Execute
alirezarezvani/claude-skills
/cs:execute <decision — Generate a 90-day execution plan with weekly milestones, DRIs, and check-in cadence from an approved decision.
持续执行框架:让 Claude 在跨多轮会话的长期任务中保持高效运行。当用户的任务规模较大、需要跨多个上下文窗口完成时使用此技能。
$ npx skills add 312362115/claude --skill task-execute -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install 312362115/claude task-execute --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/312362115/claude.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/task-execute .claude/skills/task-execute && 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 "task-execute" agent skill from https://github.com/312362115/claude/tree/main/skills/task-execute into .claude/skills/task-execute/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "task-execute", 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/312362115/claude/tree/main/skills/task-executeType 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 312362115/claude --skill task-execute -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install 312362115/claude task-execute --agent codexProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/312362115/claude.git skills-src && mkdir -p .agents/skills && cp -r skills-src/skills/task-execute .agents/skills/task-execute && rm -rf skills-srcUse ~/.agents/skills/ instead of .agents/skills for a personal install.
Codex skills documentation · loads skills from .agents/skills/
Install the "task-execute" agent skill from https://github.com/312362115/claude/tree/main/skills/task-execute into .agents/skills/task-execute/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "task-execute", 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 312362115/claude --skill task-execute -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install 312362115/claude task-execute --agent cursorProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/312362115/claude.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/skills/task-execute .cursor/skills/task-execute && 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 "task-execute" agent skill from https://github.com/312362115/claude/tree/main/skills/task-execute into .cursor/skills/task-execute/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "task-execute", 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/312362115/claude.git --path skills/task-execute--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 312362115/claude --skill task-execute -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install 312362115/claude task-execute --agent gemini-cliProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/312362115/claude.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/skills/task-execute .gemini/skills/task-execute && 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 "task-execute" agent skill from https://github.com/312362115/claude/tree/main/skills/task-execute into .gemini/skills/task-execute/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "task-execute", 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 312362115/claude task-executeInstalls 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 312362115/claude --skill task-execute -a github-copilotProject install goes to .agents/skills/; add -g for ~/.copilot/skills/.
$ git clone --depth 1 https://github.com/312362115/claude.git skills-src && mkdir -p .github/skills && cp -r skills-src/skills/task-execute .github/skills/task-execute && 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 "task-execute" agent skill from https://github.com/312362115/claude/tree/main/skills/task-execute into .github/skills/task-execute/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "task-execute", 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 312362115/claude --skill task-execute -a opencodeOpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.
$ gh skill install 312362115/claude task-execute --agent opencodeProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/312362115/claude.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/skills/task-execute .opencode/skills/task-execute && 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 "task-execute" agent skill from https://github.com/312362115/claude/tree/main/skills/task-execute into .opencode/skills/task-execute/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "task-execute", 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.
task-execute持续执行框架:让 Claude 在跨多轮会话的长期任务中保持高效运行。当用户的任务规模较大、需要跨多个上下文窗口完成时使用此技能。
Task Execute is an agent skill from 312362115/claude. 持续执行框架:让 Claude 在跨多轮会话的长期任务中保持高效运行。当用户的任务规模较大、需要跨多个上下文窗口完成时使用此技能。 触发场景包括:用户提到"长期任务"、"多阶段项目"、"跨会话开发"、"大型功能开发"、"需要多次对话才能完成", 或任何明显超出单次上下文窗口能力范围的复杂工程任务。即使用户没有明确提到"长期运行", 只要任务复杂度高、涉及多个功能模块、预计需要大量代码变更,都应该触发此技能。 工作流位置:task-start → task-execute → task-finish
Its SKILL.md is about 2.2k tokens, which your agent loads only when the skill is triggered. The skill folder holds 1 other file (for example `CHANGELOG.md`).
The licence is MIT.
8 steps, taken from the step headings in SKILL.md.
Read from SKILL.md and the folder at commit 2d4fa49. 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.
Shell commands in SKILL.md call:
npmgitnpxcurlbashFrom the folder's file list and the shell code blocks in SKILL.md.
Links to these hosts (documentation or services it may open):
anthropic.comFrom 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.
