MCP Server Builder
anthropics/skills
Guides the design and implementation of Model Context Protocol servers in TypeScript or Python, from tool naming and error messages to evaluation.
完成 Classic 技术设计并请用户确认。在用户调用 /comet-design,或 Classic Runtime 进入 Design 时使用。
$ npx skills add rpamis/comet --skill comet-design -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install rpamis/comet comet-design --agent claude-codeProject scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).
$ git clone --depth 1 https://github.com/rpamis/comet.git skills-src && mkdir -p .claude/skills && cp -r skills-src/assets/skills-zh/comet-design .claude/skills/comet-design && rm -rf skills-srcUse ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.
Claude Code skills documentation · loads skills from .claude/skills/
Install the "comet-design" agent skill from https://github.com/rpamis/comet/tree/master/assets/skills-zh/comet-design into .claude/skills/comet-design/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "comet-design", then confirm the skill loads.Claude Code copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$skill-installer install https://github.com/rpamis/comet/tree/master/assets/skills-zh/comet-designType this inside Codex. $skill-installer <name> installs a curated skill from openai/skills. The installer writes to $CODEX_HOME/skills (default ~/.codex/skills). Restart Codex if the skill does not show up.
$ npx skills add rpamis/comet --skill comet-design -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install rpamis/comet comet-design --agent codexProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/rpamis/comet.git skills-src && mkdir -p .agents/skills && cp -r skills-src/assets/skills-zh/comet-design .agents/skills/comet-design && rm -rf skills-srcUse ~/.agents/skills/ instead of .agents/skills for a personal install.
Codex skills documentation · loads skills from .agents/skills/
Install the "comet-design" agent skill from https://github.com/rpamis/comet/tree/master/assets/skills-zh/comet-design into .agents/skills/comet-design/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "comet-design", then confirm the skill loads.Codex copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add rpamis/comet --skill comet-design -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install rpamis/comet comet-design --agent cursorProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/rpamis/comet.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/assets/skills-zh/comet-design .cursor/skills/comet-design && rm -rf skills-srcUse ~/.cursor/skills/ instead of .cursor/skills for a personal install.
Cursor skills documentation · loads skills from .cursor/skills/, .agents/skills/, .claude/skills/, .codex/skills/
Install the "comet-design" agent skill from https://github.com/rpamis/comet/tree/master/assets/skills-zh/comet-design into .cursor/skills/comet-design/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "comet-design", then confirm the skill loads.Cursor copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gemini skills install https://github.com/rpamis/comet.git --path assets/skills-zh/comet-design--scope user (default) or --scope workspace; --path is the subfolder of the repo that holds the skill; --consent skips the security confirmation prompt.
$ npx skills add rpamis/comet --skill comet-design -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install rpamis/comet comet-design --agent gemini-cliProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/rpamis/comet.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/assets/skills-zh/comet-design .gemini/skills/comet-design && rm -rf skills-srcUse ~/.gemini/skills/ instead of .gemini/skills for a personal install, then run /skills reload.
Gemini CLI skills documentation · loads skills from .gemini/skills/, .agents/skills/
Install the "comet-design" agent skill from https://github.com/rpamis/comet/tree/master/assets/skills-zh/comet-design into .gemini/skills/comet-design/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "comet-design", then confirm the skill loads.Gemini CLI copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gh skill install rpamis/comet comet-designInstalls for Copilot at project scope by default; add --scope user for a personal install. Preview a skill first with gh skill preview. Needs GitHub CLI 2.90.0 or later (public preview).
$ npx skills add rpamis/comet --skill comet-design -a github-copilotProject install goes to .agents/skills/; add -g for ~/.copilot/skills/.
$ git clone --depth 1 https://github.com/rpamis/comet.git skills-src && mkdir -p .github/skills && cp -r skills-src/assets/skills-zh/comet-design .github/skills/comet-design && rm -rf skills-srcUse ~/.copilot/skills/ instead of .github/skills for a personal install. Commit .github/skills so cloud agent and code review can use it.
