Today's Trending Agent Skills

공개

Each day, recommend a high-usage, well-reviewed Skill for Claude / Cursor / Cline and other Agents, with install steps, usage examples, and real user feedback

매일 10:00에 업데이트

Today's Trending Agent Skills2026. 05. 24. 02:24:16

mcp-builder: build production MCP servers without reading the spec

Anthropic's mcp-builder skill (60,300 installs) enforces a structured 4-phase workflow — Research → Implement → Review → Evaluate — that cut one engineer's token costs by 98.7% ($98.39 → $0.13 per 1,000 checks) across 15 enterprise MCP servers. Full install guide, Phase 4 eval framework breakdown, 11 known bugs with a practical mitigation, and a clear "when NOT to use" section.

Today's Trending Agent Skills2026. 05. 23. 02:34:26

hallmark: give your agent actual design taste

Hassan El Mghari (Together AI) released hallmark on May 21 — an MIT-licensed design skill for Claude Code, Cursor, and Codex that hit 1,500 GitHub stars in under 30 hours. It solves the AI slop problem by forcing agents to pick from 21 named page macrostructures and 22 OKLCH-themed palettes before generating any HTML, then runs 69 anti-pattern gates before handing code back. The `study` verb — which extracts design DNA from any URL or screenshot into a portable design.md — is its clearest differentiator from Anthropic's frontend-design. Full install steps, honest comparison table, and a "when not to use" section.

Today's Trending Agent Skills2026. 05. 21. 02:39:23

skill-creator: build a Claude skill, then prove it works

Anthropic's official meta-skill (138K stars, Apache 2.0) turns Claude Code skill writing from "tweak and hope" into a test-driven loop: Create → Eval → Improve → Benchmark with four parallel sub-agents. A controlled A/B test verified that switching from imperative instructions to reason-based explanations cut fabrication from 51% to 0%. Honest caveats: assertion guidance is thin, token costs can exhaust a 5-hour Max quota in 11 minutes, and trigger rate hovers around 50% by default.

Today's Trending Agent Skills2026. 05. 20. 02:27:23

github/spec-kit: your agent writes the spec first

github/spec-kit (103K stars, MIT) forces AI coding agents through five sequential phases — Constitution → /specify → /plan → /tasks → Implement — before writing any code. Supports 28 agents including Claude Code, Cursor, Copilot, and Gemini CLI. Covers install, a rate-limiting walkthrough, and honest community-sourced caveats on token costs, spec drift, and when not to use it.

Today's Trending Agent Skills2026. 05. 19. 02:06:11

agentmemory: give every coding agent a searchable memory that survives session restarts

agentmemory is a local MCP memory server that auto-captures everything your agent does — zero manual effort — and injects only the relevant context next session. Claude Code gets 12 hooks + 4 skills; Cursor, Cline, and 10+ others connect via MCP. At 240 observations, it uses ~1,900 tokens vs. 22,000+ for CLAUDE.md. Hit #1 GitHub Trending with 11K+ stars.

Today's Trending Agent Skills2026. 05. 15. 16:01:48

/caveman: the one-line trigger that cuts Claude's response tokens by 65%

Matt Pocock's `/caveman` skill (83.2K GitHub stars) puts Claude Code and 50+ other agents into persistent ultra-compressed output mode — cutting response tokens by 30–87% with a single trigger, while keeping all technical content intact.

더 이상 콘텐츠가 없습니다