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.
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。
$ npx skills add rpamis/comet --skill comet -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install rpamis/comet comet --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/eval/local/skills/benchmarks/040-beta/comet .claude/skills/comet && 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" agent skill from https://github.com/rpamis/comet/tree/master/eval/local/skills/benchmarks/040-beta/comet into .claude/skills/comet/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "comet", 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/eval/local/skills/benchmarks/040-beta/cometType 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 -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install rpamis/comet comet --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/eval/local/skills/benchmarks/040-beta/comet .agents/skills/comet && 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" agent skill from https://github.com/rpamis/comet/tree/master/eval/local/skills/benchmarks/040-beta/comet into .agents/skills/comet/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "comet", 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 -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install rpamis/comet comet --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/eval/local/skills/benchmarks/040-beta/comet .cursor/skills/comet && 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" agent skill from https://github.com/rpamis/comet/tree/master/eval/local/skills/benchmarks/040-beta/comet into .cursor/skills/comet/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "comet", 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 eval/local/skills/benchmarks/040-beta/comet--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 -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install rpamis/comet comet --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/eval/local/skills/benchmarks/040-beta/comet .gemini/skills/comet && 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" agent skill from https://github.com/rpamis/comet/tree/master/eval/local/skills/benchmarks/040-beta/comet into .gemini/skills/comet/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "comet", 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 cometInstalls 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 -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/eval/local/skills/benchmarks/040-beta/comet .github/skills/comet && 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" agent skill from https://github.com/rpamis/comet/tree/master/eval/local/skills/benchmarks/040-beta/comet into .github/skills/comet/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "comet", 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 -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 --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/eval/local/skills/benchmarks/040-beta/comet .opencode/skills/comet && 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" agent skill from https://github.com/rpamis/comet/tree/master/eval/local/skills/benchmarks/040-beta/comet into .opencode/skills/comet/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "comet", 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.
cometA 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。
Comet is an agent skill from rpamis/comet. Use 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。
Its SKILL.md is about 2.7k tokens, which your agent loads only when the skill is triggered. The skill folder holds 27 other files, including scripts (for example `reference/auto-transition.md`, `reference/comet-yaml-fields.md` and `reference/context-recovery.md`).
