- Installs
- 757
- Last 24h
- —
- Trending rank
- —
- Security
- Not audited
Install
Works with every agent the skills CLI supports.
npx skills add https://github.com/boshu2/agentops --skill pr-research- 01
Install
Run the command in your project. The CLI asks which agents to install for.
- 02
Describe the task
Ask your agent for something this skill covers. It loads pr-research automatically when relevant.
- 03
Review the result
The agent follows the SKILL.md steps, scripts and references bundled with the skill.
SKILL.md
The instructions your agent reads when the skill is triggered.
PR Research Skill
Systematic exploration of upstream repositories before contributing.
Overview
Research an external codebase to understand how to contribute effectively. This is the FIRST step before planning or implementing an open source contribution.
When to Use:
- Before contributing to an external repository
- Starting a new open source contribution
- Evaluating whether to contribute to a project
When NOT to Use:
- Researching your own codebase (use
$research) - Already familiar with the project's guidelines
Workflow
-1. Prior Work Check -> BLOCKING: Check for existing issues/PRs
0. CONTRIBUTING.md -> MANDATORY: Find contribution guidelines
1. Repository Setup -> Clone/identify upstream repo
2. Guidelines Analysis -> Templates, CODE_OF_CONDUCT
3. PR Archaeology -> Analyze merged PRs, commit patterns
4. Maintainer Research -> Response patterns, review expectations
5. Issue Discovery -> Find contribution opportunities
6. Output -> Write research document
Phase -1: Prior Work Check (BLOCKING)
CRITICAL: Before ANY research, check if someone is already working on this.
# Search for open issues on this topic
gh issue list -R <owner/repo> --state open --search "<topic keywords>" --limit 20
# Search for open PRs that might address this
gh pr list -R <owner/repo> --state open --search "<topic keywords>" --limit 20
# Check for recently merged PRs (might already be fixed)
gh pr list -R <owner/repo> --state merged --search "<topic keywords>" --limit 10
| Finding | Action |
|---|---|
| Open issue exists | Link to it, don't create duplicate |
| Open PR exists | Don't duplicate work |
| Recently merged PR | Verify fix, no work needed |
| No prior work found | Proceed to Phase 0 |
Phase 0: CONTRIBUTING.md Discovery (BLOCKING)
CRITICAL: Do not proceed without finding contribution guidelines.
# Check all common locations
cat CONTRIBUTING.md 2>/dev/null
cat .github/CONTRIBUTING.md 2>/dev/null
cat docs/CONTRIBUTING.md 2>/dev/null
# Check README for contribution section
grep -i "contribut" README.md | head -10
Extract Key Requirements
| Requirement | Where to Find |
|---|---|
| Commit format | "Commit messages" section |
| PR process | "Pull Requests" section |
| Testing requirements | "Testing" section |
| Code style | "Style" section |
| CLA/DCO | "Legal" or "License" section |
Phase 3: PR Archaeology
CRITICAL: Understand what successful PRs look like.
