试模式逐条观察念头, 意识到即失去控制; 冥想=收件箱归零/心灵间歇性禁食。 不适用于: 严重精神疾病急性发作(先就医); 需要立刻处理的实际问题(先做事)。 Triggers: 冥想/焦虑/脑子停不下来/胡思乱想/专注/…
9.3KGitHub
judgment-training
kangarooking
当用户需要做方向性判断、评估「该往哪走/这事靠谱吗」、或想提升决策能力时调用。 核心理念: 判断力(知道行为长期后果)比努力重要; 清晰思考=从基础学科重建推理; 收集心智模型(复利/委托代理/可证伪性/基础数学)。 不适用于: 需要立即执行的具体任务步骤。 Triggers: 判断力/方向/第一性原理/心智模型/思维模型/判断靠不靠谱…
9.3KGitHub
decision-heuristics
kangarooking
当用户在重大选择上纠结（换工作/买房/搬城/合伙/结婚）、列了利弊表还是拿不定主意时调用。 核心理念: 无法决定就答否; 三个重大决定(住哪/和谁/做什么)值得花一两年; 两个均等选择选短期更痛苦的路。 不适用于: 日常琐碎选择（晚饭吃什么）、信息查询。 Triggers: 纠结/拿不定主意/要不要/该不该/利弊/decision/he…
9.3KGitHub