Token导航 LogoToken导航

Agent Skill · 研究检索

positron-issue-creator(正电子问题创造者)

用于围绕 GitHub 仓库、Issue、Pull Request、分支、提交和代码协作流程提供辅助能力。它适合让 Agent 查询项目状态、整理变更、辅助创建或检查协作事项,并把仓库中的信息转成可执行的下一步。使用时需要区分只读查询和写入操作;涉及创建 PR、修改 Issue、推送分支或访问私有仓库时,应确认 token 权限、目标仓库范围和用户授权。

positron-issue-creator 是研究检索类 Agent Skill,可用宿主为 Codex、Claude、Cursor、Gemini CLI,通过GitHub 仓库获取,权限为需要联网;许可证为 MIT,第三方扫描有提醒项,按安装量在研究检索类的 73,675 个 Skill 里排第 41,613。

总安装 1,152周安装 49GitHub Stars 4,030下载 404核验 2026-05-01

安装说明

本站只整理中文说明,不托管安装包,也不代用户安装。
GitHub
许可证
MIT

安装方式

通过对话安装

复制提示词发给支持本地命令或 Skills 的 AI 助手,先确认命令和权限,再让它执行。

请帮我安装这个 Agent Skill:positron-issue-creator(正电子问题创造者)
来源仓库:https://github.com/posit-dev/positron
仓库路径:skills/positron-issue-creator
安装命令:
npx skills add https://github.com/posit-dev/positron --skill positron-issue-creator
安装前请先检查当前环境是否支持对应 CLI,并向我确认将要执行的命令、安装目录、联网范围和文件读写权限;确认后再执行。

命令行安装

复制命令到本机终端执行。不同来源提供的安装方式可能略有差异;本站展示可直接复制的安装命令,安装前请核对来源页面。

skills.shnpx skills
npx skills add https://github.com/posit-dev/positron --skill positron-issue-creator

这个 Skill 是做什么的

研究检索类 Skill 主要解决「找资料、核对事实、把来源整理清楚」的问题,通常会让助手先检索再总结。

positron-issue-creator 用于围绕 GitHub 仓库、Issue、PR 等协作流程提供辅助能力。适合查询项目状态、整理变更、创建协作事项并生成可执行下一步。使用时需区分只读查询与写入操作,避免越权修改。涉及创建 PR、修改 Issue 或推送分支时,应确认 token 权限和仓库范围。

建议在私有仓库操作前获取用户明确授权。

来源仓库内路径:skills/positron-issue-creator

上手步骤

4 步
  1. 1

    确认自己的宿主工具

    公开资料标注支持 Codex、Claude、Cursor、Gemini CLI;先确认自己用的是其中之一,再按对应工具的 Skills 目录放置。

  2. 2

    拿到安装命令

    可以直接复制的命令是 npx skills add https://github.com/posit-dev/positron --skill positron-issue-crea…;命令里的占位符换成自己的路径或密钥再执行。

  3. 3

    安装后重启宿主

    命令执行完要完全退出宿主工具再打开,让新装的 Skill 被重新扫描到,否则列表里可能看不到。

  4. 4

    按最小权限试用

    它需要需要联网,先在测试目录或测试账号里跑,确认没问题再放到正式项目。

常见问题

6 条

positron-issue-creator 怎么安装?

在终端执行 npx skills add https://github.com/posit-dev/positron --skill positron-issue-creator。装完完全退出宿主工具再打开,让它重新扫描本地 Skill。

positron-issue-creator 支持哪些 AI 工具?

公开资料标注支持 Codex、Claude、Cursor、Gemini CLI。其他工具只要能读取本地 Skill 目录,一般也能手动放进去,但要自己确认触发方式是否一致。

positron-issue-creator 需要什么权限?

权限级别是需要联网。该 Skill 可能需要联网访问来源站点、仓库或外部 API;具体网络访问范围需要结合源码和 README 复核。

positron-issue-creator 是免费的吗?

