Skill Creator
Azure/azqr
Create new skills, modify and improve existing skills, and measure skill performance.
Creates a focused workspace skill from the current conversation in QwenPaw, moving through a planning, approval, drafting, validation and publishing script pipeline.
Install QwenPaw Make Skill
$ npx skills add agentscope-ai/QwenPaw --skill make-skill -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install agentscope-ai/QwenPaw make-skill --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/agentscope-ai/QwenPaw.git skills-src && mkdir -p .claude/skills && cp -r skills-src/src/qwenpaw/agents/skills/make-skill-zh .claude/skills/make-skill && 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 "make-skill" agent skill from https://github.com/agentscope-ai/QwenPaw/tree/main/src/qwenpaw/agents/skills/make-skill-zh into .claude/skills/make-skill/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "make-skill", 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/agentscope-ai/QwenPaw/tree/main/src/qwenpaw/agents/skills/make-skill-zhType 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 agentscope-ai/QwenPaw --skill make-skill -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install agentscope-ai/QwenPaw make-skill --agent codexProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/agentscope-ai/QwenPaw.git skills-src && mkdir -p .agents/skills && cp -r skills-src/src/qwenpaw/agents/skills/make-skill-zh .agents/skills/make-skill && rm -rf skills-srcUse ~/.agents/skills/ instead of .agents/skills for a personal install.
Codex skills documentation · loads skills from .agents/skills/
Install the "make-skill" agent skill from https://github.com/agentscope-ai/QwenPaw/tree/main/src/qwenpaw/agents/skills/make-skill-zh into .agents/skills/make-skill/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "make-skill", 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 agentscope-ai/QwenPaw --skill make-skill -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install agentscope-ai/QwenPaw make-skill --agent cursorProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/agentscope-ai/QwenPaw.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/src/qwenpaw/agents/skills/make-skill-zh .cursor/skills/make-skill && 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 "make-skill" agent skill from https://github.com/agentscope-ai/QwenPaw/tree/main/src/qwenpaw/agents/skills/make-skill-zh into .cursor/skills/make-skill/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "make-skill", 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/agentscope-ai/QwenPaw.git --path src/qwenpaw/agents/skills/make-skill-zh--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 agentscope-ai/QwenPaw --skill make-skill -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install agentscope-ai/QwenPaw make-skill --agent gemini-cliProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/agentscope-ai/QwenPaw.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/src/qwenpaw/agents/skills/make-skill-zh .gemini/skills/make-skill && 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 "make-skill" agent skill from https://github.com/agentscope-ai/QwenPaw/tree/main/src/qwenpaw/agents/skills/make-skill-zh into .gemini/skills/make-skill/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "make-skill", 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 agentscope-ai/QwenPaw make-skillInstalls 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 agentscope-ai/QwenPaw --skill make-skill -a github-copilotProject install goes to .agents/skills/; add -g for ~/.copilot/skills/.
$ git clone --depth 1 https://github.com/agentscope-ai/QwenPaw.git skills-src && mkdir -p .github/skills && cp -r skills-src/src/qwenpaw/agents/skills/make-skill-zh .github/skills/make-skill && 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 "make-skill" agent skill from https://github.com/agentscope-ai/QwenPaw/tree/main/src/qwenpaw/agents/skills/make-skill-zh into .github/skills/make-skill/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "make-skill", 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 agentscope-ai/QwenPaw --skill make-skill -a opencodeOpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.
$ gh skill install agentscope-ai/QwenPaw make-skill --agent opencodeProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/agentscope-ai/QwenPaw.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/src/qwenpaw/agents/skills/make-skill-zh .opencode/skills/make-skill && 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 "make-skill" agent skill from https://github.com/agentscope-ai/QwenPaw/tree/main/src/qwenpaw/agents/skills/make-skill-zh into .opencode/skills/make-skill/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "make-skill", 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.
Facts
- Skill name
make-skill- GitHub stars
- 35k
- Token cost
- ~1.2k tokens
- SKILL.md length
- 295 words
- Files
- 8 (incl. scripts, references)
- Skills in repo
- 20
- Repo updated
- First seen
- Licence
- Apache-2.0
At a glance
Creates a focused workspace skill from the current conversation in QwenPaw, moving through a planning, approval, drafting, validation and publishing script pipeline.