Task Execute loads about 2.2k tokens when it runs. Until then it costs about 66 tokens; SKILL.md has 392 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 312362115/claude at commit 2d4fa49, republished under its MIT licence (© 312362115). 392 words, ~2,163 tokens.
.claude/skills/task-execute/SKILL.md (or your agent's skills folder). This skill also uses 1 other file; get the full folder from GitHub.灵感来源:Anthropic - Effective Harnesses for Long-Running Agents
Agent 在离散的会话中工作,每个新会话对之前的工作没有记忆。这意味着跨越数小时甚至数天的复杂任务很容易失败。本框架解决两个核心失败模式:
第一次会话有两个任务:快速建立框架文件,然后立即开始第一个功能的开发。不要把整个会话都花在"准备工作"上——用户希望看到实际进展。
框架搭建限制在 5 次以内的工具调用(创建 init.sh + 创建 claude-progress.md + git add + git commit),完成后立即进入编码。
init.sh根据项目实际情况编写,包含:依赖安装、数据库迁移、服务启动、健康检查。脚本要能幂等运行(重复执行不出错)。
#!/bin/bash
set -e
npm install
npx prisma migrate dev 2>/dev/null || true
npm run dev &
# 等待服务就绪后输出确认
for i in $(seq 1 15); do
curl -s http://localhost:3000 > /dev/null 2>&1 && echo "就绪" && exit 0
sleep 1
done
echo "启动超时" && exit 1claude-progress.md根据项目是否已有文档体系,选择不同模式:
判断标准:项目中是否存在 docs/specs、docs/plans 或类似的方案/计划目录?
适用于从零开始的项目,progress.md 同时承担功能清单和进度记录。
# 项目进度
## 功能清单
| # | 功能 | 优先级 | 状态 | 依赖 |
|---|------|--------|------|------|
| 1 | 用户登录页面 | high | pending | - |
| 2 | 用户注册流程 | high | pending | #1 |
| 3 | 书籍列表与搜索 | high | pending | - |
## 已完成
(暂无)
## 下一步
- #1: 用户登录页面
## 已知问题
(暂无)功能清单原则:
done = 代码写完可运行;verified = 通过端到端测试验证。只有 verified 才算完成verified(前提是你亲自验证过)适用于已有方案文档(docs/specs)和开发计划(docs/plans)的项目。不重复维护功能清单,只记录会话延续信息。
# 会话日志
## 相关文档
- 方案设计:docs/specs/
- 开发计划:docs/plans/
- 产品文档:docs/prd/
## 最近会话
### 2026-03-14 会话 #5
- 做了:购物车 API 的数量修改和删除接口(B3)
- 状态:B3 约 80%,价格计算还没做
- 遗留决策:价格服务端算,快照价格策略(详见 docs/specs/cart.md)
- 下一步:完成 B3 价格计算,然后等设计稿确认再开前端
### 2026-03-13 会话 #4
- 做了:购物车 API 的 CRUD 基础接口(B3)
- 状态:B3 约 40%
- 下一步:数量修改 + 删除接口
## 已知问题
- 搜索接口 >1000 条时慢,需加索引(不阻塞当前任务)模式 B 的关键原则:
git add init.sh claude-progress.md
git commit -m "chore(init): 建立长期运行框架文件"然后直接进入第二阶段的开发循环,开始处理第一个功能。不要等到"下次会话"。
每次新会话开始,快速进入状态:
模式 A(完整模式):
1. cat claude-progress.md → 功能清单 + 上次做到哪了
2. git log --oneline -10 → 最近的变更历史
3. bash init.sh → 启动开发环境
4. 快速冒烟测试 → 确认已有功能没坏模式 B(会话日志模式):
