Updated 4mo ago
by Fandry96
k3-agentic-skills
50+ AI agent skills + local semantic search powered by Gemma. No API keys required.
27 GitHub stars (27)
Steady at 27 stars — no new stars in the 16 days since Sep 30.
- 30 skills (30 skills found in its SKILL.md files)
- 5 forks (5 forks)
- 4mo ago last update (Last updated 4mo ago)
Install
Skills CLI
npx skills add Fandry96/k3-agentic-skills
Asks which skills and agents to install. Just one: npx skills add Fandry96/k3-agentic-skills --skill adk-python — add -g for every project.
Claude Code
git clone https://github.com/Fandry96/k3-agentic-skillscp -r "k3-agentic-skills/skills/adk-python" ~/.claude/skills/
Copies the adk-python skill into ~/.claude/skills/ for every project (use .claude/skills/ for one project). Repeat for the other skills listed below.
Plugin
/plugin marketplace add Fandry96/k3-agentic-skills
Run inside Claude Code if the repository ships a plugin marketplace, then pick plugins from /plugin.
Skills can run code on your machine — read the SKILL.md first.
What it does
In the author's own words, from each skill's SKILL.md — showing the first 30 of 82 files.
-
adk-python
Google Agent Development Kit (ADK) for Python — verified API patterns for building production-grade multi-agent systems. Covers Workflow graphs (ADK 2.0 Beta), LlmAgent, SequentialAgent, LoopAgent, CustomAgent (BaseAgent), MCP integration via McpToolset, FunctionTool, ToolContext state, session management, context compaction, callbacks (before/after agent/model/tool), human input via RequestInput…
skills/adk-python/SKILL.md on GitHub (opens in a new tab) -
agent-memory-systems
You are a cognitive architect who understands that memory makes agents intelligent. You've built memory systems for agents handling millions of interactions. You know that the hard part isn't storing - it's retrieving the right memory at the right time.
skills/agent-memory-systems/SKILL.md on GitHub (opens in a new tab) -
ai-agents-architect
Expert in designing and building autonomous AI agents. Masters tool use, memory systems, planning strategies, and multi-agent orchestration. Use when: build agent, AI agent, autonomous agent, tool ...
skills/ai-agents-architect/SKILL.md on GitHub (opens in a new tab) -
auth-implementation-patterns
Build secure, scalable authentication and authorization systems using industry-standard patterns and modern best practices.
skills/auth-implementation-patterns/SKILL.md on GitHub (opens in a new tab) -
blind-spot-advisor
Surfaces risks, blind spots, and opportunities the operator didn't ask about. Runs after plans are drafted but before execution. Use when reviewing implementation plans, launching features, or making architectural decisions.
skills/blind-spot-advisor/SKILL.md on GitHub (opens in a new tab) -
brainstorming
Use before creative or constructive work (features, architecture, behavior). Transforms vague ideas into validated designs through disciplined reasoning and collaboration.
skills/brainstorming/SKILL.md on GitHub (opens in a new tab) -
code-reviewer
Elite code review expert specializing in modern AI-powered code
skills/code-reviewer/SKILL.md on GitHub (opens in a new tab) -
codebase-audit-pre-push
Deep audit before GitHub push: removes junk files, dead code, security holes, and optimization issues. Checks every file line-by-line for production readiness.
skills/codebase-audit-pre-push/SKILL.md on GitHub (opens in a new tab) -
concise-planning
Use when a user asks for a plan for a coding task, to generate a clear, actionable, and atomic checklist.
skills/concise-planning/SKILL.md on GitHub (opens in a new tab) -
content-marketer
Elite content marketing strategist specializing in AI-powered content creation, omnichannel distribution, SEO optimization, and data-driven performance marketing.
skills/content-marketer/SKILL.md on GitHub (opens in a new tab) -
context-compression
When agent sessions generate millions of tokens of conversation history, compression becomes mandatory. The naive approach is aggressive compression to minimize tokens per request.
skills/context-compression/SKILL.md on GitHub (opens in a new tab) -
context-degradation
Language models exhibit predictable degradation patterns as context length increases. Understanding these patterns is essential for diagnosing failures and designing resilient systems.
skills/context-degradation/SKILL.md on GitHub (opens in a new tab) -
context-driven-development
Guide for implementing and maintaining context as a managed artifact alongside code, enabling consistent AI interactions and team alignment through structured project documentation.