- Saving a reusable process or decision from the current conversation as a new skill
- SKILL.md covers 脚本接口, 计划, 构建 and 校验、测试并发布
- Runs Python scripts from its folder; calls python
- Turning a repeated workflow into a parameterized Batch for a workflow skill
What it does
Written in Chinese, this skill turns a reusable decision, piece of knowledge, template or workflow from the current conversation into a new skill under the agent workspace. It runs four scripts in order through a shell command, each reading a JSON object from stdin and returning one: create_plan.py to create or revise a plan, init_draft.py to initialize a draft once approved, validate_skill.py to check the draft, and publish_skill.py to publish it using the digest the validator returned. Every call carries the same workspace path, and returned ids such as plan_id and draft_id are reused as given, never guessed from a name.
Planning picks a primary type and the files actually needed, informed by a reference on type and package structure, and reads a behavior-testing reference when the test mode is not off. For workflow skills, a batch mode can be enabled when the actions, branches and success conditions for a reusable area can be specified up front and a stored entry point would meaningfully cut back-and-forth; a further reference on running batches is read only once batch mode is chosen. The plan stage stays read-only until the user approves it, and the saved plan is rendered in Chinese as a compact options table covering type, batch, execution mode and behavior-testing level.
When your agent uses it
- Saving a reusable process or decision from the current conversation as a new skill
- Turning a repeated workflow into a parameterized Batch for a workflow skill
- Validating and publishing a drafted skill package
Example prompts
- “Save this deployment checklist we just worked out as a skill.”
- “Turn this repeated data-cleaning workflow into a skill with batch mode enabled.”
- “/make-skill PDF invoice extraction”
Requirements
- Python to run the create_plan, init_draft, validate_skill and publish_skill scripts
- A QwenPaw agent workspace
What it can do on your machine
Read from SKILL.md and the folder at commit f389534. It shows what the files ask for, not the result of running them.
Tool permissions
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.
Runs code
Ships 4 files in scripts/ (Python), which the agent can run.
Shell commands in SKILL.md call:
python
From the folder's file list and the shell code blocks in SKILL.md.
Network
No URLs in SKILL.md.
From URLs in SKILL.md, links to its own repository left out.
Credentials
Names no API keys, tokens, secrets or passwords.
From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.
Context cost
QwenPaw Make Skill loads about 1.2k tokens when it runs, and up to ~3.5k if it reads all its reference files. Until then it costs about 32 tokens; SKILL.md has 295 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.
Safety
Auto-check passed
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.
SKILL.md
The full file from agentscope-ai/QwenPaw at commit f389534, republished under its Apache-2.0 licence (© agentscope-ai). 295 words, ~1,167 tokens.
Download SKILL.mdSave it as