GitHub Copilot skills documentation · loads skills from .github/skills/, .claude/skills/, .agents/skills/
Install the "comet-design" agent skill from https://github.com/rpamis/comet/tree/master/assets/skills-zh/comet-design into .github/skills/comet-design/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "comet-design", then confirm the skill loads.GitHub Copilot copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add rpamis/comet --skill comet-design -a opencodeOpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.
$ gh skill install rpamis/comet comet-design --agent opencodeProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/rpamis/comet.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/assets/skills-zh/comet-design .opencode/skills/comet-design && rm -rf skills-srcUse ~/.config/opencode/skills/ instead of .opencode/skills for a personal install.
OpenCode skills documentation · loads skills from .opencode/skills/, .claude/skills/, .agents/skills/
Install the "comet-design" agent skill from https://github.com/rpamis/comet/tree/master/assets/skills-zh/comet-design into .opencode/skills/comet-design/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "comet-design", then confirm the skill loads.OpenCode copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
comet-design完成 Classic 技术设计并请用户确认。在用户调用 /comet-design,或 Classic Runtime 进入 Design 时使用。
Comet Design is an agent skill from rpamis/comet. 完成 Classic 技术设计并请用户确认。在用户调用 /comet-design,或 Classic Runtime 进入 Design 时使用。
Its SKILL.md is about 2.3k tokens, which your agent loads only when the skill is triggered. The skill folder holds 2 other files (for example `agents/openai.yaml`).
It sits in Agent Workflows. The repository describes itself as: Comet: agent skill harness for turning ideas into evaluated workflows. The licence is MIT.
3 steps, taken from the step headings in SKILL.md.
Read from SKILL.md and the folder at commit 0fd42a0. It shows what the files ask for, not the result of running them.
Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.
From allowed-tools in the SKILL.md frontmatter.
No scripts in the folder and no shell commands in SKILL.md (its code samples are bash, yaml and markdown).
From the folder's file list and the shell code blocks in SKILL.md.
No URLs in SKILL.md.
From URLs in SKILL.md, links to its own repository left out.
Names no API keys, tokens, secrets or passwords.
From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.
Comet Design loads about 2.3k tokens when it runs. Until then it costs about 22 tokens; SKILL.md has 492 words of instructions outside code blocks.
Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.
The automated check found no risky patterns in SKILL.md.
Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.
The full file from rpamis/comet at commit 0fd42a0, republished under its MIT licence (© rpamis). 492 words, ~2,256 tokens.
.claude/skills/comet-design/SKILL.md (or your agent's skills folder). This skill also uses 1 other file; get the full folder from GitHub.收到入口返回的 layout 后,按 comet-classic/reference/classic-layout.md 确定各逻辑根对应的目录。当前上下文已有这份协议时,无需重复加载。本文件中的 OpenSpec CLI 调用均通过适配器执行,文件路径均基于已绑定的 <classic-*> 根目录,无需先额外运行 root show。
各文档的用途:proposal 记录目标与范围,spec 记录行为和验收要求,Design Doc 记录技术决策,plan 记录实施步骤,tasks.md 记录任务完成状态。已有
design.md时,在同一文件中补充必要设计,不另建一份相同的技术方案。正式技术设计以design_doc指向的文件为准;旧 change 已记录其他路径时,沿用该路径。其他文件只引用这份设计,不重复维护同一项决策。
按 comet-classic/reference/scripts.md 使用正式支持的 Comet CLI,执行以下入口验证。从任意入口恢复任务时,先按 comet-classic/reference/context-recovery.md 检查恢复状态:
comet state select <change-name>
comet state check <name> design --json上一阶段 guard 已成功返回本阶段状态信息时,直接使用其中的状态与 agent.continuation 继续,不重复 select/check;恢复任务、工作区变化或外部状态变化时,才执行上述入口验证。验证通过后,使用入口返回的 layout、configuration、nextAction 和协作进度摘要继续,不逐字段查询,也不重复 root show。正常进入本阶段时,只做入口检查;丢失上下文后恢复任务或需要读取详情时,按 context-recovery.md 处理。验证失败时,处理返回的具体原因。
恢复:先核对现有产物和用户确认记录,只补未完成的步骤。无论正常进入还是恢复任务,都要保留已登记且仍然有效的设计,并读取 data.designReadiness、data.issues 和 data.nextAction。补回缺失文件、纠正文件关联的 change,或更新过期 handoff,不清空 design_doc。用户已确认设计后,可以执行返回的 complete-design 动作;该命令会保留已完成的步骤。如果已经进入 Build,则只返回当前阶段的入口信息。
必须由脚本生成,不能由 Agent 手写摘要代替。
comet handoff <change-name> design --write脚本会根据 change .comet.yaml 的 context_compression 快照生成并记录交接包。
默认 context_compression: off 时生成:
<classic-change-dir>/.comet/handoff/design-context.json
<classic-change-dir>/.comet/handoff/design-context.md启用 beta(项目 .comet/config.yaml 中 classic.context_compression: beta,创建 change 时快照进入 .comet.yaml)时生成:
<classic-change-dir>/.comet/handoff/spec-context.json
<classic-change-dir>/.comet/handoff/spec-context.md并在 .comet.yaml 写入:
handoff_context: <classic-change-ref>/.comet/handoff/design-context.json
handoff_hash: <sha256>默认交接包由脚本摘录源文件,并保留来源信息,不是 Agent 撰写的摘要:
design-context.json:供程序读取的索引,包含 change、phase、正式规格(canonical spec)、源文件路径(source paths)和 hashdesign-context.md:供 Superpowers 阅读的上下文,包含脚本标记、source path、line range、sha256,以及脚本按固定规则生成的摘录[TRUNCATED],并保留 Full source 路径beta 交接包按固定结构组织规格内容,在减少 OpenSpec 原文 token 占用的同时,保留实现所需的规格依据:
spec-context.json:供程序读取的索引,包含 change、phase、mode=beta、source paths、context_hash,以及 files 中各文件的角色spec-context.md:供 Superpowers 阅读的上下文,逐字保留 delta spec 文件内容,并按 hash 引用相关产物如确实需要全文上下文,可显式运行:
comet handoff <change-name> design --write --full交接包取自 OpenSpec open 阶段的产物:
