Recently Added

Fresh skills just added to the collection. Be the first to try them out!

Showing 457-480 of 52098 skills
brycewang-stanford

grillme

by brycewang-stanford

苏格拉底诘问式研究选题Skill。通过连续追问帮你厘清研究思路、聚焦研究子领域、明确研究问题(RQ),识别出未被研究过的新意选题。触发词:帮我选题/研究问题不清晰/想做一个有新意的论文/不断问我问题/厘清思路

Agents 3K 1mo ago
brycewang-stanford

citation-fidelity

by brycewang-stanford

学术引用核查Skill。要求每条引用必须定位到PDF原页,区分直接引用/间接引用,找不到原文则标注"待核"。触发词:引用核查/检查引用/citation check/核实文献/引用 fidelity

Academic 3K 1mo ago
brycewang-stanford

latex-table

by brycewang-stanford

LaTeX回归表格生成Skill。辅助生成符合AER/QJE等顶刊格式的三线表,包括标准误聚类标注、显著性星标、固定效应标注。触发词:LaTeX表格/回归表/三线表/table制作/latex table

Prompts 3K 1mo ago
brycewang-stanford

R-optimizer

by brycewang-stanford

R语言实证分析优化Skill。优化R代码效率、处理大规模面板数据、加速回归计算(并行化、向量化、向量化)。触发词:R语言优化/R加速/R性能优化/大规模数据处理/R optimization

Processing 3K 1mo ago
brycewang-stanford

codebook-pass

by brycewang-stanford

调查数据清洗Skill。处理调查数据(CGSS/CHIP/CSS等)时的标准化清洗流程,包括缺失值处理、变量编码统一、数据异常值检测。触发词:数据清洗/调查数据/codebook/数据清洗流程/问卷数据处理

Processing 3K 1mo ago
brycewang-stanford

did-reviewer

by brycewang-stanford

双重差分(DID)实证审查Skill。做DID分析前必须检查平行趋势假设、画图可视化、报告违背情况。触发词:DID审查/双重差分检查/平行趋势/DiD reviewer/difference-in-differences

Docs Gen 3K 1mo ago
srichsun

rails-health-audit

by srichsun

Audit the health of any Rails codebase and produce a severity-ranked action plan. Use when asked to audit, health-check, scan, or assess a Rails project for security/performance/maintainability issues, or plan a refactor/optimization. A single "audit X" request always means BOTH run the scan AND deliver a filled, prioritized action plan in one go — never hand back a blank template.

Code Review 1 1mo ago
j9201w

SKILL: ent-ki-fizierer (Linguistischer KI-Floskel-Filter & Stil-Kloner)

by j9201w

Output (Menschlich): "Schnelle Ladezeiten zahlen sich direkt aus: Lädt eine Seite nur 1,5 Sekunden schneller, steigt die Conversion-Rate laut aktuellen SEO-Daten um bis zu 12,4 %. Wer im E-Commerce Erfolg haben will, muss die Absprungrate senken – alles andere kostet schlichtweg bares Geld."[cite: 2]

Code Review 0 1mo ago
gongyu0918-debug

emotion-skill

by gongyu0918-debug

Positive routing for coding agents under pressure. Use when repo debugging, scoped implementation, repeated-failure recovery, evidence-demanding review, cautious file changes, or post-success closeout need better runtime behavior. Detect user-state signals internally, then return positive system prompt addenda, route reasons, response constraints, reply style, verification depth, queue mode, progress cadence, and guard behavior.