.claude/skills/make-skill/SKILL.md (or your agent's skills folder). This skill also uses 7 other files; get the full folder from GitHub.- name
- make-skill
- description
- 将当前对话中可复用的决策、知识、模板或工作流创建为聚焦的 workspace Skill。适用于带 focus 参数的 /make-skill，以及“保存这个流程”“把它做成 skill”等请求；不适用于一次性总结或普通文件创建。
- metadata.builtin_skill_version
- 2.1
创建 Skill
从当前对话创建一个新的 workspace Skill，依次完成规划、用户批准、草稿编写、校验和发布。
从运行时目录上下文获取 <workspace>：使用当前 agent workspace 的绝对路径（未单独配置项目时，也是工作目录）。整个生命周期传入同一个值，与任务的 project directory 和脚本 cwd 分开确定。生命周期产物归属 <workspace>/.qwenpaw/make-skill/，发布后的 Skill 归属 <workspace>/skills/。
脚本接口
通过 execute_shell_command 运行 python scripts/<script>，将 cwd 设为 available-skills 条目中本 Skill 的 <dir>。每个脚本从 stdin（或 --input <file>）读取一个 JSON 对象，返回一个 JSON 对象。每次输入均包含 workspace；下表列出其余顶层字段。
| 操作 | 脚本 | 其余输入字段 | 成功返回 |
|---|---|---|---|
| 创建计划 | create_plan.py | plan | plan_id、规范化 plan |
| 修改该计划 | create_plan.py | plan_id、完整新 plan | 同一个 plan_id、规范化 plan |
| 批准后初始化 | init_draft.py | plan_id | draft_id、skill_dir |
| 校验草稿 | validate_skill.py | draft_id | digest |
| 发布已校验草稿 | publish_skill.py | draft_id、来自校验结果的 expected_digest | 发布结果 |
plan_id 标识一份可修改的计划，修订和改名时均沿用。draft_id 标识初始化后的草稿，用于校验、测试和发布；skill_dir 是其 package 文件的编写位置。原样使用返回值，不根据名称或路径推算 ID。
计划
/make-skill <focus> 的 focus 必填；自然语言请求则结合请求和当前对话推断。用户较晚的纠正会替换冲突的旧规则。保留会改变未来 agent 行为的稳定指导、契约、模板和流程，排除一次性数据、临时路径、密钥与重试噪声。
阅读主类型与包结构，选择一个主类型和实际需要的文件。计划的测试模式不是 off 时，在定义测试目标前阅读行为测试。
Batch workflow
存储 Batch 是随 workflow Skill 一起提供的参数化 run_tool_batch 程序。当一个可复用区域的动作、分支和成功条件能在执行前说明，并且存储入口能实质减少 agent 与工具往返时，设置 batch: true。该区域可以是完整 workflow、一个 substantial helper，或一个语义完整的 tool-native action；action 数量不是判据。只要处理规则已经确定，运行时数据、observation 和最终 agent review 都不妨碍使用 Batch。
只有运行时必须重新发明下一步或成功条件，或者统一入口没有实际复用价值时，才设置 batch: false。用户明确要求 Batch 时，将该选择纳入计划，不再争论 eligibility。
只有选择 batch: true 后，才在最终确定 workflow 和文件树前阅读运行 Batch；batch: false 时不要读取。
保存并展示计划
计划阶段除通过 create_plan.py 保存计划外只读：依据对话证据和已有产物判断，不执行或探测候选工作流，不创建 package 文件，也不初始化 draft。首次创建不传 plan_id，传入完整候选计划：
{
"workspace": "<workspace>",
"plan": {
"revision": 1,
"focus": "一句话说明提炼范围",
"name": "lowercase-hyphen-name",
"goal": "未来 agent 要达成的结果",
"type": "workflow",
"batch": true,
"steps": ["用户可判断的流程步骤"],
"package": ["SKILL.md", "scripts/run.batch.json"],
"execution": "foreground",
"test": {"mode": "off", "target": ""},
"warnings": []
}
}修订时，在上述输入的顶层加入返回的 plan_id，并将 plan 替换为完整修订计划，而非局部 patch。这会更新原计划，不创建副本。更新返回 missing-plan 时，返回规划和批准流程，不继续构建。计划已保存不代表用户已批准。
用中文渲染规范化计划，并把已选值和全部可选项一起展示，让用户无需了解 schema 也能修改。用户可见计划必须包含下列紧凑选项表，不得用散文或批准提示代替；非 workflow 省略 Batch 行：
| 选项 | 当前值 | 全部可选 |
|---|---|---|
| 类型 | 当前中文值 | 指令 / 模板 / 工作流 |
| Batch（仅 workflow） | 启用或关闭 | 启用 / 关闭 |
| 执行方式 | 前台或后台 | 前台 / 后台 |
| 行为测试 | 当前中文值 | 关闭 / 冒烟测试 / 完整评测 |
传给脚本的值仍分别使用 instruction/template/workflow、true/false、foreground/background 和 off/smoke/eval。同时展示名称、目标、工作流、完整文件树、适用时的测试目标和警告。不得发明脚本 schema 之外的选项；不展示 Batch 关闭理由、schema、revision 或内部 enum。请用户批准、修改或取消，然后结束当前响应，不再调用工具。
只有后续新的用户消息明确批准最近一次已展示的 create_plan.py 返回计划，才可进入构建。/make-skill 发起的是规划；此前的任务讨论或手写方案不能替代这次计划展示与批准。
- 用户修改后合并反馈、增加
revision，更新同一份计划。在当前会话中串行修订，然后展示完整返回计划，等待批准；旧批准不适用于修改后的计划。 - 取消时停止，保留计划，不创建 draft。区分知悉与批准；用户意图不明确时，只追问一次简短确认并等待回复。
- execution 和 test 已在计划中，不再单独询问。
本版本只创建新 Skill；名称冲突时通过新 revision 重新批准名称，不覆盖已有 Skill。
构建
批准后，将已保存的 plan_id 传给 init_draft.py。初始化会将当前计划快照保存到新 draft；后续修改 plan 不会更新该 draft。不接受内联替代计划。计划缺失或无效时返回规划阶段，不继续构建。