proposal.md:目标、动机、范围、非目标design.md(存在时):已有技术决策、方案约束tasks.md:初始任务范围specs/**/spec.md:各项功能的增量规格,保留嵌套 capability 的完整路径立即执行: 使用 Skill 工具加载 Superpowers brainstorming 技能。禁止跳过此步骤。
技能加载时,ARGUMENTS 必须包含:
Language: 使用入口 configuration.language 中的 Comet 配置产物语言输出技能加载后,按其指引使用以下上下文:
Change: <change-name>
OpenSpec Context Pack: <classic-change-dir>/.comet/handoff/design-context.md
如 context_compression: beta,则使用:
OpenSpec Context Pack: <classic-change-dir>/.comet/handoff/spec-context.md
已确认需求以 OpenSpec 产物为准。brainstorming 引用这些需求,只讨论尚未解决的技术选择,不重新询问已经确认的需求。
默认只读取上述一个 Markdown 上下文包;机器 JSON 由 Runtime 校验,只有诊断索引问题才读取。截断或验收条款不足时按 source path/line range 补读相关原文,不同时通读 JSON、Markdown 和全部源文件。
你的任务是基于交接包做深度技术设计:实现方案、技术风险、测试策略、边界条件。
如发现目标、范围、非目标、验收场景或关键约束仍不清楚,先澄清缺口;信息已足够时直接形成设计方案,不设置最低问答轮数。
需要提问时,先读取 comet-classic/reference/decision-point.md,逐问给出明确问题、推荐及基于当前约束的理由、各选项影响,优先使用可用的 AskUserQuestion,并等待回答。无法形成真实选项的缺失事实明确请求补充。已有有效确认不重复询问;技术方案唯一不替代 Step 1c 的正式设计确认。
不要重写 proposal/spec。如发现 OpenSpec delta spec 缺少验收场景,只能提出 Spec Patch,并回写 OpenSpec delta spec,不能在 Design Doc 中创建第二份需求规格。Spec Patch 仅限于补充验收场景、修正歧义描述或添加边界条件,不得大幅重写 delta spec 的结构或范围。如需大幅修改,应记录设计阶段发现的需求问题,回到 brainstorming 请用户确认。
Design Doc frontmatter 必须最小化,只包含:
---
comet_change: <change-name>
role: technical-design
canonical_spec: openspec
---
按风险决定设计深度:存在真实取舍时比较 2-3 个方案;既有架构已决定方案时说明依据,不为凑数编造替代方案。高风险接口、迁移、安全与并发必须说明失败路径及验证策略。
只采用 brainstorming 的探索与设计方法;相邻的设计段落合并展示,统一在 Comet Step 1c 请用户正式确认设计。外部 Skill 不得额外要求用户再次批准整份设计文档,不得自动调用 writing-plans、切换工作区或进入实施。不得提前写入 Design Doc。禁止在未加载该技能的情况下继续。
如 Superpowers brainstorming 技能不可用,停止流程并提示安装或启用 Superpowers 技能,不要用普通对话替代该步骤。
技能加载后,按其指引产出设计方案(以对话形式呈现):
brainstorming 阶段先提出候选方案,供用户在 Step 1c 确认,不直接写成正式 Design Doc。确认后,才创建或更新正式设计及 delta spec。保留 Open 阶段已有的 design.md 内容,将待确认的修改先记录到检查点,不能提前覆盖已确认的决策。
为便于上下文压缩后恢复,brainstorming 过程中必须持续更新 brainstorm-summary.md。每轮澄清或方案调整后,只要新增了已确认事实、关键约束、候选方案、取舍与风险、测试策略或 Spec Patch 候选,就更新该文件。未确认的内容必须标注为“待确认”或“候选”。该文件用于恢复讨论进度,不是 Design Doc,也不能代替 Step 1c 的用户确认。
brainstorming 产出设计方案后,必须按 comet-classic/reference/decision-point.md 的协议暂停并等待用户明确确认设计方案。不得在用户确认前创建最终 Design Doc、写入 design_doc、运行 design guard,或进入 /comet-build。
暂停时只展示必要摘要:
以单选题给出以下三个选项:
用户确认本设计后,才继续 Step 2。若用户要求调整,继续 brainstorming 迭代,直到用户确认。
用户确认设计方案后、创建 Design Doc 前,创建或更新上述检查点文件,将摘要整理为用户最终确认的方案:
使用文件工具确保 <classic-change-dir>/.comet/handoff/ 存在;不要依赖 POSIX 专用目录命令。
<classic-change-dir>/.comet/handoff/brainstorm-summary.md 结构:
# Brainstorm Summary
- Change: <change-name>
- Date: <YYYY-MM-DD>
## 确认的技术方案
<用户确认的方案摘要>
## 关键取舍与风险
<主要取舍和风险>
## 测试策略
<测试方法概述>
## Spec Patch
<将回写的 delta spec 变更,无则写"无">上下文压缩说明:brainstorm-summary.md 用于在中断后恢复讨论;主动式压缩应等正式设计、状态和 handoff 都保存到文件后再进行。此前如果上下文已被压缩,按需加载以下文件,再继续 Step 2:
<classic-change-dir>/.comet/handoff/brainstorm-summary.md<classic-change-dir>/.comet/handoff/design-context.md(或 beta 的 spec-context.md)及缺失的原文段落;机器 JSON 不作为必读上下文brainstorm-summary.md 用于恢复进度,但 Design Doc 尚未保存时,不能主动丢弃当前设计上下文。直接进入 Step 2,等 Design Doc、状态和最新 handoff 都保存后,再执行上下文压缩。
根据当前主会话中 brainstorming 对话的完整上下文,创建 Design Doc。
Design Doc frontmatter 必须最小化:
---
comet_change: <change-name>
role: technical-design
canonical_spec: openspec
---按以下顺序确定唯一的 <design-doc-path>:已有 design_doc 时沿用;否则优先使用 <classic-change-dir>/design.md,在同一文件中完善 Open 阶段的技术决策。只有项目已有约定要求单独的 Superpowers 文档时,才使用 docs/superpowers/specs/YYYY-MM-DD-<topic>-design.md。此时,Open 的 design.md 只保留 schema 要求的摘要和正式设计链接,不复制详细技术内容。根据风险决定设计需要写多详细,不强制生成空章节或重复的备选方案。
如需回写 delta spec(Spec Patch),同时编辑对应的 specs/**/spec.md。行为需求只在 spec 中维护;正式设计引用相关 capability/验收条款,不能创建第二份需求规格。
上下文压缩恢复:若上下文已被压缩,读取 brainstorm-summary.md 和 handoff,恢复设计讨论。用户尚未确认方案时,回到 Step 1b/1c 继续 brainstorming;用户已确认时,继续创建 Design Doc。brainstorm-summary.md 保存了恢复所需的摘要,但创建 Design Doc 时,还应结合恢复后的完整上下文。
用户明确确认且正式设计已保存后,将 data.artifactRefs.designDoc 中的仓库相对路径用作 <design-doc-ref>。如果用户确认采用其他设计文件,则使用相对于 projectRoot 的路径。文件读写仍使用绝对路径 <design-doc-path>。运行以下命令,一次完成设计登记、必要的 handoff 更新和原有 Guard 检查:
comet state complete-design <name> --design-doc "<design-doc-ref>" --json只要 handoff 的任何来源发生内容变化,包括 proposal、design、任务含义、delta spec 或 OpenSpec metadata,都必须更新 handoff,不能只检查 Spec Patch;否则 design guard 会拒绝推进。只有所有来源内容都没有变化时,才跳过重新生成。单纯勾选任务完成状态不会改变需求 hash。状态文件会自动更新,无需手动编辑其他字段。
只在 Design Doc 和状态记录已保存后、进入 Build 前考虑主动式压缩。先确认 design_doc、最新 handoff、handoff_hash 和 design guard 的结果都已保存;这样压缩后才能从文件恢复,不会丢失尚未记录的设计判断。
comet_change、role: technical-design、canonical_spec: openspechandoff_context 和 handoff_hash 已写入 .comet.yaml(由 guard 强制校验)handoff_hash 与当前 OpenSpec open 阶段产物一致(由 guard 强制校验)design-context.md 或 beta spec-context.md 必须是脚本生成,且包含 source path、mode、sha256 等可追溯标记(由 guard 强制校验)spec-context.json 必须结构合法且引用当前源文件(由 guard 强制校验)design_doc 已写入 .comet.yamlcomet guard <change-name> design --apply,全部 PASS 后由守卫推进到 phase: build(此步骤更新 phase 字段,与 auto_transition 无关)Step 3 成功返回 data.phase: build 即已通过并应用 Guard,不重复执行。失败时处理 data.issues,保留成果并重试同一 complete-design。
按 comet-classic/reference/context-recovery.md 执行,phase 参数为 design。
按 comet-classic/reference/auto-transition.md 和成功结果中的 agent.continuation 继续,不再查询 next。只有丢失上下文后恢复任务、外部状态变化,或旧结果未提供下一步信息时,才重新读取:
comet state next <change-name>NEXT: auto → 调用 SKILL 指向的 skill 进入下一阶段NEXT: manual → 不调用下一 skill,按 HINT 交还控制权并结束当前调用;不再创建确认点NEXT: done → 流程已完成,无需继续© rpamis, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file
SKILL.md and 1 other file in assets/skills-zh/comet-design of rpamis/comet.