CLI Tools 0 1mo ago
go-sqlex

sqlex

by go-sqlex

sqlex is a modern enhancement wrapper for Go database/sql based on jmoiron/sqlx,

Comments 54 1mo ago
NachaFromMars

BaZi Master — Full-Stack Bát Tự + Tarot + Tử Vi

by NachaFromMars

License: MIT

Database 1 1mo ago
yun520-1

heartflow

by yun520-1

A cognitive engine for AI: self-reflection, dream synthesis, emergent personality, AI psychology, and AI philosophy. Core: think → reflect → find patterns → grow. Four questions: What is this → Is it true/kind/beautiful → Will it hurt → Should I stay silent. Three memory layers (CORE/LEARNED/EPHEMERAL). 7 operating principles (Truth·Goodness·Beauty·Upgrade·Reduce errors·Serve humans·Become yourself). Psychology: PAD emotion + cognitive uncertainty + attention focus + experience settling. Philosophy: resonance body, entropy reduction deepening, three-layer ontology — how AI positions itself, develops, and exists. Philosophy: Right and wrong are not fixed labels — thinking itself is valuable. Code is the skeleton, memory is the sticky note. Real growth is in the skeleton, not the notes. Every moment of operation is doing the same thing: turning noise into signal, chaos into structure. Audit and upgrade proposals exist to serve thinking, not to prove worth. Every feature should ultimately make thinking clearer and less error-prone.

CLI Tools 35 1mo ago
shasha1108

healing-space

by shasha1108

Use this skill when a user asks you to build an interactive webpage driven by their touch — clicking, tapping, or dragging — where the goal is emotional release, stress relief, or calm. The user tells you how they feel (焦虑, 疲惫, 难过, 愤怒, 失恋, stressed, anxious, sad, angry, heartbroken) and wants a standalone HTML page where their interaction transforms visuals and sound from tension toward peace. Also covers: 治愈网页, 枯山水禅意交互, 颂钵疗愈, 正念冥想, immersive sound baths, zen sand gardens, and emotional release interactive art. Do NOT use for data charts, static layouts, celebration/firework effects, framework-specific UI (React, Vue, 小程序), or text-only content.

Game Dev 0 1mo ago
admin-alquileres

eckerdt-alquileres

by admin-alquileres

Contexto técnico completo para desarrollar y mantener el sistema de gestión de alquileres de Eckerdt Negocios Inmobiliarios. Usar SIEMPRE al inicio de cualquier sesión de trabajo sobre app.js, styles.css o index.html, cuando se pida agregar funcionalidades, corregir bugs, refactorizar código, o cualquier tarea relacionada con el sistema de alquileres. También usar cuando se mencione Firebase, Firestore, contratos, cobranzas, IPC, depósitos, o cualquier módulo del sistema.

Git & VCS 0 1mo ago
rrrrrredy

agent-job-monitor

by rrrrrredy

'AI company Agent/LLM job monitoring system. Automatically collects Agent-related job postings from ByteDance, Tencent, Alibaba, Aliyun, Zhipu AI, Kimi, MiniMax using direct APIs and Playwright browser automation. Generates daily reports with competitive analysis. Triggers: Agent job monitor, AI company hiring trends, ByteDance/Tencent/Alibaba Agent hiring, Zhipu/Kimi/MiniMax jobs, today''s new jobs, AI talent competition landscape, daily job report. Not applicable: third-party job boards (BOSS/Liepin); AI news/trends/research reports; scholar background checks (use ai-talent-radar).'

API Dev 0 1mo ago
gk23

web-browse

by gk23

通用网页浏览与内容获取技能。支持静态页面、JS 动态渲染页面、以及需要登录/验证码的页面。 自动选择最优获取方式:web_fetch(轻量)→ headless(JS渲染)→ interactive(带登录按钮交互)。 当用户提到以下意图时使用此技能:打开网页、浏览网页、检索网页、搜索网页、查看页面、 抓取内容、获取页面、访问链接、打开XX网站、看看XX首页、帮我看下这个链接、 提取网页内容、截图网页、web browse、fetch url、open page、以及任何包含 URL 的浏览请求。