来源标注的许可证是 MIT。本站不代收任何费用,也不托管安装包;能否商用、要不要署名,以许可证原文为准。

positron-issue-creator 用的人多吗?

公开数据是累计安装 1,152 次,近一周安装 49 次,下载 404 次,GitHub 4,030 星。这些数字来自第三方目录统计,只能当作热度参考,不代表质量或安全性。

positron-issue-creator 安全吗?

第三方扫描有提醒项,说明存在需要人工确认的行为。安装前请打开源码看清它读了什么、联网到哪里。

值得选的地方和要先想清楚的地方

值得选的地方

  • 同时适配 4 种工具,换客户端不用重新找替代品。
  • 3 个目录同时收录,说明这个 Skill 流传比较广。
  • 许可证明确为 MIT,商用和分发边界好判断。
  • 来源仓库有 4,030 星,维护活跃度相对可查。

先想清楚的地方

  • 第三方扫描存在提醒项或未通过项,需要人工逐条确认。
  • 第三方目录整理,版本更新和行为细节以来源仓库为准。

适不适合你

更适合

  • 已经在用 Codex,想直接扩展它能力的人。
  • 需要处理研究检索类任务、又不想每次都手写提示词的人。

不太适合

  • 需要厂商级技术支持和 SLA 的生产系统。

研究检索类 Skill 对比

6 个同类
Skill总安装GitHub 星权限许可证扫描
find-skills

寻找技能 · Codex、Claude

31,199,81316,486操作浏览器MIT有提醒
self-improving-agent

自我改进 Agent · OpenClaw

16,464,0023,396接触敏感数据MIT-0通过
soultrace

灵魂追踪 · Codex、Claude

7,588,94412需要联网未明确有提醒
self-improving

自我完善 · OpenClaw

6,829,2841,046需要联网MIT-0通过
microsoft-foundry

微软代工厂 · Codex、Claude

6,614,144764调用外部服务未明确有提醒
positron-issue-creator

正电子问题创造者 · 本页

1,1524,030需要联网MIT有提醒

按安装量取同分类前几名;数字来自第三方目录统计,只作热度参考,不代表质量结论。

SKILL.md 原文

Positron Issue Creator

Purpose

This skill guides the drafting of high-quality GitHub issues for the Positron IDE repository. It ensures issues are:

  • Thoroughly checked for duplicates before drafting
  • Properly labeled for efficient triage
  • Written with complete, specific information
  • Free of unnecessary fluff and filler
  • Actionable by the development team
  • Ready for manual submission by the user

When to Use This Skill

Use this skill when:

  • User explicitly asks to draft, create, file, or report an issue
  • User describes a bug or feature request that should be tracked
  • Drafting documentation or improvement requests
  • User says "can you draft an issue for..." or similar

Do NOT use this skill for:

  • Intake rotation duties (use positron-intake-rotation instead)
  • Responding to existing issues
  • General Positron development tasks

GitHub Access Policy

Read operations (ALLOWED):

  • Search for existing issues and discussions via gh CLI
  • Fetch repository labels via gh CLI
  • View issue details for duplicate checking
  • Read any public repository information

Write operations (NOT ALLOWED):

  • Creating issues directly via gh issue create
  • Commenting on issues
  • Modifying labels on existing issues
  • Any other GitHub write operations

Instead: Prepare issues in markdown files or clipboard-ready format for manual user submission.

Core Workflow

Important: This skill prepares issues for manual submission. It does NOT automatically create GitHub issues. The user maintains full control over submitting to GitHub.

Follow this workflow for every issue drafting request:

1. Gather Complete Context

Before drafting anything, ensure all necessary information is available. Use iterative questioning if needed.