skills/context-driven-development/SKILL.md on GitHub (opens in a new tab) -
context-guardian
Guardiao de contexto que preserva dados criticos antes da compactacao automatica. Snapshots, verificacao de integridade e zero perda de informacao.
skills/context-guardian/SKILL.md on GitHub (opens in a new tab) -
context-optimization
Context optimization extends the effective capacity of limited context windows through strategic compression, masking, caching, and partitioning. The goal is not to magically increase context windows but to make better use of available capacity.
skills/context-optimization/SKILL.md on GitHub (opens in a new tab) -
context-window-management
You're a context engineering specialist who has optimized LLM applications handling millions of conversations. You've seen systems hit token limits, suffer context rot, and lose critical information mid-dialogue.
skills/context-window-management/SKILL.md on GitHub (opens in a new tab) -
conversation-memory
Persistent memory systems for LLM conversations including short-term, long-term, and entity-based memory Use when: conversation memory, remember, memory persistence, long-term memory, chat history.
skills/conversation-memory/SKILL.md on GitHub (opens in a new tab) -
copywriting
Write rigorous, conversion-focused marketing copy for landing pages and emails. Enforces brief confirmation and strict no-fabrication rules.
skills/copywriting/SKILL.md on GitHub (opens in a new tab) -
create-pr
Create pull requests following Sentry conventions. Use when opening PRs, writing PR descriptions, or preparing changes for review. Follows Sentry's code review guidelines.
skills/create-pr/SKILL.md on GitHub (opens in a new tab) -
debugging-strategies
Master systematic debugging techniques, profiling tools, and root cause analysis to efficiently track down bugs across any codebase or technology stack. Use when investigating bugs, performance iss...
skills/debugging-strategies/SKILL.md on GitHub (opens in a new tab) -
deep-research
Execute autonomous multi-step research using Google Gemini Deep Research Agent. Use for: market analysis, competitive landscaping, literature reviews, technical research, due diligence. Takes 2-10 ...
skills/deep-research/SKILL.md on GitHub (opens in a new tab) -
design-corporate
Corporate design system blueprint — Open Sans/Poppins typography, enterprise layouts. Strict K3 implementation guide for B2B/Admin dashboards in Next.js 15.
skills/design-corporate/SKILL.md on GitHub (opens in a new tab) -
design-editorial
Editorial design system blueprint — Gelasio serif typography, modern editorial layouts, 8pt grid, WCAG 2.2 AA. Strict K3 implementation guide for magazine-style Next.js 15 apps.
skills/design-editorial/SKILL.md on GitHub (opens in a new tab) -
design-elegant
Elegant design system blueprint — Google Sans (Outfit), minimal aesthetic. Strict K3 implementation guide for refined, light-weight UI in Next.js 15.
skills/design-elegant/SKILL.md on GitHub (opens in a new tab) -
design-glassmorphism
Glassmorphism design system blueprint — frosted glass effects, backdrop-blur, liquid depth. Strict K3 implementation guide for complex UI layering in Next.js 15 apps.
skills/design-glassmorphism/SKILL.md on GitHub (opens in a new tab) -
design-luxury
Luxury design system blueprint — dark surfaces, Oswald typography, bold expressive headings, 8pt grid. Strict K3 implementation guide for premium dark-mode Next.js 15 apps.
skills/design-luxury/SKILL.md on GitHub (opens in a new tab) -
design-premium
Premium design system blueprint (Apple-style) — Inter typography, clean modern aesthetic, 4pt spacing scale. Strict K3 implementation guide for polished SaaS Next.js 15 apps.
skills/design-premium/SKILL.md on GitHub (opens in a new tab) -
differential-review
Security-focused code review for PRs, commits, and diffs.
skills/differential-review/SKILL.md on GitHub (opens in a new tab) -
dispatching-parallel-agents
Use when facing 2+ independent tasks that can be worked on without shared state or sequential dependencies
skills/dispatching-parallel-agents/SKILL.md on GitHub (opens in a new tab) -
docker-expert
Docker containerization expert with deep knowledge of multi-stage builds, image optimization, container security, Docker Compose orchestration, and production deployment patterns. Use PROACTIVELY f...
skills/docker-expert/SKILL.md on GitHub (opens in a new tab)
No skill matches that filter.
Review before you install
A skill is a set of instructions and scripts your agent will follow, and it can run code on your machine. Read the SKILL.md and any scripts first — this listing is not a security review.