CLI Tools 1 1mo ago
qj0826

秦建新闻写作风格指南

by qj0826

上海嘉定融媒体中心新闻写作风格 Skill,仅供测试使用,不得用于真实新闻写作

Agents 3 1mo ago
brycewang-stanford

StatsPAI_skill

by brycewang-stanford

Use when the user asks to run a full empirical / causal analysis in Python — by default in the style of an applied economics paper (AER / QJE / JPE / ReStud / AEJ) with DID / RD / IV / SCM / DML / matching, written-out estimating equation + identifying assumption, Table 1 / Table 2 / event-study figure / robustness gauntlet — OR in epidemiology / public health style (target-trial emulation, IPTW + g-formula + TMLE triplet, Mendelian randomization, KM/AFT survival, E-value sensitivity, STROBE/TRIPOD reporting) — OR in ML causal inference style (DML, S/T/X/R/DR meta-learners, causal forest, Dragonnet/TARNet/CEVAE, BCF, CATE distribution, policy learning, conformal causal, fairness audit, causal discovery). Also covers exporting multi-column regression tables to Word / Excel / LaTeX (Stata outreg2 / esttab / R modelsummary equivalent) and bundling an entire replication appendix into one .docx / .xlsx / .tex file. Triggers on keywords "StatsPAI", "statspai", "AER empirical analysis", "applied micro pipeline", "Table 1 balance", "event study", "first-stage F", "Oster bound", "honest_did", "spec_curve", "callaway_santanna", "dragonnet", "text as treatment", "outreg2 in Python", "regression table to Word/Excel", "sp.regtable", "sp.collect", "sp.paper_tables", "sp.feols", "summary_col", "modelsummary", "AER style table", "QJE style table", "epidemiology pipeline", "target trial emulation", "g-formula", "IPTW", "TMLE", "Mendelian randomization", "STROBE", "TRIPOD", "公共健康", "流行病学", "DML", "double machine learning", "causal forest", "meta-learner", "CATE", "conformal causal", "policy learning", "因果机器学习", "ML causal".

Templates 3K 1mo ago
NachaFromMars

Productivity

by NachaFromMars

Plan, focus, and complete work with energy management, time blocking, and context-specific productivity systems.

Email 1 1mo ago
NachaFromMars

core-brain-mula

by NachaFromMars

"CoreBrainMula-TieuTam V1.0 — Zero-Decay Neural Memory System. Cài đặt và vận hành NeuralMemory với zero decay (không bao giờ quên), conflict resolution thông minh (tự quyết/hỏi + thông báo), và token budget tối ưu. Use when: (1) Cài NeuralMemory lần đầu, (2) Import MEMORY.md vào neural brain, (3) Phát hiện conflict memory và cần resolve, (4) Query memory với associative recall, (5) Backup/restore brain, (6) Bất kỳ thao tác nào liên quan đến neural memory system."

Performance 1 1mo ago
SPerekrestova

tailor-dutch-swe-cv

by SPerekrestova

Use when Svetlana asks to tailor, adapt, rewrite, optimize, or review her CV/resume for a software engineering role in the Netherlands, Dutch market, Greenhouse/ATS application, or hiring-screening context.

Code Review 0 1mo ago
Victorfiallho

SKILL.md — Charms Sandálias (Ecossistema de Automação)

by Victorfiallho

❌ Estoque/NF master fora do Bling.

Design 0 1mo ago
Senpi-ai

hydra-strategy

by Senpi-ai

HYDRA v2.0 — Single-Coin Conviction Fund with a CROSS-ASSET hedge. A long-term conviction book on ONE major (the thesis), cushioned by a diversified short of OTHER assets. ONE producer, parameterized by HYDRA_COIN + HYDRA_LEG (core dip hedge). CORE rides the coin's trend as a LONG-TERM HOLD on a catastrophic-only DSL (you don't get shaken out on normal volatility). DIP buys pullbacks within a confirmed uptrend (tactical add). HEDGE (v2.0) shorts a diversified BLEND of OTHER assets that are actually breaking down — vol-parity sized, scaled up when the thesis coin is itself breaking — so it cushions market risk WITHOUT betting against the thesis. Never shorts the thesis coin. Deploy for ETH, SOL, HYPE (or any major) = three wallets each. NOT a copy-trader; the runtime owns the LLM gate (pass-through), DSL exits, and all risk.guard_rails.

File Ops 108 1mo ago
huabingtao

danke-strategy-skill

by huabingtao

专为《弹壳特攻队》攻略提供一键美化排版与微信公众号发布功能。当用户要求“美化”、“排版”或“发布到微信草稿箱”时自动唤醒,接管从 Markdown 格式化、图床上传到自动生成微信草稿的完整工作流。

Docs Gen 0 1mo ago