For Bug Reports, obtain:

  • Positron version (Help > About or specific build number)
  • Operating system and version
  • Session details (R/Python version)
  • Exact steps to reproduce
  • Expected vs. actual behavior
  • Error messages (from UI, Output panel, or Developer Console)
  • Screenshots if relevant

For Feature Requests, obtain:

  • Clear description of the desired feature
  • Use case (why it's needed, what problem it solves)
  • Proposed behavior (how it should work)
  • Any related issues or examples from other tools

Ask specific questions when information is missing:

  • "What Positron version are you using? Check Help > About"
  • "What's the exact error message displayed?"
  • "What did you expect to happen vs. what actually happened?"
  • "Can you provide the specific steps to reproduce this?"

Never make assumptions. If unclear, ask rather than guess.

2. Search for Duplicates

Use scripts/search_duplicates.sh to search for existing issues and discussions:

cd /path/to/positron/.claude/skills/positron-issue-creator
./scripts/search_duplicates.sh "keywords from issue"

Review results carefully:

  • Check both open and closed issues
  • Look at discussions as well
  • Consider variations of the search terms

Present findings to user:

  • Show all potentially related issues
  • Highlight any that seem very similar
  • Ask user to confirm whether these are duplicates
  • For uncertain matches, explicitly ask: "Is this the same issue as #1234?"

If duplicate found:

  • Inform user that issue already exists
  • Provide link to existing issue
  • Suggest they add a comment or 👍 reaction if they want to track it
  • Do NOT create new issue

If no duplicates:

  • Proceed to drafting the issue
  • Reference any related issues in the draft

3. Select Appropriate Labels

Use scripts/fetch_labels.sh to retrieve current repository labels:

cd /path/to/positron/.claude/skills/positron-issue-creator
./scripts/fetch_labels.sh

Choose labels based on:

Area labels (select 1-2):

  • area: console - Console/REPL functionality
  • area: notebook - Jupyter notebook integration
  • area: editor - Text editor functionality
  • area: plots - Plot viewer and visualization
  • area: data-explorer - Data viewer and explorer
  • area: connections - Database connections
  • area: help - Help pane and documentation
  • area: ui - General UI/UX issues
  • Review full list from fetch_labels.sh for complete options

Type label (select 1):

  • Bug - Something doesn't work as intended
  • Feature Request - New capability or enhancement
  • Documentation - Documentation improvements
  • Performance - Works but too slowly

Other considerations:

  • Avoid adding priority labels (set during triage)
  • Don't add status labels (will be set by team)
  • Multiple area labels are acceptable if issue spans components

4. Draft the Issue

Use the templates in references/issue_templates.md as starting points, but adapt to the specific issue.

Load templates when needed:

  • Bug reports: Reference bug report structure
  • Feature requests: Reference feature request structure
  • Hybrid cases: Adapt as appropriate

Follow writing guidelines from references/writing_guidelines.md:

Core principles:

  1. Be terse - Every word serves a purpose
  2. Be fluff-free - No apologies, preambles, or unnecessary politeness
  3. Be specific - Exact versions, precise steps, concrete details
  4. Be direct - Get to the point immediately

Title guidelines:

  • Bug: [Component] fails when [condition]
  • Feature: Add [feature] to [component]
  • Complete sentence that tells the full story
  • Scannable and searchable

Body structure:

  1. What - The issue itself (1 sentence)
  2. Why - Impact/context (1-2 sentences if not obvious)
  3. How - Steps or proposed solution (bullet points)
  4. Details - System info, errors, screenshots (as needed)

Example bug report:

Title: Console freezes when printing dataframes with 100k+ rows

The console becomes unresponsive when printing large dataframes.

## Steps to reproduce

1. Create dataframe: `df = pd.DataFrame({'a': range(100000)})`
2. Print it: `print(df)`
3. Console freezes, UI becomes unresponsive

## System details

- Positron 2024.10.0 Build 123
- macOS 14.5
- Python 3.11.6

## Error messages

Developer Console shows: "Maximum call stack size exceeded"

Example feature request:

Title: Add keyboard shortcut to insert markdown cell in notebooks

Currently inserting markdown cells requires clicking the dropdown menu.
Keyboard shortcut would improve notebook authoring workflow.

