Repository
CodeAlive-AI/ai-driven-development agent skills
- skills
- 22
- GitHub stars
- 155
GitHub description: “Practices, protocols, and skills for AI-driven software development. Skills and safety hooks for Claude Code, Codex, OpenCode, Cursor, Antigravity, and any agent supporting the Agent Skills standard.”
- Stars
- 155 (13 forks)
- Licence
- MIT
- Last push
- Oct 2026
- Created
- Jan 2026
- agent-skills
- ai-coding
- ai-driven-development
- antigravity
- claude-code
- codex-cli
- cursor
- gemini-cli
- hooks
- mcp
- multi-agent
- opencode
- plugins
- prompt-engineering
- skills
- subagents
Install all skills
npx skills add CodeAlive-AI/ai-driven-developmentAdd --skill <name> for a single skill and -a <agent> to choose the agent (see the agent guides).
Skills in CodeAlive-AI/ai-driven-development, ranked
Ranked by score. Sort bymost stars,trending,newest,recently updated
| # | Skill | Repository | Stars | Used in | Tokens | Auto-check | Licence | Updated |
|---|---|---|---|---|---|---|---|---|
| 1 | Investigate GitHub repository history before risky code changes using git blame/log, GitHub PRs, review comments, squash/rebase/cherry-pick/rename heuristics, and cited evidence. | CodeAlive-AI/ | 155 | — | ~2k | Automated safety check: Pass | MIT | yesterday |
| 2 | Create, publish, delete, and submit plugins for coding agents (Claude Code, OpenCode, Devin CLI/Desktop). | CodeAlive-AI/ | 155 | — | ~3.1k | Automated safety check: Notes | MIT | yesterday |
| 3 | Deep research over the Semantic Scholar Graph API. An agent skill from CodeAlive-AI/ai-driven-development. | CodeAlive-AI/ | 155 | 1 repo | ~2.2k | Automated safety check: Pass | MIT | yesterday |
| 4 | A skill your agent uses when testing Windows 11 desktop apps (WinForms/WPF/UWP) via UFO UIA/Win32 automation MCP. | CodeAlive-AI/ | 155 | — | ~1.4k | Automated safety check: Pass | MIT | yesterday |
| 5 | Audit and improve repositories for reliable agentic work across Codex and Codex App, Claude Code, and OpenCode. | CodeAlive-AI/ | 155 | — | ~1.2k | Automated safety check: Pass | MIT | yesterday |
| 6 | Manage hooks and automation for coding agents (Claude Code, Codex CLI, OpenCode, Devin CLI/Desktop). | CodeAlive-AI/ | 155 | — | ~4.8k | Automated safety check: Notes | MIT | yesterday |
| 7 | Fetch a web page (URL) and return clean Markdown via local trafilatura, with Exa MCP as a fallback for JS-rendered or anti-bot pages. | CodeAlive-AI/ | 155 | — | ~906 | Automated safety check: Pass | MIT | yesterday |
| 8 | Hands-on playbook for Windows 11 disk cleanup, dev-machine optimization, and proactive health alerting. | CodeAlive-AI/ | 155 | — | ~4k | Automated safety check: Pass | MIT | yesterday |
| 9 | Summarize a repository's recent engineering activity from git history — technologies, work types, churn hotspots, contributor patterns, and velocity. | CodeAlive-AI/ | 155 | — | ~1.2k | Automated safety check: Pass | MIT | yesterday |
| 10 | Universal prompt engineering techniques for any LLM. An agent skill from CodeAlive-AI/ai-driven-development. | CodeAlive-AI/ | 155 | 1 repo | ~4.1k | Automated safety check: Pass | MIT | yesterday |
| 11 | Search, find, discover, install, remove, update, review, deduplicate, list, move, optimise, and iterate on skills for AI coding agents. | CodeAlive-AI/ | 155 | — | ~6.2k | Automated safety check: Pass | MIT | yesterday |
| 12 | Maintain a project thesaurus (domain glossary) following DDD ubiquitous language principles. | CodeAlive-AI/ | 155 | — | ~7.4k | Automated safety check: Notes | MIT | yesterday |