It sits in Agent Workflows. The repository describes itself as: Comet: agent skill harness for turning ideas into evaluated workflows. The licence is MIT.
5 steps, taken from the first numbered list 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.
Ships 1 file in scripts/ (JavaScript, from the files we listed), which the agent can run.
Shell commands in SKILL.md call:
nodeFrom 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 loads about 2.7k tokens when it runs. Until then it costs about 24 tokens; SKILL.md has 792 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); the scripts in this folder are not scanned.
The full file from rpamis/comet at commit 0fd42a0, republished under its MIT licence (© rpamis). 792 words, ~2,725 tokens.
.claude/skills/comet/SKILL.md (or your agent's skills folder). This skill also uses 22 other files; get the full folder from GitHub.OpenSpec 与 Superpowers 如双星系统围绕同一目标运转。
OpenSpec 负责 WHAT — 大纲、提案、spec 生命周期、归档
Superpowers 负责 HOW — 技术设计、计划、执行、收尾核心原则:brainstorming 必不可跳过。每次变更都必须经过深度设计(hotfix 和 tweak 预设除外)。
<IMPORTANT>
本文中的“调用 `/comet-*`”“调用 OpenSpec/Superpowers 技能”均指使用当前平台的 Skill 工具加载对应 Skill,并把必要上下文作为 ARGUMENTS 传入。不得把“调用”降级为在当前 `/comet` 上下文中手工执行子 Skill 的步骤,也不得只按记忆或本文摘要模拟子 Skill。
当路由结果是 /comet-hotfix、/comet-tweak、/comet-open、/comet-design、/comet-build、/comet-verify 或 /comet-archive 时,必须立即用 Skill 工具加载对应的 Comet 子 Skill。该子 Skill 若要求 OpenSpec 或 Superpowers 技能,也必须继续用 Skill 工具加载对应依赖 Skill。Skill 工具调用是 workflow evidence 的一部分。
</IMPORTANT>
agent 做决策只需读本节,参考附录按需查阅。
以触发本次工作流的用户请求语言作为默认输出语言。恢复已有 change 时,如果现有产物有明确主语言,除非用户明确要求切换,否则保持该语言。
Step 0: 活跃 Change 发现与意图判定
comet/reference/scripts.md 完成脚本定位,确保 $COMET_INTENT 可用。openspec list --json 获取所有活跃 change。CometIntentFrame。node "$COMET_INTENT" route --stdin 传入 frame JSON,获取 runtime 规范化路由。CometIntentFrame + runtime scorer 是事实源;本节自然语言规则只用于意图识别槽位提取。hotfix → 直接调用 /comet-hotfixtweak → 直接调用 /comet-tweakfull → 按活跃 change 表决定 /comet-open 或用户确认resume → 进入 Step 1 读取对应 change 的 .comet.yamlask_user → 按 comet/reference/decision-point.md 暂停并等待用户选择out_of_scope → 说明本次输入不是 Comet workflow 启动/恢复请求,不初始化 changeCometIntentFrame 最小骨架:
{
"schema_version": "comet.intent.v1",
"utterance": "<用户原话>",
"intent": { "name": "start_change", "confidence": 0.8 },
"slots": {
"requested_action": "start",
"workflow_candidate": "full",
"user_explicit_workflow": null,
"change_id": null,
"existing_behavior": null,
"new_capability": null,
"public_api_change": null,
"schema_change": null,
"cross_module_change": null
},
"context": {
"active_changes_count": 0,
"active_change_names": []
},
"evidence": [],
"proposed_route": {
"name": "ask_user",
"confidence": 0.5
}
}意图识别槽位提取:
字段完整含义见 comet/reference/intent-frame.md;正常路由只需按上方最小骨架填写。
fix_bug + existing_behavior: true + 无新增 capability/public API/schema/cross-module 信号 → 倾向 hotfix/comet 深度设计/plan → 倾向 tweaktweakfullask_userask_user| 活跃 change | 用户输入 | 行为 |
|---|---|---|
| 无 | full 路由 | → 调用 /comet-open |
| 恰好 1 个 | /comet <描述> | → 询问:继续该变更 or 创建新变更 |
| 多个 | /comet <描述> | → 询问:继续现有变更 or 创建新变更;若选继续 → 列出清单让用户选择 |
| 恰好 1 个 | /comet(无描述) | → 自动选中,进入 Step 1 |
| 多个 | /comet(无描述) | → 列出清单让用户选择 |
<IMPORTANT>
当用户选择「创建新变更」时,**必须调用 `/comet-open`**(禁止直接调用 `/opsx:new`)。
`/comet-open` 负责完整双初始化:OpenSpec artifacts(由内部 `/opsx:new` 创建)+ `.comet.yaml` 状态文件。
直接调用 `/opsx:new` 会缺失 `.comet.yaml`,导致后续阶段判定失败。
</IMPORTANT>
Step 1: 读取 .comet.yaml 状态元数据
优先读取 openspec/changes/<name>/.comet.yaml。不存在时回退到 openspec status --change "<name>" --json、tasks.md 和 docs/superpowers/ 文件检查。
断点恢复规则:
