Skip to content

Skillselionwith God's help

By phase

IdeaResearch & spot demand
ValidateScope & prototype
BuildFrontend, backend, MCP
ShipTest, review, deploy
LaunchDistribution, SEO, ASO
GrowAnalytics & retention
OperateMonitoring & uptime

By type

Skills
Marketplaces
MCP servers
Workflows

Skills Marketplaces MCP Learn Brief

Browse all tools →By phase

Idea Validate Build Ship Launch Grow Operate

Explore

Skills
Marketplaces
MCP
Learn
Brief

This week for builders

Five minutes, every Monday — the tools, releases and tactics for shipping solo.

Email address

unsubscribe anytime.

Skillselion

An independent, curated directory of AI-coding tools for solo builders - skills, MCP servers, marketplaces and workflows for Claude Code, Codex and Cursor, organized by the indie build journey from idea to operate.

ResourcesBrowse Skills Browse MCP Servers Browse Marketplaces Browse Workflows Best-of shortlists Glossary State of AI Skills 2026 Weekly Brief

CommunityAbout Learn Feedback Privacy Policy Terms Cookie Policy Accessibility Cookie settings

Last updated June 10, 2026 · © 2026 Skillselion. Skillselion is an independent project and is not affiliated with Anthropic, OpenAI, Cursor, Claude, Claude Code, or Codex.

Skills/DAVIDKISS/SMART AI SKILLS

davidkiss/smart-ai-skills

1 skill · 673 installs · 1 stars · GitHub

Install

npx skills add https://github.com/davidkiss/smart-ai-skills

Skills in this repo

1ReflectionReflection is a meta agent skill for solo builders who run Claude Code, Cursor, Codex, or similar agents and want the assistant to learn from corrections instead of repeating mistakes. Install it when users give feedback, ask for a specific way of working, or when tool calls fail—you use it to review what happened, decide whether a preference belongs in AGENT.md or CLAUDE.md, or whether an existing skill definition needs a small update. The workflow is deliberate: analyze the thread, identify one codifiable behavior, show a diff or memory snippet, wait for explicit confirmation, and only then write files. That guardrail keeps agent memory trustworthy and prevents the model from silently rewriting your skill library. It pairs naturally with brainstorming and writing-plans stacks because approved specs and new habits can be captured after each session. Complexity is intermediate because you need a repo with skills and optional memory files, but the skill itself is short and procedural.673installs