
- Installs
- 593
- 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-plan- 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-plan 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 Plan Skill
Strategic planning for open source contributions.
Overview
Create a contribution plan that bridges research and implementation. Takes
$pr-research output and produces an actionable plan.
Output: .agents/plans/YYYY-MM-DD-pr-plan-{repo-slug}.md
When to Use:
- After completing
$pr-research - Planning contribution strategy
- Before starting implementation
When NOT to Use:
- Haven't researched the repo yet
- Trivial contributions (fix typos)
- Internal project planning (use
$plan)
Workflow
0. Input Discovery -> Find/load pr-research artifact
1. Scope Definition -> What exactly to contribute
2. Target Selection -> Which issues/areas to address
3. Criteria Definition -> Acceptance criteria from research
4. Risk Assessment -> What could go wrong
5. Strategy Formation -> Implementation approach
6. Output -> Write plan artifact
Phase 1: Scope Definition
Scope Questions
| Question | Why It Matters |
|---|---|
| What specific functionality? | Clear deliverable |
| Which files/packages? | Limits impact surface |
| What's explicitly out of scope? | Prevents scope creep |
| Single PR or series? | Sets expectations |
Scope Template
## Scope
**Contribution**: [1-2 sentences describing the change]
**Affected Areas**:
- `path/to/file.go` - [what changes]
**Out of Scope**:
- [Related but excluded work]
Phase 3: Acceptance Criteria
Define success from maintainer perspective:
## Acceptance Criteria
### Code Quality
- [ ] Follows project coding style
- [ ] Passes existing tests
- [ ] Adds tests for new functionality
- [ ] No linting warnings
### PR Requirements
- [ ] Title follows convention
- [ ] Body uses project template
- [ ] Size within acceptable range
- [ ] Single logical change
### Project-Specific
- [ ] [Any project-specific requirements from research]
Phase 4: Risk Assessment
| Risk | Likelihood | Impact | Mitigation |
|---|---|---|---|
| PR review takes > 2 weeks | Medium | Medium | Start small, be responsive |
| Scope expands during review | Medium | High | Define scope clearly upfront |
| Breaking change discovered | Low | High | Test against multiple versions |
Phase 5: Implementation Strategy
## Implementation Strategy
### Approach
1. **Setup**: Fork repo, configure dev environment
2. **Understand**: Read existing code in affected area
3. **Implement**: Make changes following project patterns
4. **Test**: Run existing tests + add new tests
5. **Document**: Update any affected documentation
6. **Submit**: Create PR following project conventions
### Pre-Implementation Checklist
- [ ] Fork created and up-to-date with upstream
- [ ] Dev environment working
- [ ] Issue claimed or comment posted
- [ ] Recent repo activity reviewed
Output Template
Write to .agents/plans/YYYY-MM-DD-pr-plan-{repo-slug}.md
# PR Plan: {repo-name}
## Executive Summary
{2-3 sentences: what you're contributing, why, expected outcome}
## Scope
**Contribution**: {description}
**Affected Areas**: [list]
**Out of Scope**: [list]
## Target
**Primary Issue**: #{N} - {title}
## Acceptance Criteria
[checklist]
## Risk Assessment
[table]
## Implementation Strategy
[numbered steps]
## Next Steps
1. Claim/comment on target issue
2. Fork and set up development environment
3. Implement following strategy
4. Run `$pr-prep` when ready
Workflow Integration
$pr-research <repo> -> $pr-plan <research> -> implement -> $pr-prep
Examples
Plan a Focused External Contribution
User says: "Create a contribution plan from my PR research artifact."
What happens:
- Extract accepted conventions and constraints.
- Define scope boundaries and acceptance criteria.
- Produce an implementation strategy with risks.
Tighten Scope Before Coding
User says: "Check if this PR plan is too large for one submission."
What happens:
- Compare proposed changes to historical PR size patterns.
- Split oversized scope into phased contributions.
- Emit a revised plan and next-step checklist.
Troubleshooting
| Problem | Cause | Solution |
|---|---|---|
| Plan has vague acceptance criteria | Criteria not measurable | Convert criteria to concrete behavioral checks |
| Scope too broad | Multiple concerns mixed | Split by user-visible change or subsystem boundary |
| Risk section is weak | Missing failure-mode analysis | Add integration, review, and rollback risks explicitly |
| Plan conflicts with repo norms | Research artifact incomplete | Re-run $pr-research and refresh constraints |
FAQ
What does the pr-plan skill do?
Plan an open source PR.
How do I install pr-plan?
Run npx skills add https://github.com/boshu2/agentops --skill pr-plan 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-plan/ (personal) or .claude/skills/pr-plan/ (project).
Which AI agents can use pr-plan?
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-plan 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-plan?
It is published by boshu2 in boshu2/agentops. It has 593 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 code quality & workflow skills
grill-me
mattpocock/skills
A relentless interview to sharpen a plan or design.
improve-codebase-architecture
mattpocock/skills
Scan a codebase for deepening opportunities, present them as a visual HTML report, then grill through whichever one you pick.
handoff
mattpocock/skills
Compact the current conversation into a handoff document for another agent to pick up.
domain-modeling
mattpocock/skills
Build and sharpen a project's domain model. Use when discussing codebase terminology, writing or editing a GLOSSARY.md, or recording or editing an ADR.
codebase-design
mattpocock/skills
Shared vocabulary for designing deep modules. Use when the user wants to design or improve a module's interface, find deepening opportunities, decide where a seam goes, make code more testable or AI-navigable, or when another skill needs the deep-module vocabulary.
diagnosing-bugs
mattpocock/skills
Diagnosis loop for hard bugs and performance regressions. Use when the user says "diagnose"/"debug this", or reports something broken/throwing/failing/slow.