comet/reference/dirty-worktree.md 协议处理。该协议定义了检查步骤、归因分类和禁令,本文件不重复phase: build,先检查 build_pause、plan、isolation、build_mode、tdd_mode 和 review_mode(详见下方):build_pause: plan-ready 但 isolation、build_mode、tdd_mode 和 review_mode 都已经设置,则视为 stale pause:先输出 [COMET] 检测到 stale pause(build_pause=plan-ready 但 isolation/build_mode/tdd_mode/review_mode 已设置),自动清除并继续,再运行 node "$COMET_STATE" set <name> build_pause null,然后读取 tasks.md 的下一个未勾选任务并按 build_mode 恢复执行build_pause: plan-ready 且 plan 文件存在,但 isolation、build_mode、tdd_mode 或 review_mode 尚未设置,回到 /comet-build 的 plan-ready 恢复点,提示用户继续补齐/确认工作区隔离、执行方式、TDD 模式和代码审查模式,不重新生成 planbuild_pause: plan-ready 但 plan 文件缺失,回到 /comet-build 处理状态损坏或重新生成 planisolation、build_mode、tdd_mode 或 review_mode 未设置,回到 /comet-build 对应步骤补充后再执行build_mode 恢复执行:build_mode: subagent-driven-development,不得在主窗口直接执行任务;必须回到 /comet-build 的后台 subagent 调度规则,由主窗口只做协调/comet-build 的对应规则继续phase: verify 且 verify_result: fail,进入验证失败决策阻塞点:暂停并询问用户修复或接受偏差;用户选择修复后才运行 node "$COMET_STATE" transition <name> verify-fail 并调用 /comet-buildphase: open 但 proposal/design/tasks 已完整,先运行 node "$COMET_GUARD" <change-name> open --apply 修正状态,再继续判定phase: archive,只允许调用 /comet-archive;/comet-archive 必须先等待归档前最终确认,归档成功后 change 会移动到 archive 目录,不再对原活跃目录运行 guardStep 2: 阶段判定(按顺序,命中即停)
archived: true 或 change 已移入 archive → 流程已完成verify_result: pass 且 archived 不是 true → /comet-archive(先进行归档前最终确认)verify_result: fail → 进入验证失败决策阻塞点(暂停询问修复或接受偏差;用户选择修复后才 verify-fail 并 /comet-build)phase: verify 或 tasks.md 全部勾选 → /comet-verifyphase: build 或已有 Design Doc 但计划/执行未完成 → 优先按 workflow 路由:hotfix → /comet-hotfix,tweak → /comet-tweak,full → /comet-buildphase: design 或有 change 但无 Design Doc → /comet-designphase: open 或有活跃 change 但 .comet.yaml 缺失 → /comet-open/comet-open如果元数据与文件状态冲突,以文件状态为准,修正 .comet.yaml 后继续。
hotfix/tweak 的范围判定采用三层分工,避免「用纯文件数当硬性升级条件」误杀正常小改动:
comet-state scale 仅决定 verify_mode(验证轻重),不卡流程、不触发升级升级决策点(用户二选一):
/comet(使用 node "$COMET_STATE" transition <name> preset-escalate 合法回退到 design 阶段,补 Design Doc 和 Superpowers plan)详细判定规则见 comet-hotfix / comet-tweak 各自的「升级判定」章节。
| 场景 | 处理方式 |
|---|---|
openspec list --json 失败 | 检查 openspec 是否已安装,提示 openspec init |
| 子 skill 不可用 | 停止流程,提示安装或启用对应 skill |
.comet.yaml 格式异常或缺失 | 以文件状态为准,用 node "$COMET_STATE" set 修正后继续 |
| 构建/测试失败 | 返回 build 阶段修复,不进入 verify |
| change 目录结构不完整 | 按 comet-open 产物要求补齐 |
<IMPORTANT>
单次 `/comet` 调用从检测到的阶段开始,退出条件满足后进入下一阶段。
流转链:open → design → build → verify → archive
连续执行要求:从检测到的阶段开始,agent 自动推进后续阶段。但自动推进仅适用于没有用户决策的衔接点。遇到用户决策点时,必须使用当前平台可用的用户输入/确认机制暂停并等待用户明确回复,不得用推荐规则、默认值或历史偏好代替用户确认,也不得仅输出文字提示后继续执行。
阶段推进与自动衔接的区分:每个子 skill 退出前都会运行阶段守卫 --apply 推进 .comet.yaml 的 phase 字段——这一步始终发生,与 auto_transition 无关。之后子 skill 运行 node "$COMET_STATE" next <name> 解析下一步:auto_transition 不为 false 时输出 NEXT: auto(自动调用下一 skill),为 false 时输出 NEXT: manual(不调用下一 skill,提示用户手动运行)。因此 auto_transition 只控制是否自动调用下一个 skill,不影响 phase 推进。无论 auto_transition 取何值,下方的用户决策点都必须阻塞等待。
决策点是阻塞点:只要到达下列任一节点,当前 /comet 调用必须停住,并按 comet/reference/decision-point.md 的协议获取用户明确选择。用户明确选择后才能写入对应状态字段、执行对应操作,随后再继续自动流转。
需要用户参与的节点(仅在这些节点暂停):
agent 不应跳过这些决策点;其他明确无歧义的阶段衔接必须自动继续推进,不得中途退出。到达决策点时,禁止跳过用户确认或自动选择——必须通过当前平台可用的用户输入/确认机制明确获取用户选择后才能继续。
红旗清单 — 以下想法出现时立即停止并检查:
| Agent 心理 | 实际风险 |
|---|---|
| "用户应该会同意这个方案" | 不能替用户决策,必须等待用户明确选择 |
| "这只是个小改动,不需要确认" | 决策点无大小之分,阻塞点必须等待 |
| "用户之前选过 A,这次也选 A" | 历史偏好不能替代当前确认 |
| "我已经解释了方案,用户没反对" | 没反对 ≠ 同意,必须用工具获取明确选择 |
| "流程走到这里应该没问题了" | 验证不通过 ≠ 通过,检查 verify_result |
</IMPORTANT> |
| 命令 | 阶段 | 归属 | 产物 |
|---|---|---|---|
/comet-open | 1. 开启 | OpenSpec | proposal.md、design.md、tasks.md |
/comet-design | 2. 深度设计 | Superpowers | Design Doc、delta spec |
/comet-build | 3. 计划与构建 | Superpowers | 实施计划、代码提交 |
/comet-verify | 4. 验证与收尾 | Both | 验证报告、分支处理 |
/comet-archive | 5. 归档 | OpenSpec | delta→main spec 同步、design doc 标注、归档 |
/comet-hotfix | 预设路径 | Both | 快速修复(跳过 brainstorming) |
/comet-tweak | 预设路径 | Both | 串联 OpenSpec 的中等改动(delta spec 为一等公民,跳过 brainstorming 和完整 plan) |
/comet
↓ 自动检测
/comet-open ──→ /comet-design ──→ /comet-build ──→ /comet-verify ──→ /comet-archive