execution 决定由当前 agent 还是后台 subagent 完成 Skill 创建。选择 background 时，初始化后调用 spawn_subagent 并设置 background: true，将完整批准计划、最新纠正、workspace、draft_id 和 skill_dir 交给通用 subagent，由其编写文件、校验、执行已批准的行为测试并发布，不再请求批准。完成后报告创建结果；除已批准的行为测试外，运行生成的 Skill 需用户另行要求。
只在返回的 skill_dir 中创建批准文件。生成的 SKILL.md 使用合法 frontmatter：
---
name: lowercase-hyphen-name
description: 简要说明能力及适用场景。
---正文只保留必要流程和约束，不重复 description；无需 type metadata。
校验前，从“未来 agent 看不到原始对话”的视角通读 package。除非资源确实随包提供且可复用，否则删除对原任务目录、旧输出、临时 ID、当前 case 示例或 make-skill draft/publish 话术的引用。复用已有 helper 时，要泛化路径、docstring 和结果说明，并确认实现仍符合最终可复用规则。这只是一轮作者自查，不增加 case-specific lifecycle 检查。
校验、测试并发布
执行任何 draft script 或 batch 前，先对初始化后的草稿运行 validate_skill.py。
按静态或安全错误修复 draft 并重新校验。测试与 Batch 相互独立：按行为测试只运行已批准的测试，off 不执行 draft。测试或 Batch 运行失败时保留 draft，报告具体错误；如果修正方向明确，就修改 Skill 后重新校验，不用 fallback 隐藏失败。
通过 publish_skill.py 发布未经改动且已校验的 draft，将校验结果中的 digest 作为 expected_digest 传入。
成功后报告 package tree、校验摘要、已执行的测试结果和调用命令 /<name>；冲突或失败时保留 draft 并报告错误。发布 Skill 已经完成持久化；除非用户另行明确要求，不再写入 MEMORY.md 或 daily memory。
© agentscope-ai, Apache-2.0. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file
Files
SKILL.md and 7 other files (scripts, references) in src/qwenpaw/agents/skills/make-skill-zh of agentscope-ai/QwenPaw.
- SKILL.md
- references/behavior-testing.md
- references/run-batch.md
- references/type-and-package.md
- scripts/create_plan.py
- scripts/init_draft.py
- scripts/publish_skill.py
- scripts/validate_skill.py
Open the folder on GitHubat commit f389534
Compare with similar skills
QwenPaw Make Skill 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 |
|---|---|---|---|---|---|---|
| QwenPaw Make Skill this skillagentscope-ai/QwenPaw | 35k | — | ~1.2k | Automated safety check: Pass | Apache-2.0 | |
| Skill CreatorAzure/azqr | 795 | 89 repos | ~8.2k | Automated safety check: Pass | Apache-2.0 | |
| Claude Code Skill Developer Guidediet103/claude-code-infrastructure-showcase | 10k | 11 repos | ~3.5k | Automated safety check: Pass | MIT | |
| Darwin Skill Optimizeralchaincyf/darwin-skill | 6.2k | 1 repos | ~4.7k | Automated safety check: Pass | MIT | |
| Claude Code Command Developmentanthropics/claude-plugins-official | 38k | 10 repos | ~4.8k | Automated safety check: Pass | Apache-2.0 | |
| Claude Code Plugin Structureanthropics/claude-plugins-official | 38k | 10 repos | ~3.4k | Automated safety check: Pass | Apache-2.0 |
Similar skills
- Official
Claude Code Skill Developer Guide
diet103/claude-code-infrastructure-showcase
A guide to creating and managing Claude Code skills with auto-activation: skill-rules.json triggers, hooks, enforcement levels, YAML frontmatter and progressive disclosure.
Darwin Skill Optimizer
alchaincyf/darwin-skill
Scores SKILL.md files on a nine-dimension rubric, then improves them in a keep-or-revert loop with independent judge agents, test prompts, git history and human checkpoints.
- Official
Claude Code Command Development
anthropics/claude-plugins-official
Explains how to write Claude Code slash commands: Markdown files with YAML frontmatter, arguments, file references, bash context and interactive prompts.
- Official
Claude Code Plugin Structure
anthropics/claude-plugins-official
Explains the directory layout, plugin.json manifest and component organization of a Claude Code plugin, including auto-discovery and portable paths.