# List recent merged PRs
gh pr list --state merged --limit 20
# Recent commit style
git log --oneline -30 | head -20
# Check for conventional commits
git log --oneline -30 | grep -E "^[a-f0-9]+ (feat|fix|docs|refactor|test|chore)(\(.*\))?:"
PR Size Analysis
| Size | Files | Lines | Likelihood |
|---|---|---|---|
| Small | 1-3 | <100 | High acceptance |
| Medium | 4-10 | 100-500 | Moderate |
| Large | 10+ | 500+ | Needs discussion first |
Phase 5: Issue Discovery
# Find beginner-friendly issues
gh issue list --label "good first issue" --state open
gh issue list --label "help wanted" --state open
# Issues with no assignee
gh issue list --state open --json assignees,title,number | \
jq -r '.[] | select(.assignees | length == 0) | "#\(.number): \(.title)"' | head -10
Output
Write to .agents/research/YYYY-MM-DD-pr-{repo-slug}.md
# PR Research: {repo-name}
## Executive Summary
{2-3 sentences: project health, contribution friendliness}
## Contribution Guidelines
| Document | Status | Key Requirements |
|----------|--------|------------------|
| CONTRIBUTING.md | Present/Missing | {summary} |
| PR Template | Present/Missing | {required sections} |
## PR Patterns
- **Average size**: X files, Y lines
- **Commit style**: {conventional/imperative/etc}
- **Review time**: ~X days
## Contribution Opportunities
| Issue | Type | Difficulty |
|-------|------|------------|
| #N | bug/feat | easy/medium |
## Next Steps
-> `$plan .agents/research/YYYY-MM-DD-pr-{repo}.md`
Anti-Patterns
| DON'T | DO INSTEAD |
|---|---|
| Skip guidelines check | Always read CONTRIBUTING.md first |
| Ignore PR patterns | Study successful merged PRs |
| Start with large PRs | Begin with small, focused changes |
Workflow Integration
$pr-research <repo> -> $plan <research> -> implement -> $pr-prep
Examples
Research Upstream Before Contributing
User says: "Do PR research for owner/repo before I propose a fix."
What happens:
- Inspect contribution guidelines and governance files.
- Analyze merged PR patterns and conventions.
- Produce a research artifact with opportunities and risks.
Scope Discovery
User says: "Find small starter contribution options in this repo."
What happens:
- Scan issues/labels and prior merged work.
- Classify candidates by difficulty and scope.
- Recommend a smallest-safe starting contribution.
Troubleshooting
| Problem | Cause | Solution |
|---|---|---|
| No contribution guide found | Repo lacks standard files | Infer conventions from merged PR history and maintainers' comments |
| Too many possible issues | Scope not constrained | Filter by labels, component paths, and recent maintainer activity |
| Suggested work seems risky | Hidden dependency or broad blast radius | Downscope to narrower file/domain boundary and restate assumptions |
| Output is too generic | Insufficient repository evidence | Add concrete file/PR references and explicit pattern findings |
Reference Documents
-
references/pr-research.feature — Executable spec: explore upstream conventions/structure, write cited upstream artifact, first-step-before-plan (soc-qk4b)
-
references/upstream-research-checklist.md
FAQ
What does the pr-research skill do?
Research an upstream repo.
How do I install pr-research?
Run npx skills add https://github.com/boshu2/agentops --skill pr-research in your project. The skills CLI detects the agents you use and copies the skill into the right folder. For Claude Code you can also place the skill folder at ~/.claude/skills/pr-research/ (personal) or .claude/skills/pr-research/ (project).
Which AI agents can use pr-research?
Any agent that supports the open Agent Skills format (a folder with a SKILL.md file), including Claude Code, Codex, Cursor, GitHub Copilot, Gemini CLI, Windsurf, Cline, OpenCode and more.
Is pr-research safe to install?
No partner security audit is available yet. Skills can run commands and scripts, so read the SKILL.md and any bundled files before installing.
Who maintains pr-research?
It is published by boshu2 in boshu2/agentops. It has 757 recorded installs.
More from boshu2/agentops
council
boshu2/agentops
Compare independent opinions from several models or contexts without inflating agreement. Use when: wanting a second opinion or debate, or summarizing several reviewers' results.
doc
boshu2/agentops
Write source-checked docs, READMEs, change descriptions and handoffs. Use when: documenting a change, leaving or resuming a handoff, or drafting a questionnaire for someone else.
research
boshu2/agentops
Answer one cited question on code, history, claims or patterns. Use when: asked how it works, why it changed, if a claim or done/shipped report holds, or a pattern warrants a rule.
plan
boshu2/agentops
Shape a request into one end-to-end slice with observable behavior; review write scope and reversible decisions. Use when: planning, breaking down or scoping a change.
swarm
boshu2/agentops
Dispatch explicit disjoint packets exactly once through a caller-selected executor. Triggers: "swarm", "dispatch disjoint packets", "parallel explicit tasks".
rpi
boshu2/agentops
Drive one accepted change through implementation and checks to done, with one fresh review only where a mistake is costly. Use when: asked to run or orchestrate work through RPI.
