davidkiss/smart-ai-skills
7 skills1.7k installs28 starsGitHub
Install
npx skills add https://github.com/davidkiss/smart-ai-skillsSkills in this repo
1Reflectionreflection is a self-improvement skill from davidkiss/smart-ai-skills that agents must use when users give corrective feedback, request a specific working style, or when tool calls fail. It analyzes what worked, what failed, and recurring patterns, then proposes concise updates to existing skills and stores durable preferences in AGENT.md or CLAUDE.md. Developers reach for reflection when an agent keeps repeating mistakes, ignores stated conventions, or needs formalized lessons from a debugging session. The skill turns one-off chat corrections into persistent agent memory and actionable skill patches instead of losing context between sessions.714installs2Codingcoding is a mandatory general-coding skill in davidkiss/smart-ai-skills that agents should load for all implementation, refactoring, and review tasks. It codifies core software engineering principles: DRY to avoid duplicated logic, KISS to prefer simple solutions, and practices for robust, maintainable, scalable code. The skill applies across frontend, backend, and test codebases without prescribing a specific framework, acting as a baseline quality guardrail when agents implement features or fix bugs. Developers reach for coding when they want agent-written code to follow consistent engineering discipline rather than ad-hoc shortcuts. It complements project-specific conventions in AGENTS.md or linters by steering architectural and readability decisions during generation. Because it spans the full implementation lifecycle, it pairs with narrower skills for testing, security, or deployment rather than replacing them.384installs3Task Breakdownsmart-ai-skills task-breakdown guides Claude through structured decomposition of complex requests into prioritized subtasks with dependencies, outcomes, and checkpoints so validation-phase scoping stays concrete before frontend, backend, or integration work begins.208installs4Subagent Task ExecutionExplains how to run subagent task execution in Claude Code-style agent builds: when to fork work, how to scope prompts and files, parallelize safely, resume sessions, and fold subagent results back into the parent orchestration without losing coherence.168installs5BrainstormingStructured AI brainstorming skill for early product discovery: expands directions, reframes problems, and produces organized concept lists before validation or build work begins.158installs6Skill EditorGuides creation and maintenance of Claude Code skills in davidkiss/smart-ai-skills, covering SKILL.md authoring, bundled resources, and agent-tooling patterns so teams ship consistent, reusable agent capabilities.111installs7InvestigatorGathers deep project context and performs rigorous analysis via parallel investigation subagents across context/history, impact mapping, and root-cause troubleshooting. A developer uses it when asked to analyze, research, or understand a project's state before taking action.6installs