1. cat claude-progress.md → 最近 2-3 条会话记录,快速了解上下文
2. 按需读 docs/plans/当前模块.md → 当前阶段的开发计划和任务清单
3. 按需读 docs/specs/相关方案.md → 当前功能涉及的设计方案
4. git log --oneline -10 → 最近的变更历史
5. bash init.sh → 启动开发环境
6. 快速冒烟测试 → 确认已有功能没坏模式 B 的步骤 2-3 是"按需"——只读当前要做的功能相关的文档,不要把所有 specs/plans 都读一遍。
启动例程要快。目的是进入状态,不是做审计。
接续上次未完成的 Plan:如果 progress.md 中有遗留决策(模式 A 在"进行中"区,模式 B 在最近的会话记录中),说明上次会话中断了一个大功能。此时用 EnterPlanMode 基于遗留信息重建 Plan——不是从零开始分析,而是在上次决策的基础上继续。Plan 中标注"沿用上次决策"的部分可以简写,只展开新增或调整的部分。
选择功能 → Plan 方案设计 → 用户 approve → 实现 → 验证 → 提交 → 更新进度选择功能:从清单中选优先级最高的、依赖已满足的、状态为 pending 的功能。
Plan 方案设计:选定功能后,使用 EnterPlanMode 做方案设计。Plan 负责"这次会话怎么做",claude-progress.md 负责"整个项目做到哪了"——两者职责不同,不要混淆:
Plan 中不需要重复 progress.md 里已有的项目全景信息,只聚焦当前功能的实现方案。用户 approve 后再开始编码。
简单功能可以跳过 Plan:如果功能很小(改动不超过 2-3 个文件、实现路径明确无歧义),可以直接编码,不需要走 Plan 流程。
实现:每完成一个有意义的步骤就 git commit。好处——出错可回退,后续会话有细粒度历史。
验证:不能只靠"代码看起来对"。用 Playwright/Puppeteer 或测试框架做端到端验证。绝对不能为了让测试通过而修改测试——这会掩盖真实问题,让后续会话在错误前提上继续。
更新进度:每完成一个功能就立即更新 claude-progress.md 并 git commit,不要攒到最后一起更新。原因:你不知道什么时候会中断,攒着更新 = 中断时丢失进度记录。
模式 A 的更新内容——改功能清单状态 + 在"已完成"区写清楚做了什么:
## 已完成
- #1: 用户登录页面 — commit abc1234
- 登录表单 + 客户端验证 + 对接 /api/auth/login
- 已通过 Playwright 端到端验证模式 B 的更新内容——在"最近会话"区追加一条记录:
### 2026-03-14 会话 #5
- 做了:购物车 API 的数量修改和删除接口(B3)
- 状态:B3 约 80%,价格计算还没做
- 遗留决策:价格服务端算(详见 docs/specs/cart.md 第 3 节)
- 下一步:完成 B3 价格计算两种模式的共同目标:让下一个会话能在 30 秒内理解现状。写具体的事实,不写模糊的总结。
在开发循环中,每个子任务可按需触发工作流中的其他 skill:
task-start 进行需求对焦和方案设计task-finish 进行 CR 自检。大任务全部完成时执行完整复盘Agent 没有 API 可以查"还剩多少 token",所以需要依赖可观测的信号主动管理。
具体信号——出现以下任一情况时,准备收尾:
| 信号 | 怎么判断 | 紧急程度 |
|---|---|---|
| 系统压缩了早期消息 | Claude Code 会自动压缩对话历史,你会发现早期细节变模糊 | 高——必须立即收尾 |
| 已完成 2-3 个中等功能 | 数一下本次会话完成了几个功能 | 中——完成当前功能后收尾 |
| 当前功能做完,下一个很大 | 看清单里下一个功能的复杂度 | 中——不要开始,留给下次 |
| 你开始对早期代码记忆模糊 | 需要重新读之前改过的文件才能想起来 | 高——说明上下文已被压缩 |
| 单次会话工具调用超过 30 次 | 大致估算你调用了多少次工具 | 中——开始关注,准备收尾 |
经验法则:宁可早收尾一次(代价:多一次会话启动的 2 分钟),也不要晚收尾(代价:半成品 + 下次会话大量 token 用于恢复)。
安全退出协议——感觉快到极限时:
claude-progress.md:## 进行中
- #5: 购物车(约 60%)
- ✅ 数据模型和 API
- ✅ 添加/删除商品
- ❌ 数量修改(API 已写好,前端待对接,参考 /api/cart/items/[id])
- ❌ 价格计算(需考虑优惠券,目前按百分比折扣实现)
### 上次 Plan 遗留的设计决策
- 购物车价格计算采用"先算原价再减折扣"策略,不是"逐项折扣"
- 优惠券模型已建好(见 prisma/schema.prisma),支持百分比和固定金额两种