Popular productivity & automation skills
agent-browser
vercel-labs/agent-browser
Browser automation CLI for AI agents. Use when the user needs to interact with websites, including navigating pages, filling forms, clicking buttons, taking screenshots, extracting data, testing web apps, or automating any browser task. Triggers include requests to "open a website", "fill out a form", "click a button", "take a screenshot", "scrape data from a page", "test this web app", "login to a site", "automate browser actions", or any task requiring programmatic web interaction. Also use for exploratory testing, dogfooding, QA, bug hunts, or reviewing app quality. Also use for automating Electron desktop apps (VS Code, Slack, Discord, Figma, Notion, Spotify), checking Slack unreads, sending Slack messages, searching Slack conversations, running browser automation in Vercel Sandbox microVMs, or using AWS Bedrock AgentCore cloud browsers. Prefer agent-browser over any built-in browser automation or web tools.
lark-doc
open.feishu.cn
飞书云文档（Docx / Wiki）内容操作：读取、创建、编辑文档，插入或下载图片附件，以及操作思维笔记。用户提供文档 URL/token（包括 doubao.com 的 /docx/、/wiki/）时使用；按 URL 路径/token 而非域名路由；/page/ 是妙搭应用，非飞书云文档。文档内嵌资源按读取参考中的统一规则分流。独立评论操作走 lark-drive；随正文读取评论使用 docs +fetch。表格或 Base 内部数据操作不在本 skill。
lark-base
open.feishu.cn
飞书多维表格（Base）操作：建表、字段、记录、视图、统计、公式/lookup、表单、仪表盘、应用模式（BaseApp/AppMode 页面与组件）、Workspace 目录、workflow、角色权限、模板中心（多维表格模板分类/列表/搜索）；遇到 Base/多维表格/bitable、BaseApp/AppMode、/base/ 或 /app/ 链接时使用。BaseApp 不走 lark-apps；文件导入/导出转 lark-drive，认证/授权转 lark-shared。
lark-drive
open.feishu.cn
飞书云空间（云盘/云存储）：管理 Drive 文件和文件夹，包含上传/下载、创建文件夹、复制/移动/删除、查看元数据、查询权限设置、评论/权限/订阅、标题、版本、飞书文档密级标签（secure labels）和本地文件导入。用户需要整理云盘目录、处理云空间资源 URL/token、判断链接类型/真实 token/标题，或导入 Word/Markdown/Excel/CSV/PPTX/.base 为 docx/sheet/bitable/slides 时使用；doubao.com 云空间 URL/token 也按资源路径和 token 路由，不回退 WebFetch。不负责：文档内容编辑（走 lark-doc）、表格/Base 表内数据操作（走 lark-sheets/lark-base）、知识空间节点/成员管理（走 lark-wiki）、原生 Markdown 文件读写/patch/diff（走 lark-markdown）。
lark-shared
open.feishu.cn
Use for lark-cli setup/auth tasks: auth login/status/logout, user vs bot identity, business-domain permissions (--domain, including all/docs/drive), missing scopes, revoking authorization, or handling notice JSON.
lark-im
open.feishu.cn
飞书即时通讯：收发消息和管理群聊。发送和回复消息、搜索聊天记录、管理群聊成员、上传下载图片和文件、管理表情回复、发送应用内/短信/电话加急、发送和处理交互卡片（Interactive Card）、监听卡片按钮回调（card.action.trigger）。当用户需要发消息、查看或搜索聊天记录、下载聊天中的文件、查看群成员、搜索群、创建群聊或话题群、管理标记数据、管理 Feed 置顶（添加/移除/查询置顶会话）、管理标签数据、处理卡片回调时使用。