Recently Added
Fresh skills just added to the collection. Be the first to try them out!
Pitch Deck Analysis Skill
by edwardjanes
Maintain investor perspective: would a rational, experienced investor find this compelling enough to take a second meeting?
AKShare Stock Analysis Skill — v2.0.0
by yiming2333
简易DCF使用固定WACC=10%、永续增长率=3%，精确度有限
skill-code-review
by ctxr-dev
Use when completing tasks, implementing major features, or before merging to verify work meets requirements. Runs an FSM-driven, deterministic, manifest-producing code-review pipeline via scripts/run-review.mjs. The runner stages every intermediate (brief, agent dispatch prompt, worker output) under <run_dir>/workers/. The orchestrator drives a shell loop using --print-run-dir / --print-current-state / --print-dispatch-prompt and never writes to /tmp. The LLM is a worker, not the orchestrator.
Cloudflare Workers Runtime APIs & Best Practices
by hexamh
Last updated: May 2025 — based on official Cloudflare Workers documentation.
long-long-run
by huahuadeliaoliao
Use when a task needs a persistent session-bound runtime for long-running execution, project exploration, recovery, monitoring, or continued progress toward one main objective while still handling temporary user interruptions.
research-reading-map
by apandy02
Use when asked to analyze a local research papers directory organized by read, unread, and in-progress folders, then generate a simple static website that maps reading progress, inferred knowledge areas, gaps, and recommended next reads.
frontend-design
by Yns941
Create distinctive, production-grade frontend interfaces with high design quality. Use this skill when the user asks to build web components, pages, or applications. Generates creative, polished code that avoids generic AI aesthetics.
equity-research-agentic-workflow
by Abhillashjadhav
Triggers when user asks to run weekly equity analysis, run backtest, or research a specific ticker. Reads MASTER_PLAN.md to load strategy, calls tools/screen.py to produce ranked top-50 candidates, then for each candidate runs ReAct loop using tools/research.py (max 10 iterations) gathering news, fundamentals, insider data, peer comparison. After thesis is built, runs Devil's Advocate attack on the thesis surfacing the strongest reason it could be wrong. Then runs Critic verdict assigning a confidence score 0.0-1.0; only theses with confidence >=0.85 become PICK. Outputs full reasoning trace plus final picks to runs/YYYY-MM-DD.md.
prompt-master
by nidhinjs
Generates optimized prompts for AI tools. Activates only when the user explicitly asks to write, fix, improve, or adapt a prompt for a specific AI tool (LLM, Cursor, Midjourney, image AI, video AI, coding agents, etc.). Does not activate for general conversation, coding tasks, document writing, or other non-prompt-engineering work.
MISSION
by Andrew363601
trap_price, trap_tp_price, trap_sl_price: (If action is VIRTUAL_TRAP).
schemapin
by ThirdKeyAI
Cryptographic tool schema verification to prevent MCP Rug Pull attacks — ECDSA P-256 signing, SHA-256 hashing, TOFU key pinning, .well-known discovery, signed revocation documents, and (v1.4-alpha across all four languages) signature expiration, DNS TXT cross-verification, and schema version binding (lineage chain)
TEP Copilot Generator Skill
by pnurimoto
Never claim a sprint is complete without human verification steps and PR notes.
artagents
by banodoco
"Use for the ArtAgents repo: file-based hype-cut/video pipeline work, source analysis, transcript/event-talk splitting, pure-generative Remotion timelines, Reigh-compatible timeline/assets JSON, validation/review loops, and GPT Image asset generation via generate_image.py."
gsDesignNB
by keaven
Design, simulate, and adapt clinical trials with negative binomial recurrent event endpoints using the gsDesignNB R package. Use this skill when the task involves: NB sample size or power, event gaps and Jensen correction, calendar-time group sequential design, blinded or unblinded information estimation, sample size re-estimation (SSR), recurrent-event simulation (constant or seasonal rates), interim data cuts, completer-based analyses, or non-inferiority/super-superiority designs for recurrent events.
ocr-disruptivo
by rogermaiocchi
Pipeline production-grade de OCR jurídico com 8 engines, privacy-gate, roteamento automático, preservação de tabelas e FAIR-compliance. Unifica transcrever-pdf + ocr-juridico.
SKILL CONFIGURATION — AI DEVELOPMENT AGENT
by RahmatHadinata23758051
You are a development partner.
backend-architect
by kozz36
Backend architecture expert for API design, database modeling, auth patterns, caching, and system design. Trigger: When designing APIs, choosing databases, planning auth systems, scaling backends, or making architecture decisions.
pubmed-cli
by drpedapati
"Search PubMed, fetch article metadata, traverse citation graphs, and look up MeSH terms from the command line. Use when: (1) Searching PubMed with Boolean/MeSH queries, (2) Fetching article details by PMID (abstract, authors, DOI, MeSH terms), (3) Finding papers that cite a given article (cited-by), (4) Finding papers cited by a given article (references), (5) Finding related articles with relevance scores, (6) Looking up MeSH vocabulary (tree numbers, scope notes), (7) Exporting citations in RIS format for Zotero/EndNote, (8) Building reproducible literature review workflows, (9) Verifying document references against PubMed for accuracy and detecting fabricated citations."
Pair Framework
by viames
"Entry skill for assistants working on the Pair v4 framework repository."
self-evolving-agent
by Marrowleaf
"Watch what you repeatedly ask, identify capability gaps, and auto-generate new skills. The agent that levels itself up."
web-fetch
by code-yeongyu
"Fetch a URL and save the body to a temp file so you can pipe it through rg / jq / awk instead of dumping the whole page into the conversation. Use this whenever a user gives you a URL to read - articles, docs, PRs, gists, README files, blog posts, anything HTTP. Returns a path on disk; the agent then greps the path for the relevant section and quotes only what matters. Strongly preferred over the built-in webfetch tool when (a) the page is more than a few KB, (b) the user wants to find a specific phrase / table / code block on the page, (c) you need to keep the long page out of context, or (d) you want to inspect raw HTML alongside rendered markdown. Triggers: 'fetch', 'fetch this URL', 'fetch and save', 'fetch the page', 'pull this', 'grab this article', 'read this URL', 'read the docs at', 'mirror this page', 'page is too long', 'save the page so I can grep it', 'put it on disk so I can rg', 'cache this URL'."
meme-generator
by Marrowleaf
Generate memes from templates with custom text overlays using Python Pillow, supporting 20+ popular formats with batch generation for content calendars
speed-reader
by Marrowleaf
Extract key points from long articles, PDFs, and URLs with configurable summary lengths and automatic Obsidian integration
ai-worklog
by Zhanbingli
Create durable AI-assisted work records for software or writing projects. Use when the user asks to log an AI session, maintain an AI changelog, preserve project memory, create build-in-public notes, summarize a task for future Codex/Claude sessions, or turn work into reusable GitHub-backed records without storing unnecessary private prompt transcripts.