- 前端购物车组件计划用 /components/Cart.tsx,复用已有的 ProductCard 样式蒸馏的原则:只写下次会话需要但无法从代码推断的信息——设计决策、技术选型理由、未完成步骤的上下文。代码里能看到的实现细节不需要重复写。
下次会话读到这些信息后,可以快速重建 Plan 继续推进,而不是从头分析"为什么这样设计"。
绝不留下的状态:编译不通过、运行报错、数据库迁移没跑。下一个会话的第一件事是 bash init.sh,如果这都失败了,大量 token 会浪费在调试环境上。
当用户说"项目做了一半"时,初始化流程需要调整——先摸清现状,再建框架。
1. 阅读项目结构和技术栈 → ls, package.json, 核心目录
2. 阅读已有代码 → 理解架构模式、命名规范、错误处理方式
3. git log --oneline -30 → 了解开发历史
4. 尝试运行项目 → 确认能跑起来
5. 验证用户说的"已完成"功能 → 不能假设,要亲自验
6. 建立框架文件 → init.sh + claude-progress.md
7. 开始第一个新功能关键区别:
verified(但前提是你真的验证了)当所有功能都标记为 verified 时:
task-finish skill 的复盘流程执行。跨多会话的长期项目是典型的"大任务",必须复盘。重点关注:| 问题 | 根因 | 对策 |
|---|---|---|
| 过早宣告完成 | 没有功能清单对照 | 会话开始必读 claude-progress.md |
| 代码有 bug 但标记完成 | 没做端到端验证 | verified = 测试通过,不是"我觉得写完了" |
| 上下文耗尽留下半成品 | 没有主动管理上下文 | 检测信号 + 安全退出协议 |
| 后续会话不知从何开始 | 进度记录太模糊 | 写具体事实:做了什么、commit hash、下一步 |
| 环境配置浪费 token | 每次重新摸索 | init.sh 一键启动 |
| 新代码风格不一致 | 没读已有代码就动手 | 中途接手流程的第 2 步 |
| 复杂功能实现方向跑偏 | 没做方案设计就动手 | 用 task-start 对焦 + Plan 对齐方案 |
| Plan 和 progress.md 内容重复 | 职责不清 | Plan = 当前会话怎么做;progress = 项目做到哪了 |
| 条件(满足任一) | 判断 |
|---|---|
| 功能点 ≤ 3 个,且每个改动 ≤ 5 个文件 | 不需要,直接做 |
| 功能点 > 3 个,或任一功能涉及 > 5 个文件 | 需要此框架 |
| 预计需要跨 2 次以上会话 | 需要此框架 |
| 用户说"项目很大"、"分阶段做"、"长期任务" | 需要此框架 |
pending → in-progress → done → verified| 状态 | 含义 | 转换条件 |
|---|---|---|
pending | 未开始 | 初始状态 |
in-progress | 正在做 | 开始编码时标记 |
done | 代码写完 | 代码可运行、已 commit |
verified | 验证通过 | 通过端到端测试或手动验证完整用户流程 |
只有 verified 才算"完成"。done 意味着还需要在后续会话中验证。
初始化会话选择的第一个功能跳过 Plan,直接编码。原因:初始化阶段已经对项目有了全面了解,第一个功能通常是基础功能(如项目脚手架、数据模型),路径明确。从第二个功能开始,根据复杂度判断是否走 Plan。
启动例程第 4 步"快速冒烟测试"的具体操作:
npm test 或等价命令,跑全量测试。如果超过 2 分钟,只跑与最近 commit 相关的测试目标是 2 分钟内确认"已有功能没坏",不是做全面回归。
每次会话结束(不管是正常收尾还是安全退出),都用以下模板与用户沟通:
## 本次会话总结
- 完成:#1 用户登录、#2 用户注册
- 进行中:#3 书籍搜索(约 70%,API 完成,前端待对接)
- 下次会话计划:完成 #3 剩余部分,然后开始 #4 购物车
- 已知问题:搜索分页超过 100 条时性能下降,需要加索引不需要长篇大论,4 行以内说清楚。
task-start — 启动:对焦需求 + 设计方案
│
↓
task-execute(本 skill)— 执行:持续编码 + 跨会话进度管理
│
├─ 子任务开始 → 按需触发 task-start(需求模糊或 3+ 文件时)
├─ 子任务完成 → 触发 task-finish 的 CR 自检
├─ 全部完成 → 触发 task-finish 的完整复盘
│
↓
task-finish — 收尾:CR 自检 + 复盘沉淀© 312362115, 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 skills/task-execute of 312362115/claude.
