Topic · Agent Workflows
Best skill authoring skills, page 2
Skill authoring skills, ranked
Ranked by score. Sort bymost stars,trending,newest,recently updated
| # | Skill | Repository | Stars | Used in | Tokens | Auto-check | Licence | Updated |
|---|---|---|---|---|---|---|---|---|
| 49 | Create new agent skills with proper structure, progressive disclosure, and bundled resources. | sanity-io/ | 6.4k | 13 repos | ~757 | Automated safety check: Pass | MIT | today |
| 50 | Create or update a Codex skill with appropriately scoped instructions and any needed supporting resources. | harperreed/ | 334 | 2 repos | ~3.8k | Automated safety check: Pass | Apache-2.0 | 5 days ago |
| 51 | 51.Dao Skill 道生万 · Agent Skill 元设计器:从模糊需求归根,设计、生成、审计、优化、发布准备或基于证据进化可运行的 Skill。Use when the user wants to create a Skill or Skill family; find a Skill's root problem; evaluate, refactor, harden, optimize, or… | gnipbao/ | 244 | — | ~4.2k | Automated safety check: Pass | MIT | 2 mo ago |
| 52 | A skill your agent uses when creating new skills, editing existing skills, or verifying skills work before deployment | farm-fe/ | 5.6k | 38 repos | ~5.6k | Automated safety check: Pass | MIT | 16 days ago |
| 53 | 53.Luban 鲁班(Luban)——Skill打磨工坊。把一个"能用的Skill"打磨成"能被理解、能被安装、能被传播、能被验证、能持续进化"的公共Skill资产。 | LearnPrompt/ | 958 | — | ~3.1k | Automated safety check: Pass | MIT | 3 mo ago |
| 54 | Create new skills, modify and improve existing skills for JavaClaw. | ClawRunr/ | 754 | — | ~1.5k | Automated safety check: Pass | LGPL-3.0 | yesterday |
| 55 | 55.Api2cli Generate a working CLI from any API, then wrap it in a Claude Code skill. | alexknowshtml/ | 455 | — | ~2.9k | Automated safety check: Pass | MIT | 7 mo ago |
| 56 | Explains how to design and write skills for Claude Code plugins: SKILL.md frontmatter, bundled scripts, references and assets, and descriptions that trigger at the right time. | anthropics/ | 38k | 9 repos | ~5.6k | Automated safety check: Pass | Apache-2.0 | today |
| 57 | Walks an agent through creating, importing, editing, validating, testing and publishing Prismer Skills with a fixed workflow and bundled scripts. | Prismer-AI/ | 1.6k | — | ~2.6k | Automated safety check: Notes | MIT | 8 days ago |
| 58 | Explains how the Crush coding agent embeds builtin skills in its binary and how to add or edit one, including the discovery test and build commands. | charmbracelet/ | 29k | — | ~466 | Automated safety check: Pass | Unknown | yesterday |
| 59 | Create or improve BB skills, including their triggers, instructions, and supporting resources. | get-bb/ | 4.2k | — | ~702 | Automated safety check: Pass | MIT | today |
| 60 | 60.C To Ast Parse C source code into an Abstract Syntax Tree (AST). An agent skill from Narwhal-Lab/MagicSkills. | Narwhal-Lab/ | 316 | — | ~1.1k | Automated safety check: Pass | MIT | 6 mo ago |
| 61 | 亚马逊卖家专用的 skill 创建器(中文)。当用户想把一个亚马逊运营/自媒体/日常工作流程变成可复用的 skill 时使用。触发场景包括但不限于:用户说"我想做一个 skill""把这个流程变成 skill""帮我写个自动化""优化我已有的 skill""给这个工作流做个自动化",即使用户没用"skill"这个词,只要在描述"以后每次都这样做"的重复性工作时也应触发。本 skill… | zach22-1999/ | 207 | 1 repo | ~3.9k | Automated safety check: Pass | Apache-2.0 | 1 mo ago |
| 62 | Debrief an AI agent skill (SKILL.md) after using it — capture session feedback or a retrospective and fold it back into the skill. | computerlovetech/ | 451 | 1 repo | ~2.2k | Automated safety check: Pass | MIT | 1 mo ago |
| 63 | Handles /Customize requests by sending Skill work to the internal skill-creator and managing Specialist agents through the JavaScript host.agents SDK. | aipoch/ | 5.5k | — | ~2.7k | Automated safety check: Pass | Apache-2.0 | today |
| 64 | 建立並排程定時觸發的 skill。所有新增定時/週期任務、提醒、排程通知的請求必須走此 skill,禁止直接呼叫 schedules(mode=write)(那是 skill 已存在時的時間綁定工具,不該作為新建排程的入口)。 | agenvoy/ | 564 | — | ~3k | Automated safety check: Pass | AGPL-3.0 | yesterday |
