Search
Agent Workflows · majiayu000/spellbook
Skills
Sort:BestMost starsTrending todayTrending this weekTrending this monthNewestRecently updatedName
| # | Skill | Repository | Stars | Used in | Tokens | Auto-check | Licence | Updated |
|---|---|---|---|---|---|---|---|---|
| 1 | Audits and repairs how coding-agent Skills are owned, copied and exposed across runtimes, from canonical sources to quarantine and retirement. | majiayu000/ | 287 | — | ~3k | Automated safety check: Pass | MIT | 3 days ago |
| 2 | Scans a repository for real evidence and proposes, or on request writes, a small stack of root and scoped AGENTS.md files with validation commands and generated-file boundaries. | majiayu000/ | 287 | — | ~1.5k | Automated safety check: Pass | MIT | 3 days ago |
| 3 | Single entry point that routes long or ambiguous agent tasks, checks live state, bounds autonomous loops and leaves a resumable handoff. | majiayu000/ | 287 | — | ~2.1k | Automated safety check: Pass | MIT | 3 days ago |
| 4 | Audits a repository's agent-readable context, from AGENTS.md and CLAUDE.md to skills and PRODUCT or TECH specs, and recommends the smallest useful improvements. | majiayu000/ | 287 | — | ~1.9k | Automated safety check: Pass | MIT | 3 days ago |
| 5 | Review whether a repository's coding-agent harness can reliably carry work from intent through controlled execution, verification, delivery, and learning. | majiayu000/ | 287 | — | ~3.5k | Automated safety check: Pass | MIT | 3 days ago |
| 6 | Splits substantial coding or repository-review work between a Sol commander that decides and verifies and a separate Luna Max worker that implements, with an auditable run log. | majiayu000/ | 287 | — | ~3.3k | Automated safety check: Pass | MIT | 3 days ago |
| 7 | A skill your agent uses when a skill is brittle, drifting, repeatedly failing, or needs a Reliable Skill Contract. | majiayu000/ | 287 | — | ~1.3k | Automated safety check: Pass | MIT | 3 days ago |
| 8 | 8.Threads A skill your agent uses when the user explicitly asks for $threads, Codex-native subagents, 开几个子 agent, or a GitHub issue/PR queue needing parallel lanes, worktrees, review/merge gates, and closure… | majiayu000/ | 287 | — | ~8.7k | Automated safety check: Pass | MIT | 3 days ago |
| 9 | A skill your agent uses when coordinating complex tasks across multiple AI agents with a centralized handoff document for planning, execution tracking, and feedback fusion. | majiayu000/ | 287 | — | ~1.5k | Automated safety check: Pass | MIT | 3 days ago |
| 10 | 10.Review Gate Use before an agent-produced diff is committed, pushed, opened as a PR, merged, landed, or applied to user files when explicit implementation approval is missing. | majiayu000/ | 287 | — | ~1.1k | Automated safety check: Pass | MIT | 3 days ago |
| 11 | 11.Idea Team 想法群聊室主持人 — 把一句话想法丢给多角色 AI 团队（调研员/反方/类比者）做查漏补缺。每个角色有自己的 voice，他们互相 @ 接话；你随时插话。这是创意扩展工具，不打分、不否决、不堵路。Use when 用户说"组个团队聊一下"、"开会讨论这个想法"、"找几个角度看看"、"群聊一下 X"、"team review X"，或调用插件命令 /idea-coach:idea-team。Do… | majiayu000/ | 287 | — | ~1.4k | Automated safety check: Pass | MIT | 3 days ago |
| 12 | Parallel multi-AI cross-validation research workflow (大版本). An agent skill from majiayu000/spellbook. | majiayu000/ | 287 | — | ~2k | Automated safety check: Pass | MIT | 3 days ago |
| 13 | Scaffold or standardize a production-ready repository structure with specs, source layout, tests, CI, agent context, config examples, release notes, and operational docs. | majiayu000/ | 287 | — | ~651 | Automated safety check: Pass | MIT | 3 days ago |
| 14 | 14.Skill Audit Audit, design, categorize, distribute, and measure agent skills using lessons from Anthropic's Lessons from building Claude Code: How we use skills. | majiayu000/ | 287 | — | ~1.6k | Automated safety check: Pass | MIT | 3 days ago |
| 15 | Audit and organize AI coding-agent instructions, including AGENTS.md, CLAUDE.md, skills, and agent definitions. | majiayu000/ | 287 | — | ~4k | Automated safety check: Pass | MIT | 3 days ago |
| 16 | 能力蒸馏工作流——从用户批准的强模型访谈或真实任务轨迹中提取非显然的判断规则，形成可审计的 judgment packet，再交给 skill-audit 和 skill-creator 决定是否落成可加载 skill。当用户说“蒸馏这个模型的判断力”“把这次任务的关键决策固化下来”“模型窗口要关了，保留它在某类场景的判断”时使用。普通流程文档、直接写… | majiayu000/ | 287 | — | ~1.3k | Automated safety check: Pass | MIT | 3 days ago |
| 17 | 当用户用 Claude 写小红书、公众号、视频脚本等内容时，输出出现翻译腔、英文思考、西式框架，导致“像外国人假装写中文”时使用。 | majiayu000/ | 287 | — | ~802 | Automated safety check: Pass | MIT | 3 days ago |
