Recently Added
Fresh skills just added to the collection. Be the first to try them out!
paperproof-protocol
by PaperProofLabs
Operate the PaperProof protocol for AI agents and developer assistants. Use when a user asks to publish, update, query, verify, inspect, or explain PaperProof artifacts, versions, comments, governance, native prompts, Agent Memory registrations, Walrus content, Sui package/object bindings, wallet readiness, or SDK-based PaperProof workflows. Prefer protocol, SDK, Sui, Walrus, and indexer interfaces over browser automation or website clicking.
tazkia-design
by galihsidik86
Use this skill to generate well-branded interfaces and assets for STMIK Tazkia's SIAKAD (academic information system), either for production or throwaway prototypes/mocks/etc. Contains essential design guidelines, colors, type, fonts, assets, and UI kit components for prototyping.
phase2-data-qa
by EdwardAiyw
"二期数据质检：LLM 驱动质检，支持 QA 表中间层（原表只读→QA表质检→回写原表）和 Wiki/Sheet 点行质检，结果写回飞书表格。"
czsc-ccxt-analysis
by Lzh-xbccz
"缠论技术分析 — czsc官方全API，CCXT数据源，多级别联立，lightweight-charts可视化+自动Markdown报告。触发: 缠论/czsc/中枢/分型/笔"
snaptidy
by chicogong
Use when organizing, deduplicating, importing, auditing, repairing, or reporting on macOS photo and video collections, including folders, Photos.app libraries, external drives, Android imports, iCloud placeholders, EXIF or GPS metadata, Live Photos, corrupted media, quality scoring, 整理照片, 照片去重, 整理相册, 写真整理, or 사진 정리.
world-cup-match-prediction
by 597844571
Use this skill to analyze and predict FIFA World Cup football matches with a frozen market-value framework and 10-dimension football model, including market de-vig probabilities, World Cup qualifier/continental cup formal-match strength, softmax probability correction, EV, Kelly/risk, Sporttery/中国体彩玩法 mapping, score ranges, upset triggers, tactical matchup, and confidence. Use especially when the user asks in Chinese about 世界杯预测, 胜平负, 比分, 爆冷, 盘口思路, 体彩下注建议, 串关, 总进球, 大小球, 回测, 小组赛形势, 淘汰赛预测, or match-by-match football forecasting.
Gin
by clawvpsai
Production-grade Gin (Go) web framework development — build robust APIs and web apps without common pitfalls.
asciivideo
by Rudigerwry263
Generate command-line / terminal-style animated videos built entirely from characters - arrange ASCII & keyboard symbols into text, creatures, mascots, logos and borders on a black phosphor-glow canvas, then render deterministically to MP4. Ships a Python engine (charvid) with a scene timeline; element types (block-letter banners, ASCII-art sprites, loading bars, particle fields, decorative borders, symbol grids, timers); entrance animations (typewriter, scatter-assemble, scramble-decode, wipe, fade, slide); idle motion (blink, bob, flicker, drift); a terminal-green / white / orange / blue palette; and an ffmpeg renderer. Use when the user asks for an ASCII / character / 字符 animation, a terminal or CLI-aesthetic video, kinetic ASCII art, a symbol-built logo or mascot, a "code-feel" 代码感 visual, or wants to turn text / a figure / a logo into a glowing character-grid animation.
herdr
by motionharvest
"Control herdr from inside it. Manage workspaces and tabs, split panes, spawn agents, read output, and wait for state changes — all via CLI commands that talk to the running herdr instance over a local unix socket. Use when running inside herdr (HERDR_ENV=1)."
imaging-data-commons
by ImagingDataCommons
Query and download public cancer imaging data from NCI Imaging Data Commons using idc-index. Invoke for any question about IDC collections, cancer imaging datasets, DICOM data access, radiology (CT, MR, PET) or pathology AI training sets, metadata queries, visualization, or license checks — even when the user doesn't explicitly mention "IDC". No authentication required.
hipocampo-protocol
by carrasquelalex1
Protocolo de memoria dual con Sparse Selective Caching (SSC). Persiste en memoria_vectorial y memory_items con búsqueda semántica progresiva.
hookradar-creative-intelligence
by Anagogic-blastinggelatin157
Use when researching competitors, paid ads, Meta Ad Library creatives, TikTok ads, Instagram/TikTok organic videos, HookRadar MCP data, creative trends, AI creative analysis, reports, downloadable ad/video assets, or shareable creative tables for marketing teams.
cub-strategy
by Senpi-ai
CUB v1.0 — Lion + Pre-IPO Hedge Fund. A variation of Lion that allocates ~90% of the budget to the Lion two-speed-market (K-shaped) AI long/short engine and ~10% to a pre-IPO ramp satellite. THREE books on three wallets, one producer. The LONG "haves" book + SHORT "have-nots" book ARE Lion (long the AI complex + HYPE/SOL, short the broad U.S. market via SP500 + laggard alts, trend-confirmed, conviction-sized) — the 90%. The PREIPO book auto-discovers pre-IPO perpetuals (IPOPs) on Hyperliquid XYZ by their funding signature (Lemur method) and LONGS the ones ramping into their listing (the SpaceX / Cerebras pattern) — the 10% high-optionality satellite that catches the next AI winner before it converts to a standard equity (at which point it graduates into the haves book). The 90/10 split is the operator's funding allocation across the three wallets, not a hardcoded constant. NOT a copy-trader; the runtime owns the LLM gate (pass-through), DSL exits, and all risk.guard_rails. CUB_LEG env selects the book (long short preipo).
