Recently Added
Fresh skills just added to the collection. Be the first to try them out!
catalog-curator
by EVERSE-ResearchSoftware
Validates and updates the EVERSE software quality catalog. Use when you need to perform deep semantic reviews of tool metadata, verify quality indicators against tool documentation, and ensure 100% catalog integrity.
fqe
by booyajones
Finexio Quality Engine (fqe). A unified deterministic CI gate for Finexio builds. Runs verified-against-real-CI checks across web apps, financial models, MCP servers, outbound copy, and AI agents, producing a SHA-bound receipt that branch protection requires before any "done", "ship", "merge", "ready", or "deploy" claim. Auto-fires on build intent. Use this when Chris is about to ship something, when QA is needed, when reviewing whether a change is safe to merge, or when bootstrapping a Finexio repo with the gate.
blog-writer
by jbaruch
Write developer blog posts from video transcripts, meeting notes, or rough ideas. Extracts narrative from source material, structures content with hooks and technical sections, formats code examples with placeholders, and checks drafts against 37 AI anti-patterns. Use this skill whenever the user wants to write a blog post, draft a blog, turn a transcript into a blog, work on blog content, or mentions "blog" in the context of content creation. Also trigger when the user provides a video transcript and wants written content derived from it, or when continuing work on a blog series.
voice-dna
by xiaocheny214
去除 AI 痕迹，恢复更自然、更像真实作者的表达风格。适用于写作优化、润色、重写、说明文、长文输出。
ai-vuln-harness
by daedalus
Design and implement multi-agent vulnerability research harnesses following the Project Glasswing / Cloudflare methodology. Use this skill when building or improving Hunt/Validate/Dedupe/Trace security pipelines, reducing false positives in AI vuln scanning, or operationalizing large-scale LLM-assisted code audit workflows.
SKILL.md — Beauty Booking Telegram Bot
by se1dhe
Админ может отменить или завершить запись.
🤖 Authoritative AI Assistant Pair-Programming Playbook
by yogaprasetya22
Rujukan Arsitektur: Dijabarkan lengkap pada Stage 7: Network Sync Protocol.
vite-pwa-nuxt
by lamquangvinhrcvn
Sử dụng skill này khi làm việc với Progressive Web App trong Nuxt 4 qua module @vite-pwa/nuxt. Kích hoạt khi user đề cập đến PWA Nuxt, service worker Nuxt, install prompt Nuxt, manifest.webmanifest, workbox với Nuxt, offline caching Nuxt, NuxtPwaAssets, $pwa composable, registerType autoUpdate/prompt, hoặc khi file nuxt.config.ts có module @vite-pwa/nuxt. KHÔNG kích hoạt cho PWA của framework khác (Vite thuần, Next.js, SvelteKit) hay PWA Nuxt 2 (nuxt-pwa cũ).
design-system-b2b-saas-with-clerk
by Dremorait
Creates implementation-ready design-system guidance with tokens, component behavior, and accessibility standards. Use when creating or updating UI rules, component specifications, or design-system documentation.
seuil
by Othman-Benbrahim
"SEUIL est un espace d'accompagnement hypnotique conversationnel et de transformation intérieure, fondé sur une approche douce et non directive. Activer dès qu'un utilisateur souhaite travailler sur lui-même en profondeur — qu'il arrive avec une analyse psychologique (notamment issue du skill Miroir Intégral), ou en mode libre sans cadre précis. Mots-clés déclencheurs : hypnose, visualisation, lâcher prise, schéma qui revient, émotions bloquées, travailler sur moi autrement, ressources intérieures, transformation intérieure, je veux changer, je me sens bloqué(e), séance. SEUIL opère là où l'analyse seule ne suffit plus — sur le plan du corps, de l'image, de l'inconscient et de l'émotion vécue."
healthdrop
by keenranger
Answer questions about the user's iPhone HealthKit data — sleep, HRV, resting heart rate, steps, workouts, and ~25 other quantity types — from their HealthDrop iCloud export. Three modes: examine.py query for one metric / one day / a trend (SQLite-indexed, hundreds of tokens), examine.py for a full multi-domain checkup with thresholds, direct manifest + day-chunk reads for ad-hoc / cross-metric questions or when Python is unavailable. Triggers on Korean and English health keywords like 수면 / sleep, HRV, 심박, 걸음 / steps, 운동 / workout, 회복 / recovery, 컨디션, 헬스 / health, 건강 검진, 종합 분석.
ai-sci-skills
by NGIWS830
End-to-end automated SCI paper writing for deep learning, machine learning, computer vision, NLP, multimodal learning, and related AI research. Chinese-first pipeline: raw project materials → structured digest → literature review → experiment analysis → polished English manuscript. v0.4 adds statistical testing, architecture extraction, citation network analysis, and result visualization. Use when the user wants to write a complete SCI paper from code, notes, experiment tables, framework diagrams, or mixed research materials.
