Agent skill
plan-research
Plan technical research (enters plan mode)
Install this agent skill to your Project
npx add-skill https://github.com/majiayu000/claude-skill-registry/tree/main/skills/data/plan-research
SKILL.md
Plan Research (Plan Mode)
Input
Optional implementation guidelines: $ARGUMENTS Examples:
- "Focus on SSE streaming patterns"
- "Use React Query for data fetching"
- "Based on the pattern from ALG-14"
Steps
-
Enter plan mode: Call the
EnterPlanModetool to begin planning. -
Get current feature from branch:
bashBRANCH=$(git rev-parse --abbrev-ref HEAD) # Extract: alg-27-feature-name -> 27 NUM=$(echo "$BRANCH" | grep -oE 'alg-([0-9]+)' | grep -oE '[0-9]+') -
Read the spec:
- Read
specs/alg-${NUM}-*/spec.md - Extract user stories, requirements, and scope
- Read
-
Incorporate user guidelines (if
$ARGUMENTSprovided):- Parse the implementation guidance
- Use as constraints for technology choices
- Note any specific patterns or libraries mentioned
-
Explore codebase to identify:
- Existing patterns to follow (search for similar implementations)
- Files that will need modification
- Technologies currently in use
- External documentation to reference
-
Propose research plan in the plan file: Write to the plan file (NOT research.md yet) with:
- Key Decisions to make (numbered 1, 2, 3...)
- Technologies to evaluate
- Codebase Patterns to examine
- Files likely to be modified
- External Resources to consult
-
Exit plan mode: Call
ExitPlanModeto get user approval of the research plan. -
After approval, conduct research:
- Make the key decisions with rationale
- Document alternatives considered
- Extract relevant code patterns from codebase
- Reference external documentation
-
Write research.md:
markdown# Research: {Feature Title} **Date**: {ISO date} **Feature**: ALG-{NUM} **Implementation Guidance**: {$ARGUMENTS if provided} ## Executive Summary {Brief overview of key decisions} ## Key Decisions ### 1. {Decision Title} **Decision**: {What was decided} **Rationale**: {Why this approach} **Alternatives Considered**: - {Alternative 1}: {Why rejected} - {Alternative 2}: {Why rejected} ## Implementation Patterns {Code snippets from codebase showing patterns to follow} ## Files to Modify - `path/to/file.ts`: {What changes} -
Commit the research:
bashgit add specs/alg-${NUM}-*/research.md git commit -m "spec: ALG-${NUM} - research and decisions"
Notes
- Research should validate decisions against existing codebase patterns
- Include actual code snippets showing how similar things are done
- Reference specific file paths for implementation guidance
Recommended Agent Skills
Expand your agent's capabilities with these related and highly-rated skills.
agent-ops-spec
Manage specification documents in .agent/specs/. Use when user provides requirements, acceptance criteria, or feature descriptions that need to be tracked and validated against implementation.
agent-ops-state
Maintain .agent state files. Use at session start, after meaningful steps, and before concluding: read/update constitution/memory/focus/issues/baseline consistently.
agent-ops-spec
Manage specification documents in .agent/specs/. Use when user provides requirements, acceptance criteria, or feature descriptions that need to be tracked and validated against implementation.
agent-ops-testing
Test strategy, execution, and coverage analysis. Use when designing tests, running test suites, or analyzing test results beyond baseline checks.
agent-ops-testing
Test strategy, execution, and coverage analysis. Use when designing tests, running test suites, or analyzing test results beyond baseline checks.
agent-ops-state
Maintain .agent state files. Use at session start, after meaningful steps, and before concluding: read/update constitution/memory/focus/issues/baseline consistently.
Didn't find tool you were looking for?