You MUST use this before any creative work - creating features, building components, adding functionality, or modifying behavior. Explores user intent, requirements and design before implementation.
Use when you have a spec or requirements for a multi-step task, before touching code
Use when executing implementation plans with independent tasks in the current session
Refine questions and problems through 7 Socratic lenses to improve thinking, AI interactions, and decision-making. Use this skill when the user wants to ask better questions, refine a question, think through a problem from multiple angles, explore an idea, challenge their thinking, apply Socratic questioning, use the 7 lenses framework, stress-test a decision, or generally improve the quality of a question before asking it. Also use when the user seems stuck on a decision or is asking a surface-level question that would benefit from deeper exploration.
Ultra-compressed communication mode. Cuts token usage ~75% by dropping filler, articles, and pleasantries while keeping full technical accuracy. Use when user says "caveman mode", "talk like caveman", "use caveman", "less tokens", "be brief", or invokes /caveman.
Own this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge. GitHub access is read-only (username + org membership).
Sign in to claimOwn this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge. GitHub access is read-only (username + org membership).
Sign in to claimBased on adoption, maintenance, documentation, and repository signals. Not a security audit or endorsement.
Agent skills for Claude Code.
This repo is inspired by mattpocock/skills. If you're new to agent skills, watch his talk: Software Fundamentals Matter More Than Ever.
git clone https://github.com/corneliu-iancu/skills.git
cd skills
./install.sh
This symlinks all skills into ~/.claude/skills/, making them available alongside your existing ones. Skills appear as /skill-name — no namespacing.
| Bucket | Skill | Description |
|---|---|---|
| meta | brainstorming | Socratic design refinement before any code |
| meta | writing-plans | Bite-sized implementation plans with exact file paths |
| meta | subagent-driven-development | Parallel subagent orchestration for implementation plans |
| productivity | ask-better-questions | Refine questions through 7 Socratic lenses |
| productivity | caveman | Ultra-compressed communication — ~75% fewer tokens |
| productivity | grill-me | Relentless interview about your plan until every branch is resolved |
| productivity | humanizer | Remove AI-writing patterns — makes text sound natural and human |
| productivity | write-a-skill | Create new skills with proper structure and progressive disclosure |
| productivity | write-docs | Write structured technical documentation from session context |
| quality | diagnose | Disciplined debugging loop: reproduce, minimise, hypothesise, instrument, fix |
| quality | improve-codebase-architecture | Find deepening opportunities — modules to consolidate, coupling to break |
| quality | verification-before-completion | Verify before claiming done — evidence before assertions |
| quality | zoom-out | Explain unfamiliar code in context of the whole system |
| security | insecure-defaults | Detect fail-open insecure defaults in production configs |
[!NOTE] Adobe colleagues: You can also install the review-kit plugin from the Experience Success marketplace. It provides multi-agent PR review with 27 specialized personas (staff engineer, SRE, security researcher, QA, etc.).
Setup:
# Add the marketplace (one-time)
/plugin marketplace add adobe/experience-success-skills
# Install review-kit
/plugin install review-kit@adobe-experience-success
# Reload to activate
/reload-plugins
Usage:
# Review any PR — spawns a multi-agent team based on diff scope
/review-kit:pr-review https://github.com/org/repo/pull/123
# Review without posting to GitHub (local only)
/review-kit:pr-review https://github.com/org/repo/pull/123
# → at the approval gate, say "don't post"
Other review-kit skills: /review-kit:review-architecture, /review-kit:review-strategy, /review-kit:triage-pr-reviews, /review-kit:implement-pr-reviews.
See adobe/experience-success-skills for full docs.
skills/
├── .claude-plugin/plugin.json # Plugin manifest
├── skills/<bucket>/<name>/ # Skills (SKILL.md + references)
├── hooks/ # Session-notes hook
├── scripts/ # Dev utilities
└── CLAUDE.md # Repo rules
MIT
npx claudepluginhub corneliu-iancu/skillsPARA-powered Notion integration for Claude Code. Discover your workspace schema, query tasks, notes, and projects through natural language.
Harness-native ECC plugin for engineering teams - 67 agents, 271 skills, 92 legacy command shims, reusable hooks, rules, MCP conventions, and operator workflows for Claude Code plus adjacent agent harnesses
Comprehensive skill pack with 66 specialized skills for full-stack developers: 12 language experts (Python, TypeScript, Go, Rust, C++, Swift, Kotlin, C#, PHP, Java, SQL, JavaScript), 10 backend frameworks, 6 frontend/mobile, plus infrastructure, DevOps, security, and testing. Features progressive disclosure architecture for 50% faster loading.
Tools to maintain and improve CLAUDE.md files - audit quality, capture session learnings, and keep project memory current.
A growing collection of Claude-compatible academic workflow bundles. Covers scientific figures, manuscript writing and polishing, reviewer assessment, citation retrieval, data availability, paper reading, literature search, response letters, paper-to-PPTX conversion, and evidence-grounded Chinese invention patent drafting. Rules are organized as reusable skill folders with explicit workflows and quality checks.
v9.44.1 — Patch release for Gemini environment/version detection and qwen auth gating. Run /octo:setup.
Browser automation and end-to-end testing MCP server by Microsoft. Enables Claude to interact with web pages, take screenshots, fill forms, click elements, and perform automated browser testing workflows.