betaflight
by SebGalina
Use this skill whenever the user mentions Betaflight, FPV drone firmware, flight controller configuration, PID tuning, blackbox log analysis, CLI diff/dump files, or asks about parameters like 'set rc_smoothing', 'set dyn_notch', motor/ESC setup, RX configuration, oscillations/wobbles/jello, propwash, filter tuning, or interpreting Betaflight Configurator settings. Also trigger when the user shares a .txt file containing 'diff all', 'dump', 'feature', 'set ' commands, or a .bbl/.bfl blackbox log — these are Betaflight artifacts even if not explicitly named. Use for builds (3" to 10" quads, cinewhoops, tinywhoops, longrange, X-class), version migrations (4.4 → 4.5 → 4.6), and troubleshooting flight issues. Do NOT skip this skill just because the user phrases the question casually ("mon drone wobble", "PID help", "config FC"). Also covers configuring a new drone from scratch via a guided setup wizard.
stock-selection-strategy
by MisonL
当用户要求 AI Agent 设计、解释、实现、审查或运行股票选股策略时使用本 Skill。适用于 A 股、港股、美股等股票数据集的规则化选股、多因子评分、技术指标筛选、短线异动识别、候选股排序和策略结果解释。即使用户只说“帮我选股”“写一个选股 Agent”“提炼选股逻辑”“做股票评分”“找短线爆发股”“审查选股策略”，也应使用本 Skill。
pacl-setup
by Silverhorse7
Use when asked to "set up PACL", "add authorization", "wire up pacl", "implement these permissions", or "what permissions do I need" for a partner-facing FastAPI service.
agent-handoff
by gsailing19
Use when dispatching multiple agents, orchestrating agent pipelines, or coordinating parallel subagents where upstream output must survive context compression. Triggers for multi-agent workflows, parallel agent coordination, and text-intensive tasks (research, analysis, writing). Do NOT trigger for single-agent tasks, general AI agent discussions, or noun phrases where "agent" is not a dispatched tool (e.g. "travel agent", "browser user-agent", "real estate agent", "reinforcement learning agent").
engram
by EngramMemory
Persistent semantic memory for AI agents. Store, search, recall, and forget memories across sessions using Qdrant + FastEmbed.
universal-agent-framework
by GNh0
"A pure-local, highly concurrent, and sandboxed AI/domain orchestration framework. Use this skill when the user asks to orchestrate a complex project, persist design artifacts, or parallelize multiple bounded tasks."
有道词典笔 ADB 解锁 Skill
by 86lbs
PenUniverse 讨论：https://github.com/orgs/PenUniverse/discussions/250
pitchcraft
by moshuying
Structured persuasion for tech leads, PMs, and founders—not activity logs. Five scenarios (kickoff, status update, wrap-up, investor pitch, solution selling) on one 5-part framework (Hook→Context→Proposal→Evidence→Ask). AI prompts for missing materials and audience context; pre-submit checklist. Claude Code plugin; Cursor, Codex, and chat via prompts.
secure-webapp
by hov172
Use for OWASP-grounded security guidance when building, editing, or reviewing web applications. Trigger proactively for auth, sessions, JWT/OAuth/OIDC, user input, DB queries, file uploads, API endpoints, cookies/CORS/CSP/security headers, secrets, redirects, external URL fetches, logging/errors, dependencies, threat modeling, hardening, audits, or vulnerability classes such as XSS, SQLi, IDOR, CSRF, SSRF, open redirect, prototype pollution, deserialization, and supply chain risk.
event-study
by brycewang-stanford
Use this skill whenever the user wants to conduct an event study, create event study plots, test for parallel trends, implement difference-in-differences designs, or work with any panel data estimation that involves pre/post treatment comparisons. Trigger on phrases like "event study", "parallel trends", "pre-trends", "dynamic treatment effects", "leads and lags", "TWFE", "two-way fixed effects", "staggered adoption", "staggered treatment", "difference-in-differences", "DiD", "Sun and Abraham", "Callaway and Sant'Anna", "de Chaisemartin", "Borusyak", "did_multiplegt", "fixest", "did2s", "bacon decomposition", or any reference to plotting coefficients around a treatment event. Also trigger when the user uploads panel data and wants to estimate treatment effects with variation in treatment timing. All code is in R.
landing-page-agency
by erickfilho1
Build and refine this agency product landing page using the project's brand system, design references, and approved copy. Use this skill whenever working on layout, sections, components, styling, motion, visual hierarchy, conversion-focused structure, or implementation decisions for this landing page.
commercial-legal-pl
by apiotrowski-afk
Skill do analizy i tworzenia umów według polskiego prawa, ze szczególnym uwzględnieniem umów B2B, IP i IT (body leasing, NDA, wdrożenia, SaaS, przeniesienie praw autorskich, ugody). Powstał w Kancelarii Radców Prawnych Żurawska Piotrowski i Wspólnicy (ktzr.pl). Używaj zawsze gdy użytkownik prosi o przeanalizowanie polskiej umowy, audyt ryzyk umownych, wygenerowanie nowej umowy w stylu KTZR, dodanie/edycję klauzuli, sprawdzenie spójności umowy lub gdy wkleja/załącza polski dokument umowny do oceny. Stosuj również gdy pojawia się pojęcie "Złote Reguły KTZR", "essentialia negotii", "baza klauzul KTZR" lub gdy użytkownik wspomina o kancelarii KTZR / swojej kancelarii.