End-to-end user research skill for AI agents — plan qualitative studies (research plans, screening questionnaires, interview guides), synthesize interview transcripts into evidence-backed reports with codebooks and personas, run AI-moderated interviews with real or synthetic participants, and design and distribute…
★not rated 1.6k▲
+2 yesterdayA
tokens not measured
originalMIT
Email marketing operating manual for AI agents, with hard send-safety gates: campaigns, newsletters and flows, deliverability and DNS, switching ESPs, compliance, anti-slop copy, email design and benchmarks, with any ESP through MCP or an API.
★not rated 342▲
+12
changed 3d agoA
tokens not measured
originalMIT
A Chinese-language writing assistant for Taiwan’s government, legal, and public-to-government documents. It identifies the document type from the user’s intent and applies the matching writing rules and format guidance.
Parse PDF / Office / image files into clean Markdown via MinerU — zero-dependency, AI-Native, auto-routing between the free Agent API and the token-gated Standard API, with 15 content-tool delivery sinks.
★not rated 124▲
+1 22d agoA
tokens not measured
originalMIT
Generate or convert single-file HTML slide presentations with interactive components (flip cards, charts, tables, code blocks, stats, architecture flows, and more) or creative visual themes.
★not rated 88▲
+1 5mo agoA
tokens not measured
forkMIT
Agentic GIS / geospatial workflows: source discovery and provenance (from open data sources first), vector/raster/point-cloud pipelines, CRS and metric analysis, spatial SQL, QGIS projects, tile generation, and web maps — compiled into reproducible projects.
★not rated 69
changed 1mo agoA
tokens not measured
originalMIT
MUST use when the user wants to plan, strategize, validate, or scope a product or feature. Composable product-thinking lenses (JTBD, PR-FAQ, positioning, pre-mortem, RICE, North Star, MVP, GTM, and more) that snap to the outcome and blend when the situation needs it, from raw idea to dev handoff.
★not rated 25 17d agoA
tokens not measured
originalMIT
A personalized AI nutrition coach built as a skill. Works for both men and women — with proper sex-based coaching built in, not bolted on. Logs food, tracks macros, learns your patterns, and remembers your data across conversations.
★not rated 7 3mo agoA
tokens not measured
originalMIT
Zero-config, token-efficient code exploration for any language. Auto-indexes your codebase and keeps the index fresh — just search, fetch, or explore. Uses LSP for precision when available, falls back to ctags, then ripgrep. Up to 99% fewer tokens than reading full files.
★not rated 7 7mo agoA
tokens not measured
originalMIT
Hypothesis-driven problem solving for AI agents: probe, falsify, escalate — never blind-retry. Bundles the behavioral skill and the inquisitor-mcp server (web search, project analysis, code tracing, phase tracking).
★not rated 5 2mo agoA
tokens not measured
originalMIT
Language-agnostic autonomous codebase improvement loop using isolated git worktrees. Every experiment runs on its own branch — main is never touched until a winning change is merged. Works with any language or framework.
★not rated 5 7mo agoA
tokens not measured
originalMIT
Production-grade design system skill. Reads DESIGN.md, sets up theme tokens for Tailwind v3/v4, ShadCN, MUI, Radix, or Geist, and enforces consistent UI/UX via quality gates on every edit.
★not rated 4 1mo agoA
tokens not measured
originalMIT
Fetch relevant, high-quality, free-to-use images from the web for any project context. Scans your directory for context or takes a description, searches Unsplash/Pexels/Pixabay (API or zero-config WebSearch fallback), presents curated picks, and downloads to your project.
★not rated 3 7mo agoA
tokens not measured
originalMIT