Help us improve
Share bugs, ideas, or general feedback.
From research-plan-implement-plugin
A structured workflow for AI-assisted development using research, planning, and systematic implementation phases. Users refer to this skill as RPI, rpi or Research Plan Implement.
npx claudepluginhub seekayel/agent-skills --plugin research-plan-implement-pluginHow this skill is triggered — by the user, by Claude, or both
Slash command
/research-plan-implement-plugin:research-plan-implementThe summary Claude sees in its skill listing — used to decide when to auto-load this skill
This skill provides a structured approach to software development through five distinct phases: Research, Plan, Validate, Implement, and Test. Each phase builds on the previous to ensure thorough understanding before making changes and verification after. This skill can be referred to as RPI, rpi, Research Plan Implement or research-plan-implement.
Guides software development through six-phase workflow: Research, Plan, Iterate Plan, Experiment, Implement, Validate. Generates structured markdown docs via slash commands for auditable trails.
Orchestrates a full research-plan-implement pipeline using parallel subagents, each in its own context window, with file artifacts as the communication channel between phases.
Creates specs and phased file-level implementation plans for features, bugs, refactors by researching codebase with search, graph queries, and context files.
Share bugs, ideas, or general feedback.
This skill provides a structured approach to software development through five distinct phases: Research, Plan, Validate, Implement, and Test. Each phase builds on the previous to ensure thorough understanding before making changes and verification after. This skill can be referred to as RPI, rpi, Research Plan Implement or research-plan-implement.
Save findings to: _thoughts/research/NNN_topic_name.md
Before writing the research summary or making any changes to the filesystem, deeply explore the codebase to understand:
Architecture Analysis
Pattern Discovery
Relevant Code Location
Research Execution Strategy:
Research Questions to Answer:
Save plan to: _thoughts/plan/NNN_feature_name.md
Based on research findings, create a detailed implementation plan:
Define Scope
Phase the Work
Specify Details
Plan Structure Template:
## Implementation Plan: [Feature/Change Name]
### Overview
[Brief description of the change and its purpose]
### Research Summary
[Key findings from the research phase]
### Phases
#### Phase 1: [Phase Name]
**Files:**
- [ ] `path/to/file1.ts` - [Description of changes]
- [ ] `path/to/file2.ts` - [Description of changes]
**Success Criteria:**
- [ ] [Specific, testable criterion]
- [ ] [Specific, testable criterion]
#### Phase 2: [Phase Name]
[Continue with additional phases...]
### Testing Strategy
[How to verify the implementation]
### Rollback Plan
[How to revert if issues arise]
Save validation notes to: _thoughts/validate/NNN_feature_name_validation.md
Before implementation, verify the plan is complete and correct:
Completeness Check
Feasibility Review
Risk Assessment
Save progress to: _thoughts/implement/NNN_feature_name.md
Execute the plan systematically:
Follow the Plan
Track Progress
Validate Continuously
Implementation Rules:
Save results to: _thoughts/test/NNN_feature_name_results.md
After implementation, execute the testing strategy defined in the plan:
Execute Test Cases
Verify Success Criteria
Handle Failures
Document Results
Testing Rules:
When invoking this skill, specify your intent:
This skill leverages specialized agents for research:
Finds relevant files and directories for a given topic or feature area. Use when you need to discover where specific functionality lives.
Performs deep analysis of code structure, patterns, and dependencies. Use for understanding how systems work.
Identifies coding patterns, conventions, and best practices used in the codebase. Use to ensure new code follows existing standards.
All workflow documents MUST be written to the _thoughts directory with stage-based subdirectories:
_thoughts/
├── research/ # Research findings and analysis
│ ├── 001_architecture_analysis.md
│ └── 002_pattern_discovery.md
├── plan/ # Implementation plans
│ ├── 001_migrate_to_bun.md
│ └── 002_add_authentication.md
├── validate/ # Validation notes and checklists
│ └── 001_migrate_to_bun_validation.md
├── implement/ # Implementation progress tracking
│ ├── 001_migrate_to_bun.md
│ └── 002_add_authentication.md
└── test/ # Test results and reports
└── 001_migrate_to_bun_results.md
Files should follow this naming pattern:
NNN_descriptive_name.md001_migrate_to_bun.md in both plan/ and implement/)_thoughts/research/ when documenting findings_thoughts/plan/ when creating implementation plans_thoughts/validate/ when documenting validation results_thoughts/implement/ to track progress and decisions_thoughts/test/ for test results and reportsFor long-running projects, save progress using a structured format in the appropriate _thoughts/ subdirectory:
## Session: [Date/Time]
### Current State
- Phase: [Research/Plan/Validate/Implement/Test]
- Progress: [Description]
### Completed
- [x] [Completed item]
### In Progress
- [ ] [Current work]
### Next Steps
- [ ] [Upcoming work]
### Notes
[Important observations or decisions]