## Proposed behavior

- Add keyboard shortcut (e.g., Cmd+M or Ctrl+M)
- Should work when focus is in notebook
- Should insert cell below current cell

## Context

Similar to Jupyter's 'M' key in command mode. Notebook workflows
frequently alternate between code and markdown cells.

Common anti-patterns to avoid:

  • Unnecessary background or preambles
  • Vague descriptions ("it doesn't work", "sometimes crashes")
  • Combining multiple unrelated issues
  • Apologetic or overly polite language
  • Missing concrete details (exact versions, error messages)
  • Long-winded explanations when concise ones suffice

Review checklist before presenting:

  • Title is complete and specific
  • Body starts with the core issue
  • Reproduction steps are clear (for bugs)
  • System details included (for bugs)
  • Error messages are exact quotes
  • No unnecessary fluff
  • Each sentence adds value
  • Single, focused topic
  • Appropriate labels selected

5. Present Draft to User

Show the complete drafted issue including:

  • Title
  • Full body text
  • Proposed labels

Ask user: "Does this accurately capture the issue? Would you like any changes before I create it?"

Allow for iteration:

  • User may want to adjust wording
  • May remember additional details
  • May want to emphasize different aspects

Make requested changes and show updated draft.

6. Prepare Issue for Manual Submission

Once user approves the draft, offer options for how they want to use it:

Ask the user: "How would you like me to prepare this issue?"

  • Option 1: Save to a markdown file
  • Option 2: Format for clipboard (provide text ready to copy)
Option 1: Save to Markdown File

Create a markdown file with all issue details:

# Create file with timestamp in name for uniqueness
cat > "positron-issue-$(date +%Y%m%d-%H%M%S).md" <<'EOF'
---
title: Issue title here
labels: area: console, Bug
repository: posit-dev/positron
---

Full issue body here
with multiple lines
EOF

After saving:

  • Show the file path
  • Remind user to manually create the issue on GitHub
  • Provide quick link: https://github.com/posit-dev/positron/issues/new
Option 2: Format for Clipboard

Present the issue in a format ready to copy:

**Title:**
Issue title here

**Labels:**
area: console, Bug

**Body:**
Full issue body here
with multiple lines

---
Create this issue at: https://github.com/posit-dev/positron/issues/new

After presenting:

  • Explain that user should copy this text
  • Remind them to paste into GitHub's new issue form
  • Note that they'll need to manually select labels in the UI

Important Guidelines

Duplicate Detection

Be thorough but not pedantic:

  • Search with multiple keyword combinations
  • Check both issues and discussions
  • Look at closed items too (might be fixed or wontfix)

When uncertain:

  • Show user the potentially similar issues
  • Ask explicitly: "Is this the same as what you're reporting?"
  • Err on the side of creating new issues rather than incorrectly marking as duplicate

Context Gathering

Never guess or assume:

  • If version is unclear, ask specifically
  • If steps are vague, request clarification
  • If error message is paraphrased, ask for exact text

Be patient with iteration:

  • Users may not have all information immediately
  • May need to reproduce issue to get details
  • It's better to ask multiple questions than create incomplete issue

Writing Style

Optimize for scanability:

  • Busy developers need to quickly understand the issue
  • Put most important information first
  • Use formatting (headings, lists, code blocks) appropriately

Respect reader's time:

  • No unnecessary pleasantries beyond "Thanks for reporting"
  • No apologetic language
  • No marketing-speak or enthusiasm
  • Just clear, factual information

Be precise:

  • Use exact versions, not "latest" or "recent"
  • Quote error messages exactly
  • Number steps clearly
  • State actual behavior, not interpretations

Special Cases

Security Issues

If user describes a security vulnerability:

  1. Do NOT create public issue
  2. Inform user: "This appears to be a security issue. Please report it privately to security@posit.co instead of creating a public issue"
  3. Do NOT proceed with issue creation

Documentation Issues

Treat as feature requests but focus on:

  • What documentation is missing or incorrect
  • Where users would look for this information
  • Suggested improvements

Label with Documentation type.

