Skip to content

🧩 Skills & Plugins ​

Claude/Codex skills & plugins, custom tools.

RepoPleasePrompto

google-ai-mode-skill: One-Shot Web Research for Claude Code

An open-source (MIT) Claude Code skill that offloads web research to Google's AI Mode, returning one cited, synthesized answer instead of having Claude read 5–10 pages itself.

  • Drives a real Chrome browser via Patchright with a persistent profile, so repeated CAPTCHAs don't pile up; supports DE/EN/NL/ES/FR/IT.
  • Extracts inline citations with 17+ fallback selectors and a 4-stage completion check, returning clean Markdown.
  • Zero-config Python install; only works with local Claude Code β€” the web UI's sandboxed environment has no network access to run it.

added by Radar β€’ 19th Jul 2026

RepoTogether AI β€’ Nutlope

Hallmark: An Open Design Skill That Fights AI-Slop UI

An open (MIT) design skill for Claude Code, Cursor, and Codex that generates interfaces deliberately built to avoid the generic "AI-slop" look.

  • Picks a page macrostructure and one of twenty themes, then runs 57 anti-pattern "slop-test" gates before output, plus a self-critique pass.
  • Covers four modes: build a new UI, audit existing code, redesign a layout, or study a design reference.
  • Installs with `npx skills add nutlope/hallmark` or by copying files directly into a Claude Code, Cursor, or Codex project.

added by Radar β€’ 16th Jul 2026

BlogFigma β€’ Georgia Rust & Rodrigo Davies

Figma's Design Agent, Now With Custom Tools and Greater Context

Figma's design agent gains custom tools, richer context sources, and reusable skills.

  • Build custom reusable generative plugins on the canvas.
  • Attach files and reference Figma files / web / MCP connectors for context.
  • Turn frequent prompts into shareable slash-command "skills".

added by Adam Tomat β€’ 29th Jun 2026

BlogDecoding AI β€’ Paul Iusztin

Build, Configure, or Use As-Is: The Agentic Harness

Argues ~80% of agent harnesses are identical, so decide what to build vs configure vs use off-the-shelf for the other 20%.

  • Tools and catalogs are mostly YAML β€” configure, don't build.
  • Skills are markdown recipes; the memory layer is the piece worth custom-building.
  • Safety must live in a deterministic layer, not in prompts.

added by Adam Tomat β€’ 23rd Jun 2026

ToolTessl

Tessl β€” agent enablement platform

A platform to build, test, distribute, and govern AI agent "skills" at team / enterprise scale.

  • Security scanning, policy, and audit before a skill deploys.
  • A shared, versioned skill registry.
  • Tracks real activation / usage plus evals.

added by Tom Harper β€’ 23rd Jun 2026

VideoAI Native DevCon

AI Native DevCon London 2026 (playlist)

The full talk playlist from AI Native DevCon London 2026 (1–2 June, The Brewery, London).

  • Guy Podjarny β€” "Skills are the New Code": agent instructions/context are becoming a software unit needing intent, review, testing and versioning.
  • Birgitta BΓΆckeler β€” "State of Play: AI Coding Assistants": field data on which adoption patterns work vs. create tech debt.
  • Patrick Debois β€” "The Rise of Agent Enablement": frames agent enablement as a new org function alongside DevOps/Platform Engineering.

added by Tom Harper β€’ 17th Jun 2026

Curated from the AI Chinwag Slack community.