| 65 | Create new skills, modify and improve existing skills, and measure skill performance. | AgentTeam-TaichuAI/ | 670 | — | ~10k | Automated safety check: Pass | Apache-2.0 | 5 mo ago |
| 66 | CodeStable skill authoring and evolution protocol. An agent skill from codestable/CodeStable. | codestable/ | 1.1k | — | ~3k | Automated safety check: Pass | No licence | 1 mo ago |
| 67 | Analyze session work and automatically convert reusable patterns into Claude Code skills. | sangrokjung/ | 850 | — | ~2.7k | Automated safety check: Pass | MIT | 1 mo ago |
| 68 | Pulls reusable knowledge out of work sessions and turns it into new skills, checking existing notes and skills first to avoid duplicates. | NateBJones-Projects/ | 4.7k | — | ~2k | Automated safety check: Notes | Unknown | yesterday |
| 69 | Guides edits to cc-wf-studio's workflow schema so AI agents generate better workflows, treating schema text as prompt engineering rather than validation. | breaking-brake/ | 5.4k | — | ~1.3k | Automated safety check: Pass | Unknown | yesterday |
| 70 | Create a skill or bring an existing one up to the same standard (validate + asm eval fix loop); run evals, tune triggering. | luongnv89/ | 953 | — | ~5.3k | Automated safety check: Pass | MIT | 2 days ago |
| 71 | Turn a completed task, browser flow, artifact pipeline, failure-recovery trace, or repeatedly refined workflow into a new reusable skill package or a reviewed skill-design plan. | dongshuyan/ | 751 | — | ~1.8k | Automated safety check: Pass | MIT | 1 mo ago |
| 72 | Tạo AI Skill mới từ ý tưởng hoặc quy trình công việc. An agent skill from marketingjuliancongdanh79-pixel/skill-generator. | marketingjuliancongdanh79-pixel/ | 338 | — | ~3.1k | Automated safety check: Pass | No licence | 7 mo ago |
| 73 | Derives a reusable personal skill for course-making from a representative sample of the user's own past classrooms and chat history, confirmed with them before saving. | THU-MAIC/ | 40k | — | ~678 | Automated safety check: Pass | MIT | today |
| 74 | Create, edit, improve, tidy, review, audit, or restructure memmy-agent skills and SKILL.md files. | MemTensor/ | 2.1k | — | ~944 | Automated safety check: Pass | MIT | today |
| 75 | Lets Codex build, refine, test, validate and list CLI-Anything harnesses for GUI applications or source repositories, following the project's full methodology. | HKUDS/ | 52k | — | ~1.5k | Automated safety check: Pass | Apache-2.0 | 16 days ago |
| 76 | Create, synthesize, and iteratively improve agent skills following the Agent Skills specification. | getsentry/ | 1k | — | ~2.5k | Automated safety check: Pass | Apache-2.0 | 6 days ago |
| 77 | Capture and organize general facts about the user by topic. An agent skill from memodb-io/Acontext. | memodb-io/ | 3.7k | — | ~439 | Automated safety check: Pass | Apache-2.0 | 2 mo ago |
| 78 | Create, edit, improve, or audit AgentSkills. An agent skill from agenvoy/Agenvoy. | agenvoy/ | 564 | — | ~3k | Automated safety check: Pass | Apache-2.0 | yesterday |
| 79 | Inspect recent session conversation turns and meta-run history. | clawdotnet/ | 520 | — | ~805 | Automated safety check: Pass | MIT | 5 days ago |
| 80 | Create, port, revise, or audit repo-local skills and their metadata, engineering contracts, and task routes. | authcrunch/ | 108 | 1 repo | ~2.5k | Automated safety check: Pass | No licence | 3 days ago |
| 81 | Create, edit, audit, tidy, validate, or restructure AgentSkills and SKILL.md files. | Kevin100202/ | 170 | 1 repo | ~596 | Automated safety check: Pass | Apache-2.0 | 4 mo ago |