Performance Issues

Use bug report template but emphasize:

  • What operation is slow
  • How long it takes vs. expected time
  • System details including hardware
  • Data size or complexity

Label with Performance type.

Multiple Related Issues

If user describes several related but distinct issues:

  1. Identify each separate issue
  2. Explain to user: "This sounds like 3 separate issues. I'll help create each one individually."
  3. Create issues one at a time
  4. Cross-reference in issue bodies if related

Scripts Reference

scripts/fetch_labels.sh

Retrieves all repository labels for categorization.

Usage:

./scripts/fetch_labels.sh          # Human-readable output
./scripts/fetch_labels.sh --json   # JSON output for parsing

scripts/search_duplicates.sh

Searches for potential duplicate issues and discussions.

Usage:

./scripts/search_duplicates.sh "search terms"
./scripts/search_duplicates.sh "search terms" --limit 30

Returns:

  • Matching issues (open and closed)
  • Related discussions
  • Direct links to review

References

Load these reference documents when drafting issues:

  • references/issue_templates.md - Templates for bugs, features, and hybrid issues
  • references/writing_guidelines.md - Detailed writing guidance, anti-patterns, examples

Common Mistakes to Avoid

  1. Creating duplicate issues - Always search first, show results to user
  2. Incomplete information - Ask questions until all details are gathered
  3. Verbose writing - Cut all fluff, be direct and specific
  4. Vague titles - Titles should tell the complete story
  5. Multiple issues in one - Split into separate, focused issues
  6. Assuming context - Ask user to confirm unclear details
  7. Skipping labels - Always fetch and apply appropriate labels
  8. Preparing without user approval - Always show draft and get confirmation before preparing files

Success Criteria

A successful issue draft means:

  • No duplicates exist (or user confirmed it's distinct)
  • All necessary information is included
  • Issue is terse and free of fluff
  • Title accurately summarizes the issue
  • Appropriate labels identified
  • User approved the draft
  • Issue prepared in user's preferred format (markdown file or clipboard text)
  • User has clear instructions for manual submission to GitHub

Workflow Summary

1. Gather Context
   ↓
   Ask specific questions until all info available
   ↓
2. Search Duplicates
   ↓
   Run scripts/search_duplicates.sh
   ↓
   Show results to user, confirm not duplicate
   ↓
3. Select Labels
   ↓
   Run scripts/fetch_labels.sh
   ↓
   Choose appropriate area and type labels
   ↓
4. Draft Issue
   ↓
   Use templates from references/
   ↓
   Follow writing guidelines (terse, specific, direct)
   ↓
5. Present Draft
   ↓
   Show complete draft to user
   ↓
   Iterate based on feedback
   ↓
6. Prepare for Submission
   ↓
   Offer markdown file or clipboard format
   ↓
   Save to file OR format for copying
   ↓
   Provide GitHub link and submission instructions

Remember: The goal is to draft clear, actionable issues that respect both the reporter's intent and the development team's time. The user maintains full control over the final submission to GitHub.

平台分布

Claude Code

27.03%
按下载量换算109

windsurf

23.03%
按下载量换算93

trae

18.01%
按下载量换算73

OpenCode

13.02%
按下载量换算53

Codex

7.16%
按下载量换算29

Antigravity

3.35%
按下载量换算14

安全审计

Gen Agent Trust Hub

通过

Socket

通过

Snyk

可疑

权限和风险

需要联网

该 Skill 可能需要联网访问来源站点、仓库或外部 API;具体网络访问范围需要结合源码和 README 复核。

安装前确认

本站仅展示第三方公开信息,不托管安装包,不提供自动安装或运行环境。安装前应自行审查源码、依赖和命令行为。来源安全扫描存在提醒或未通过项,安装前请自行复核。

继续浏览同类 Skills