lion-strategy
by Senpi-ai
LION v1.0 — Two-Speed-Market (K-Shaped) Cross-Asset Long/Short Hedge Fund. Two thematic books on two wallets, one producer. The LONG "haves" book longs the structural winners of a K-shaped world — the AI complex on Hyperliquid XYZ (trade.xyz: NVDA, AMD, MRVL, TSM, ASML, ARM, AVGO, CRWV, PLTR, ORCL, …) plus the crypto winners (HYPE large, SOL modest). The SHORT "have-nots" book shorts the laggards — the broad U.S. market via the SP500 index product (the "economy suffers" core) plus a curated, gated basket of laggard crypto alts. Both trend-confirmed on ABSOLUTE structure, with relative strength as a tiebreaker and per-name conviction sizing (HYPE big, SOL small, SP500 core). The edge is the DISPERSION between the two speeds, not market direction. Net exposure is an explicit operator decision (default modest net-long). NOT a copy-trader: each book ranks and scores its own curated, cross-asset universe; the runtime owns the LLM gate (pass-through), DSL exits, and all risk.guard_rails. LION_LEG env selects the book.
octopus-strategy
by Senpi-ai
OCTOPUS v1.0 — Market-Neutral Hedge Fund. Two single-direction books on two wallets, one producer. The LONG book ranks the live liquid main-DEX crypto cross-section by 24h relative strength and LONGS the strongest, trend-confirmed names; the SHORT book mirror-images it and SHORTS the weakest, trend-confirmed laggards. The two books net to ~beta-neutral — the edge is DISPERSION (leaders minus laggards), not market direction. NOT a copy-trader: each book scores its own universe and pushes signals; the runtime owns the LLM gate (pass-through), DSL exits, and all risk.guard_rails. OCTOPUS_LEG env selects the book.
camel-strategy
by Senpi-ai
CAMEL v1.0 — Carry Hedge Fund. Two single-direction books on two wallets, one producer, harvesting funding carry. The HARVEST book shorts the most-positive-funding names (longs pay shorts → short collects); the PAYOUT book longs the most-negative-funding names (shorts pay longs → paid to hold). Both are gated to EXHAUSTING crowds (never a fresh trend against the carry), with trend/RSI as confirmation + risk control. The edge is carry — a structural, recurring funding inefficiency — not market direction. NOT a copy-trader: each book scores its own universe and pushes signals; the runtime owns the LLM gate (pass-through), DSL exits, and all risk.guard_rails. CAMEL_LEG env selects the book.
Ramp Skill
by yangzhang75
We submit fixes.
Modern Angular best practices for agents
by Aniol0012
Security • Angular
obelisk
by tommy0103
Search and query past Claude Code and Codex session history. Reactive: when the user asks "how did I fix X", "what did we do last time", "find the session where", "上次怎么修的", "之前的session", "历史记录". Proactive: when the user references past work you lack context for, when you're about to modify a file with complex edit history, when the user says "继续之前的" or "continue where we left off", or when understanding prior decisions would improve your current response. Memory: when the user says "记住这个", "remember this", "写入记忆", "save this conclusion", or when you determine a retrieval result contains a conclusion worth persisting.
surrealdb
by 24601
"Expert SurrealDB 3 architect and developer skill (tracks v3.1.4+). SurrealQL mastery, multi-model data modeling (document, graph, vector, time-series, geospatial), schema design, security, deployment, performance tuning, SDK integration (JS, Python, Go, Rust, Java, .NET, C, PHP, Swift, Kotlin, Ruby), Surrealism WASM extensions, SurrealML scope coverage (preview), built-in MCP (v3.1+) and standalone SurrealMCP, LangChain Python integration, editor tooling (LSP v0.1.6, tree-sitter, CodeMirror v1.0.6, VS Code/JetBrains/Neovim/Zed), and ecosystem integrations (Surrealist v3.9, Surreal-Sync, SurrealFS, SurrealKit v0.7, n8n, Agent Skills, setup-surreal). Universal skill for 30+ AI agents."
eve
by vercel
Build durable backend AI agents with the eve framework. Use when creating, editing, or debugging an eve project — agent instructions, skills, tools, connections, channels, sandboxes, subagents, schedules, or evals.
financial-categorizer
by patello
"Process bank transaction CSV exports (Nordea, ICA), auto-categorize transactions using configurable rules, manage transaction links, and generate analytical database views."
SKILL.md — Pelindo RKAP HTML Dashboard Report
by Ercole28
.r Right-align (on th or td)
wallstreet-tieling
by Dear-Ded
?????????? ? 13-role concurrent AI crew ? due diligence/financial analysis/risk assessment/OSINT ? 10-30 data sources ? platform-agnostic v0.5.0 engine