create-skill
Skill1 starsChanged 7 months agoMITView on GitHub
Use this skill when the user wants to create a new public skill in this repository's canonical-skills, scaffold its package, or draft the first version of its package and instructions.
Files
Create Public Skill
用來在這個 repo 的 canonical-skills/regular-skills/ 中建立新的公開 skill。
Use This For
- 新增一個可分發的公開 skill
- 草擬
package.json、manifest.json、instruction.md與 target overrides - 建立 skill 所需的基本資料夾結構
- 視需要替 regular skill 加上
sharedtag,讓 manager install flow 也能同步它
Do Not Use This For
- 修改 repo 維護者專用的
.agents/skills/ - 安裝 skill 到其他專案
- 只做小幅文字修正或版本調整
- 把 skill 同步到本 repo 的
.agents/或.claude/
Workflow
1. Gather the definition
先確認:
- skill 名稱
- 使用情境
- 不該觸發的情境
- 分類
- 主要 workflow
- 是否需要
scripts/、references/、examples/、assets/
2. Check repository conventions
讀取:
AGENTS.mdREADME.mddocs/reference/canonical-package-spec.mddocs/reference/adapter-contract.md- 至少一個
canonical-skills/regular-skills/既有 skill 作為結構參考
3. Create the public skill
在 canonical-skills/regular-skills/<skill-name>/ 建立:
package.jsonmanifest.jsoninstruction.mdtargets/codex.frontmatter.jsontargets/claude.frontmatter.json- 視需要建立輔助目錄
package.json 必須遵守目前 canonical schema:
schema_version: 1identity.nameidentity.versionidentity.descriptionidentity.updated_atidentity.tags- 若這個 regular skill 也要給 manager workflow 使用,可加入
sharedtag distribution.scopecontent.instruction_file,固定為instruction.mdtargets.codex.frontmatter_filetargets.codex.install_path,固定為.agents/skills/{name}/targets.claude.frontmatter_filetargets.claude.install_path,固定為.claude/skills/{name}/integrity.manifest_file,固定為manifest.jsonintegrity.package_sha256
instruction.md 應包含:
- 觸發時機
- 不適用情境
- 執行流程
- 必要限制與輸出要求
shared instruction.md 只放共用 instruction 主體,不放 target-specific frontmatter、工具權限、安裝路徑或單一 target 的觸發文案。
target override 要求:
targets/codex.frontmatter.json至少包含name與descriptiontargets/claude.frontmatter.json至少包含name與description- Claude 如需 target-specific 欄位,例如
tools,只能放在 Claude frontmatter
manifest.json 必須列出 render-driving content:
instruction.mdtargets/codex.frontmatter.jsontargets/claude.frontmatter.json- 若有其他會影響 render 的受管檔案,也要一併納入
manifest.json 與 package.json.integrity.package_sha256 必須同步對應同一個 package hash。
4. Validate consistency
確認:
- 目錄名稱、
identity.name、兩個 target override 的name一致 description足以讓 target 判斷是否該觸發package.json結構符合目前 validator 契約manifest.json、integrity.package_sha256、版本與日期彼此一致- 內容屬於公開可分發 skill,而不是 repo 管理技能
建立完 canonical source 後,下一步應提醒使用者執行 finalize-skill。
建議互動收尾:
- 問使用者是否現在就要 finalize 這個 skill
- 若使用者回答
yes,立即切換到finalize-skill - 若使用者回答
no,明確提醒之後要執行finalize-skill <skill-name>
是否同步到本 repo 的 .agents/ 或 .claude/ 不由這個 skill 處理,改由 install-manager-skill 負責。
5. Smoke-check target behavior
至少確認 render / install 心智模型沒有寫錯:
- 這個 skill 之後會由 Python CLI render 並安裝到其他專案
- Codex 目標是
.agents/skills/<name>/ - Claude 目標是
.claude/skills/<name>/SKILL.md - 因此 canonical source 不應依賴這個 repo 自己的 maintainer workflow
如果這次建立的 skill 使用了 examples/、references/、scripts/、assets/,要再檢查它們在 Codex 與 Claude output 的相對路徑是否合理。
Other versions136 projects use a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 136
- microsoft/vscode★ 194ksame name
- CherryHQ/cherry-studio★ 53ksame name
- videojs/video.js★ 40ksame name
- BuilderIO/agent-native★ 7.4ksame name
- stagewise-io/stagewise★ 6.8ksame name
- dotnet/skills★ 5.7ksame name
- xstongxue/best-skills★ 2.9ksame name
- Lilac-Labs/gini-agent★ 1.9ksame name
- Open-Curiosity/gini-agent★ 1.9ksame name
- zylos-ai/zylos-core★ 1.2ksame name
126 more not listed
How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.
Used alongsideProjects with it also use review-bugbot, migrate-to-skills and 10 more.
Other files people use alongside this one.
Files found in the same public projects as a version of this one, more often than they turn up anywhere else. Each project counts once, large collections count for less, and this file's own repository is left out.
0mlkrizzz655335vSkillreview-bugbot
缺陷导向代码审查。用 Bugbot 子代理找 bug。
Also in 5 projects that use this
32103210Skillmigrate-to-skills
Convert 'Applied intelligently' Cursor rules (.cursor/rules/*.mdc) and slash commands (.cursor/commands/*.md) to Agent Skills format (.cursor/skills/). Use when you want to migrate rules or commands to skills, convert .mdc rules to SKILL.md format, or consolidate commands into the skills directory.
Also in 8 projects that use this
32103210Skillupdate-cursor-settings
Modify Cursor/VSCode user settings in settings.json. Use when you want to change editor settings, preferences, configuration, themes, font size, tab size, format on save, auto save, keybindings, or any settings.json values.
Also in 8 projects that use this
PandelisZSkillupdate-cli-config
View and modify Cursor CLI configuration settings in ~/.cursor/cli-config.json. Use when the user wants to change CLI settings, configure permissions, switch approval mode, enable vim mode, toggle display options, configure sandbox, or manage any CLI preferences.
Also in 7 projects that use this
vikneshwaran16032005-altSkillbuild-premium-website
Build a premium, animated marketing website (React + Vite + Tailwind + GSAP) for any industry. Use when the user asks to "build a website", "make a landing page for [business]", "build a marketing site", or wants a high-end animated company website. Adapts color, copy, services, and signature animation to the industry.
Also in 7 projects that use this
vikneshwaran16032005-altSkillinstantly-campaign
Create a new Instantly cold-email campaign in the proven 5-email structure of the user's top-performing campaign (~16% reply rate). Use when the user wants to launch a new outbound campaign, write a cold email sequence, create an Instantly campaign, draft outreach for a new service or niche, or set up a sales sequence.
Also in 6 projects that use this
- +1 more from vikneshwaran16032005-alt
- +1 more from 32103210
In this repository18 other files it gives its agents.
- AGENTS.mdAGENTS.md
- commitSkill
- create-prSkill
- dto-organizerSkill
- finalize-skillSkill
- import-plugin-skillSkill
- install-manager-skillSkill
- skill-review-packetSkill
- update-skillSkill
- commitSkill
- create-prSkill
- create-skillSkill
- dto-organizerSkill
- finalize-skillSkill
- import-plugin-skillSkill
- install-manager-skillSkill
- skill-review-packetSkill
- update-skillSkill
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