Open the folder on GitHubat commit 2d4fa49
Task Execute 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 |
|---|---|---|---|---|---|---|
| Task Execute this skill312362115/claude | 107 | — | ~2.2k | Automated safety check: Pass | MIT | |
| Executealirezarezvani/claude-skills | 28k | — | ~831 | Automated safety check: Pass | MIT | |
| Ulw Executecode-yeongyu/oh-my-openagent | 70k | — | ~6.3k | Automated safety check: Pass | Custom licence | |
| Executebrycewang-stanford/Auto-Empirical-Research-Skills | 4.5k | — | ~370 | Automated safety check: Notes | Custom licence | |
| Executionalsk1992/CloddsBot | 2.9k | — | ~1.7k | Automated safety check: Pass | MIT | |
| Executive Mentoralirezarezvani/claude-skills | 28k | 1 repos | ~1.8k | Automated safety check: Pass | MIT |
alirezarezvani/claude-skills
/cs:execute <decision — Generate a 90-day execution plan with weekly milestones, DRIs, and check-in cadence from an approved decision.
code-yeongyu/oh-my-openagent
Executes a written ulw-plan work plan with Boulder state, evidence ledger, worktree discipline, and parallel subagents.
brycewang-stanford/Auto-Empirical-Research-Skills
Executes all registered notebooks, strips noisy cell metadata, and syncs Jupytext pairs.
alsk1992/CloddsBot
Execute trades on prediction markets with slippage protection and order management
alirezarezvani/claude-skills
Adversarial thinking partner for founders and executives. An agent skill from alirezarezvani/claude-skills.
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.
312362115/claude
专业图表生成技能:根据需求自动选择合适的图表类型,生成符合设计规范的 PNG 图表. An agent skill from 312362115/claude.
312362115/claude
深度调研技能:对任意命题进行系统性调研并输出专业研究报告. An agent skill from 312362115/claude.
312362115/claude
MD 文件浏览器预览:GitHub 风格渲染 + 左侧自动目录. An agent skill from 312362115/claude.
312362115/claude
通用写作技能:以"内容→组件→组合"的方式产出技术文档、产品文档、汇报材料. An agent skill from 312362115/claude.
312362115/claude
代码导读技能:帮助快速理解不熟悉的项目或模块,建立心智模型. An agent skill from 312362115/claude.
312362115/claude
数据库代码审查 + Migration 安全检查. An agent skill from 312362115/claude.
持续执行框架:让 Claude 在跨多轮会话的长期任务中保持高效运行。当用户的任务规模较大、需要跨多个上下文窗口完成时使用此技能。. Task Execute is an agent skill from 312362115/claude.
Run `npx skills add 312362115/claude --skill task-execute -a claude-code`. Or copy the skill folder (skills/task-execute in 312362115/claude) into .claude/skills/task-execute in your project. Claude Code loads it when a task matches its description.
Run `npx skills add 312362115/claude --skill task-execute -a codex`. Or copy the skill folder (skills/task-execute in 312362115/claude) into .agents/skills/task-execute 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 312362115/claude --skill task-execute -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/task-execute, .gemini/skills/task-execute, .github/skills/task-execute and .opencode/skills/task-execute in your project.
Going by SKILL.md and its folder, Task Execute needs the command-line tools its instructions call (npm, git, npx, curl and bash). Our summary lists: Node.js.
SKILL.md names 1 domain. As links in the text: anthropic.com. 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.
Task Execute is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.
About 2.2k tokens (SKILL.md is roughly 8.7k 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 Task Execute: Execute (alirezarezvani/claude-skills, 28k stars), Ulw Execute (code-yeongyu/oh-my-openagent, 70k stars), Execute (brycewang-stanford/Auto-Empirical-Research-Skills, 4.5k stars) and Execution (alsk1992/CloddsBot, 2.9k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
312362115 (a GitHub user) maintains it in 312362115/claude, which has 107 GitHub stars. The repository holds 20 skills in this directory. The repository was last updated on May 14, 2026.
Source: 312362115/claude on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.