Skill Release Gate
rohitg00/ai-engineering-from-scratch
Evaluates an Agent Skill bundle before release for structure, trigger quality, artifact improvement, script correctness, safety, installed-tree integrity and host portability.
More from agentscope-ai/QwenPaw
All 20 skills in this repoTerraform and OpenTofu Guide
agentscope-ai/QwenPaw
Guidance for writing and testing Terraform and OpenTofu code: module structure, naming, test approaches, CI/CD workflows, state handling and security scanning.
Make Skill
agentscope-ai/QwenPaw
Turns reusable decisions, templates or workflows from the current conversation into a new workspace skill through plan, approval, draft, validation and publication.
QwenPaw Scheduled Tasks
agentscope-ai/QwenPaw
Creates and manages scheduled or recurring jobs with the qwenpaw cron commands, always tied to an explicit agent ID and a confirmed target channel.
DOCX Creation and Editing
agentscope-ai/QwenPaw
Creates, reads and edits Word .docx files, including tracked changes and comments, using docx-js for new files and XML editing for existing ones.
Mailbox Operations Hub
agentscope-ai/QwenPaw
Connects, registers, and operates a personal mailbox, reading, searching, sending, and organizing, through a managed mail server for nine domains.
OMP Sub-Agent Role Presets
agentscope-ai/QwenPaw
Gives the allowed_tools and skills preset for each OMP sub-agent role, to apply when calling spawn_subagent.
Related
Categories
Questions about QwenPaw Make Skill
What does QwenPaw Make Skill do?
Creates a focused workspace skill from the current conversation in QwenPaw, moving through a planning, approval, drafting, validation and publishing script pipeline. Written in Chinese, this skill turns a reusable decision, piece of knowledge, template or workflow from the current conversation into a new skill under the agent workspace.py to publish it using the digest the validator returned.
When should I use QwenPaw Make Skill?
QwenPaw Make Skill fits situations like: saving a reusable process or decision from the current conversation as a new skill; turning a repeated workflow into a parameterized Batch for a workflow skill; validating and publishing a drafted skill package.
How do I install QwenPaw Make Skill in Claude Code?
Run `npx skills add agentscope-ai/QwenPaw --skill make-skill -a claude-code`. Or copy the skill folder (src/qwenpaw/agents/skills/make-skill-zh in agentscope-ai/QwenPaw) into .claude/skills/make-skill in your project. Claude Code loads it when a task matches its description.
How do I install QwenPaw Make Skill in Codex?
Run `npx skills add agentscope-ai/QwenPaw --skill make-skill -a codex`. Or copy the skill folder (src/qwenpaw/agents/skills/make-skill-zh in agentscope-ai/QwenPaw) into .agents/skills/make-skill in your project. Codex loads it when a task matches its description.
Can I use QwenPaw Make Skill in Cursor, Gemini CLI or GitHub Copilot?
Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add agentscope-ai/QwenPaw --skill make-skill -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/make-skill, .gemini/skills/make-skill, .github/skills/make-skill and .opencode/skills/make-skill in your project.
What does QwenPaw Make Skill need to run?
Going by SKILL.md and its folder, QwenPaw Make Skill needs Python for the scripts in its folder and the command-line tools its instructions call (python). Our summary lists: Python to run the create_plan, init_draft, validate_skill and publish_skill scripts; A QwenPaw agent workspace.
Does QwenPaw Make Skill access the network?
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.
Is QwenPaw Make Skill safe to install?
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.
What licence does QwenPaw Make Skill use?
QwenPaw Make Skill is published under the Apache-2.0 licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.
How many tokens does QwenPaw Make Skill use?
About 1.2k tokens (SKILL.md is roughly 4.7k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full. Its references folder adds about 2.3k tokens, read only when the agent opens those files.
What are the alternatives to QwenPaw Make Skill?
Skills that share tags, products or a category with QwenPaw Make Skill: Skill Creator (Azure/azqr, 795 stars), Claude Code Skill Developer Guide (diet103/claude-code-infrastructure-showcase, 10k stars), Darwin Skill Optimizer (alchaincyf/darwin-skill, 6.2k stars) and Claude Code Command Development (anthropics/claude-plugins-official, 38k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
Who maintains QwenPaw Make Skill?
agentscope-ai (a GitHub organization) maintains it in agentscope-ai/QwenPaw, which has 35,493 GitHub stars. The repository holds 20 skills in this directory. The repository was last updated on October 8, 2026.
Source: agentscope-ai/QwenPaw on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.