{
  "markdown": "# zforge\n\nMy daily-driver AI coding agent skills. Works with Claude Code, Codex, OpenClaw, Hermes Agent, etc. Take what you find useful.\n\n## Personality\n\nSolves the blank-slate problem — agents forget everything between sessions.\n\n`principle` loads `~/.claude/principles.md` at session start and silently extracts new signals from your corrections and decisions as you work. After a few sessions, a fresh agent doesn't need re-training. `autopilot` goes further — the agent consults your profile to answer its own questions instead of interrupting you, and logs every decision. `memory` auto-saves a working memory (what you're doing, decisions made, blockers) via session hooks and restores it on next start. Important stuff gets promoted to long-term memory that persists across projects.\n\n| Skill | What it does |\n|-------|-------------|\n| `principle` | Extracts your style, decisions, quality bar into a reusable profile |\n| `autopilot` | Agent answers its own questions from your profile, doesn't interrupt |\n| `memory` | Working memory (daily notes) + long-term memory across sessions |\n\n## Engineering\n\nGuardrails for agents. Every skill enforces TDD, branch isolation, and PR gates.\n\n### Build\n\n| Skill | What it does |\n|-------|-------------|\n| `add-feat` | New feature — design, TDD, PR |\n| `fix-bug` | Root cause, regression test, PR |\n| `hotfix` | Emergency — smallest fix, fast PR |\n| `minor-change` | Quick tweak — branch, change, test, PR |\n| `refactor` | Restructure — tests green before and after |\n\n### Ship\n\n| Skill | What it does |\n|-------|-------------|\n| `pr-review` | Isolated worktree review, structured report |\n| `git-release` | Tag, release notes, GitHub release |\n| `update-deps` | Changelogs, compatibility tests, PR |\n\n### Infra\n\n| Skill | What it does |\n|-------|-------------|\n| `init-project` | Bootstrap repo, structure, tooling |\n| `setup-ci` | GitHub Actions via single-question flow |\n| `watchdog` | Monitor CI/CD, deployments, long-running jobs |\n| `audit` | Security, quality, architecture review |\n\n## Install\n\n### Claude Code\n\nPlugin install. Gets all skills + session hooks (personality distillation, memory auto-save/restore). [superpowers](https://github.com/obra/superpowers-marketplace) will be auto-installed on first session if not already present.\n\n```bash\nclaude plugin marketplace add zhengxuyu/zforge\nclaude plugin install zforge\n```\n\n### Codex / Kiro / OpenClaw / Hermes Agent\n\nSkills only (no hooks). Personality and memory skills still work but need manual invocation — no auto-inject at session start.\n\n```bash\nnpx skills add zhengxuyu/zforge\n```\n\n### Manual\n\nClone and symlink into your agent's skill directory.\n\n```bash\ngit clone https://github.com/zhengxuyu/zforge.git ~/.zforge\nln -s ~/.zforge/skills ~/.agents/skills/zforge\n```\n\n## License\n\nMIT\n",
  "bytes": 2807,
  "sha": "b5a1a33bd2e3522e9d359faff65f27fe353ec3d3799e0974152d5ec806a56db8",
  "repo_slug": "zhengxuyu/zforge",
  "fonte": "repo",
  "truncated": false,
  "api": "https://agentalog.com/api/listings/plg_zhengxuyu_zforge_zforge_248e04f7/readme"
}