| 82 | Create new skills for FastClaw agents. An agent skill from fastclaw-ai/fastclaw. | fastclaw-ai/ | 1.4k | — | ~1.2k | Automated safety check: Pass | Unknown | 2 days ago |
| 83 | Decides where a new agent skill belongs in the ToolJet repo, public root or private ee submodule, then wires the symlinks so it loads in Claude Code, Cursor and Codex. | ToolJet/ | 41k | — | ~867 | Automated safety check: Pass | AGPL-3.0 | today |
| 84 | Create, update, and audit repository-local agent skills against the current LLM Gateway codebase. | theopenco/ | 1.7k | — | ~662 | Automated safety check: Pass | Unknown | yesterday |
| 85 | 创建、重构或验收可复用技能包。适用于把重复工作流做成跨宿主能力包,并明确触发规则、第一动作、渐进加载、资产模板、脚本校验、触发评测、基线对比、验收证据、闭环治理、公开交付边界和不可伪造的运行证明;也适用于清理冗余参考、拆分人读模板与机器结构数据、补齐首次公开前的验收记录、记录运行反馈、生成写回或不写回决定。当用户提到"做一个 skill / 改 skill / 优化 skill / 评审… | KimYx0207/ | 174 | — | ~1.6k | Automated safety check: Pass | MIT | 2 days ago |
| 86 | 创建高效技能的指南。当用户想要创建新技能(或更新现有技能)以扩展 Claude 的能力,包括专业知识、工作流程或工具集成时,应使用此技能。 | LeastBit/ | 588 | — | ~1.9k | Automated safety check: Pass | Apache-2.0 | 8 mo ago |
| 87 | Validates an Agent Skill package against a portable contract with a Python checker, then picks the smallest set of instruction, capability or lifecycle primitives for the task. | rohitg00/ | 66k | 1 repo | ~450 | Automated safety check: Pass | MIT | 2 days ago |
| 88 | Writes and edits prose in a plain and boring style: simple everyday words, complete sentences, no dashes, no jargon, and no analogies. | docwriter-org/ | 461 | — | ~3.6k | Automated safety check: Pass | MIT | 1 mo ago |
| 89 | Create, edit, improve, or audit skills for SwarmClaw agents. | swarmclawai/ | 688 | — | ~1.4k | Automated safety check: Pass | MIT | 3 mo ago |
| 90 | Create, extend, and debug Wework Core DSH plugins and their optional nested Codex plugins. | wecode-ai/ | 868 | — | ~3.5k | Automated safety check: Pass | Apache-2.0 | 3 days ago |
| 91 | Scaffolds new ShellLM skills with the right frontmatter, directory layout and agent-facing writing style, so an agent can extend its own capabilities. | laude-institute/ | 1.2k | — | ~1.3k | Automated safety check: Pass | Apache-2.0 | yesterday |
| 92 | Guides creating, reviewing or refactoring AI-Driven Development skills so each one stays minimal, composable and named around a single clear function. | paralleldrive/ | 384 | — | ~1.1k | Automated safety check: Pass | MIT | 3 mo ago |
| 93 | A skill your agent uses when bootstrapping or tightening the smallest harness-oriented skill from an existing repository, workflow, evaluation corpus, or harness-analysis chain. | QoderAI/ | 2.4k | — | ~844 | Automated safety check: Pass | MIT | 10 days ago |
| 94 | Guide for creating effective skills for Claude Code agents. An agent skill from pymc-labs/decision-hub. | pymc-labs/ | 104 | — | ~3.1k | Automated safety check: Notes | MIT | 1 mo ago |
| 95 | Create new FreeCAD AI skills, modify existing skills, and iteratively improve them. | ghbalf/ | 550 | — | ~2.7k | Automated safety check: Pass | LGPL-2.1 | 4 days ago |
| 96 | Walks you through drafting, testing, evaluating and tuning a skill for OpenCode, from an intake interview to description optimization. | antongulin/ | 172 | — | ~8.1k | Automated safety check: Pass | Apache-2.0 | 7 days ago |
Explore related skills
More topics in Agent Workflows
- MCP servers2,051
- Subagents1,011
- Agent instruction files739
- Multi-agent orchestration526
- Agent memory505
- Planning495
- Brainstorming463
- Hooks and plugins356
- Autonomous loops324
- Context engineering301
- Session handoff259
- Requirements gathering230
- Task breakdown227
- Human-in-the-loop approvals202
- Skill management195
- Codebase knowledge for agents190
- Verification before completion170
- Agent evaluation and testing133