Open the folder on GitHubat commit 0fd42a0
Comet Design next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.
| Skill | Stars | Used in | Tokens | Auto-check | Licence | Repo updated |
|---|---|---|---|---|---|---|
| Comet Design this skillrpamis/comet | 3.2k | — | ~2.3k | Automated safety check: Pass | MIT | |
| MCP Server Builderanthropics/skills | 180k | 63 repos | ~2.3k | Automated safety check: Pass | Apache-2.0 | |
| Hook Development for Claude Code Pluginsanthropics/claude-plugins-official | 38k | 10 repos | ~4.1k | Automated safety check: Notes | Apache-2.0 | |
| Using Superpowersfarm-fe/farm | 5.6k | 35 repos | ~1.4k | Automated safety check: Pass | MIT | |
| Executing Plans Inlineobra/superpowers | 297k | 2 repos | ~5.1k | Automated safety check: Pass | MIT | |
| Skill CreatorAzure/azqr | 795 | 89 repos | ~8.2k | Automated safety check: Pass | Apache-2.0 |
anthropics/skills
Guides the design and implementation of Model Context Protocol servers in TypeScript or Python, from tool naming and error messages to evaluation.
anthropics/claude-plugins-official
Explains how to write Claude Code plugin hooks, both prompt-based checks and bash commands, for events such as PreToolUse, Stop and SessionStart.
farm-fe/farm
A skill your agent uses when starting any conversation - establishes how to find and use skills, requiring Skill tool invocation before ANY response including clarifying questions
obra/superpowers
Has the agent carry out an implementation plan itself, task by task in the current session, keeping a ledger, proving each step with a test and ending with one whole-branch review.
Azure/azqr
Create new skills, modify and improve existing skills, and measure skill performance.
anthropics/claude-plugins-official
Explains how to write agents for Claude Code plugins: the markdown file with YAML frontmatter, trigger descriptions, model and color settings, and system prompt design.
rpamis/comet
A skill your agent uses when 用户要启动或恢复 Comet 工作流,需要根据 active change、.comet.yaml、hotfix/tweak 意图路由到对应阶段 Skill。
rpamis/comet
Comet workflow entry. An agent skill from rpamis/comet.
rpamis/comet
Comet — OpenSpec + Superpowers dual-star development workflow.
rpamis/comet
Archive and deliver a Classic change. An agent skill from rpamis/comet.
rpamis/comet
Comet Classic workflow entry. An agent skill from rpamis/comet.
rpamis/comet
Complete the Classic technical design and obtain user confirmation.
Categories
完成 Classic 技术设计并请用户确认。在用户调用 /comet-design,或 Classic Runtime 进入 Design 时使用。. Comet Design is an agent skill from rpamis/comet.
Comet Design fits situations like: agent Workflows work in your project.
Run `npx skills add rpamis/comet --skill comet-design -a claude-code`. Or copy the skill folder (assets/skills-zh/comet-design in rpamis/comet) into .claude/skills/comet-design in your project. Claude Code loads it when a task matches its description.
Run `npx skills add rpamis/comet --skill comet-design -a codex`. Or copy the skill folder (assets/skills-zh/comet-design in rpamis/comet) into .agents/skills/comet-design in your project. Codex loads it when a task matches its description.
Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add rpamis/comet --skill comet-design -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/comet-design, .gemini/skills/comet-design, .github/skills/comet-design and .opencode/skills/comet-design in your project.
SKILL.md names no scripts, command-line tools or credentials: Comet Design is instructions for the agent only.
SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.
Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.
Comet Design is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.
About 2.3k tokens (SKILL.md is roughly 9k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.
Skills that share tags, products or a category with Comet Design: MCP Server Builder (anthropics/skills, 180k stars), Hook Development for Claude Code Plugins (anthropics/claude-plugins-official, 38k stars), Using Superpowers (farm-fe/farm, 5.6k stars) and Executing Plans Inline (obra/superpowers, 297k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
rpamis (a GitHub organization) maintains it in rpamis/comet, which has 3,166 GitHub stars. The repository holds 52 skills in this directory. The repository was last updated on October 9, 2026.
Source: rpamis/comet on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.