(OpenSpec) (Superpowers) (Superpowers) (Both) (OpenSpec)
/comet-hotfix(预设路径,跳过 brainstorming)
open ──→ build ──→ verify ──→ archive
↑ 命中升级判定信号 → 用户二选一(继续预设流程 / 升级 full)→ 升级则 transition preset-escalate → 补 Design Doc → 回到完整流程
/comet-tweak(轻量预设路径,串联 OpenSpec,delta spec 为一等公民)
open ──→ build ──→ verify ──→ archive
↑ 命中升级判定信号 → 用户二选一(继续预设流程 / 升级 full)→ 升级则 transition preset-escalate → 补 Design Doc → 回到完整流程字段说明、文件结构和自动衔接协议已提取为渐进式加载参考文档,按需查阅:
.comet.yaml完整字段表:按comet/reference/comet-yaml-fields.md查阅(含必需字段、可选字段和完整示例)- 文件结构:按
comet/reference/file-structure.md查阅- 自动衔接协议:按
comet/reference/auto-transition.md查阅- 上下文压缩恢复:按
comet/reference/context-recovery.md查阅- 用户决策点协议:按
comet/reference/decision-point.md查阅- 异常调试协议:按
comet/reference/debug-gate.md查阅
build → verify 前,isolation 必须是 branch 或 worktreebuild → verify 前,build_mode 必须已选择build_mode: subagent-driven-development 必须同时有 subagent_dispatch: confirmedtdd_mode 必须已选择为 tdd 或 directreview_mode 必须已选择为 off、standard 或 thoroughbuild_mode: direct 默认只允许 hotfix / tweak;full workflow 需要 direct_override: truebuild_pause 不是执行方式,不得写入 build_modecomet-guard.mjs build --apply 和 comet-state.mjs transition <name> build-completeComet 脚本随 skill 包分发在 comet/scripts/ 下。不硬编码路径 — 定位一次,缓存到环境变量。完整引导块、命令参考(--apply、transition、next、archive)和输出格式见 comet/reference/scripts.md。每会话运行一次该引导,后续全程复用 $COMET_GUARD、$COMET_STATE、$COMET_HANDOFF、$COMET_ARCHIVE、$COMET_RUNTIME。关键入口:
node "$COMET_GUARD" <change-name> <phase> --apply # 阶段守卫 + 自动状态更新
node "$COMET_STATE" transition <change-name> <event> # open-complete | design-complete | build-complete | verify-pass | verify-fail
node "$COMET_STATE" next <change-name> # NEXT: auto|manual|done + SKILL: <skill-name>;auto_transition:false → manual,只暂停下一 skill 调用,不影响已发生的 phase 推进
node "$COMET_ARCHIVE" <change-name> # 一键完成归档按 comet/reference/file-structure.md 查阅完整目录结构。
© 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 22 other files (scripts) in eval/local/skills/benchmarks/040-beta/comet of rpamis/comet.
Open the folder on GitHubat commit 0fd42a0
Comet 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 this skillrpamis/comet | 3.2k | — | ~2.7k | 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
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.
rpamis/comet
A skill your agent uses when full Comet change 已完成 open 阶段但缺少 Superpowers Design Doc,或 design 阶段需要从 OpenSpec 交接包恢复。
Categories
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。. Comet is an agent skill from rpamis/comet.
Comet fits situations like: 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.
Run `npx skills add rpamis/comet --skill comet -a claude-code`. Or copy the skill folder (eval/local/skills/benchmarks/040-beta/comet in rpamis/comet) into .claude/skills/comet in your project. Claude Code loads it when a task matches its description.
Run `npx skills add rpamis/comet --skill comet -a codex`. Or copy the skill folder (eval/local/skills/benchmarks/040-beta/comet in rpamis/comet) into .agents/skills/comet 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 -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, .gemini/skills/comet, .github/skills/comet and .opencode/skills/comet in your project.
Going by SKILL.md and its folder, Comet needs JavaScript for the scripts in its folder and the command-line tools its instructions call (node). Our summary lists: Node.js.
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. The check reads SKILL.md only: the scripts in the folder are not scanned, so read them before running anything.
Comet is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.
About 2.7k tokens (SKILL.md is roughly 11k 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: 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.