| 13 | Use First Principles Framework (FPF) to decompose problems, architect systems, evaluate alternatives, define quality, recover and replace methods, initiate inquiry from ordinary work, disambiguate… | CodeAlive-AI/ | 155 | — | ~6.6k | Automated safety check: Pass | MIT | yesterday |
| 14 | Hands-on playbook for macOS disk cleanup, dev-machine optimization, and proactive health alerting. | CodeAlive-AI/ | 155 | — | ~5.5k | Automated safety check: Notes | MIT | yesterday |
| 15 | 15.Clipboard Copy text to clipboard with optional rich formatting. An agent skill from CodeAlive-AI/ai-driven-development. | CodeAlive-AI/ | 155 | — | ~816 | Automated safety check: Pass | MIT | yesterday |
| 16 | Install, upgrade, configure, and verify developer CLI tools safely. | CodeAlive-AI/ | 155 | — | ~1.5k | Automated safety check: Notes | MIT | yesterday |
| 17 | Rename and refactor C symbols in a .NET solution or multi-solution monorepo with a one-shot Roslyn CLI. | CodeAlive-AI/ | 155 | — | ~2.5k | Automated safety check: Pass | MIT | yesterday |
| 18 | Software-engineering heuristics based on Mark Seemann's Code That Fits in Your Head (2021), updated for agent-driven development. | CodeAlive-AI/ | 155 | — | ~1.7k | Automated safety check: Pass | MIT | yesterday |
| 19 | Search, install, configure, update, and remove MCP servers across coding agents (Claude Code, Cursor, VS Code, Claude Desktop, Gemini CLI, Codex, Goose, Zed, Devin CLI/Desktop, and more). | CodeAlive-AI/ | 155 | — | ~2.3k | Automated safety check: Pass | MIT | yesterday |
| 20 | View and configure settings for coding agents (Claude Code, Codex CLI, OpenCode, Devin CLI/Desktop, and others). | CodeAlive-AI/ | 155 | — | ~1.9k | Automated safety check: Notes | MIT | yesterday |
| 21 | 8-step disciplined bug-fix protocol that treats every production bug as two failures — the code defect itself and the testing system that allowed it through. | CodeAlive-AI/ | 155 | — | ~648 | Automated safety check: Pass | MIT | yesterday |
| 22 | 22.Plan Mode A skill your agent uses when the user asks to plan, design, scope, estimate, or implement a feature, bug fix, refactor, migration, integration, API change, UI change, or other project modification. | CodeAlive-AI/ | 155 | — | ~844 | Automated safety check: Pass | MIT | yesterday |
Questions, answered from the data.
What is the best skill in CodeAlive-AI/ai-driven-development?
Investigating Repository History from CodeAlive-AI/ai-driven-development ranks first of the 22 skills in CodeAlive-AI/ai-driven-development listed here, with the highest score: its repository has 155 GitHub stars, its SKILL.md loads about 2k tokens and it passes the automated safety check with no findings. Next come Plugins Management and Semantic Scholar Deep.
Are the skills in CodeAlive-AI/ai-driven-development official?
None yet. All 22 skills in CodeAlive-AI/ai-driven-development listed here come from community repositories; a skill counts as official when the product's own GitHub organization publishes it.
How do I install all skills from CodeAlive-AI/ai-driven-development?
Run npx skills add CodeAlive-AI/ai-driven-development in your project: the open-source skills CLI installs the repository's skills into your coding agent's skills folder. To install a single skill, open its page here for the exact command.
How are these skills ranked?
By Skill Navigator score, which combines the GitHub stars of the skill's repository (shared across that repo's skills and discounted for large collections), how many other GitHub owners carry a copy of the skill, and automated SKILL.md quality checks, minus penalties for safety-check warnings and for each further skill from the same repository. Skills that fail the safety check are not listed.