Agent skill
plan-research
Research a problem space with evidence gathering and source validation
Install this agent skill to your Project
npx add-skill https://github.com/majiayu000/claude-skill-registry/tree/main/skills/other/other/plan-research-daemn256-workspace-repo-templ
SKILL.md
Plan Research
Uses Planner. Investigate a problem space by gathering evidence from the codebase, documentation, and external sources. Produce a structured research summary with cited sources.
Prerequisites: Clear research question or problem statement
Phase 1: Scope the Investigation
Define Research Boundaries
- State the research question clearly
- Identify what you need to learn and why
- Define what is in-scope and out-of-scope
- List known starting points (files, docs, APIs, prior ADRs)
Output
## Context Anchors
- **Issue:** #<number> - <title>
- **Phase:** 1 — Scope
## Research Question
<Clear statement of what needs to be investigated>
## Scope
**In:** <what to investigate>
**Out:** <what to exclude>
## Starting Points
- <file, doc, or source 1>
- <file, doc, or source 2>
## Next Step
Begin evidence gathering.
**Approval Required:** No
Phase 2: Gather Evidence
Internal Sources
- Search the codebase for relevant patterns, implementations, and conventions
- Read existing ADRs, architecture docs, and design notes
- Review git history for context on past decisions
- Quantify where possible (line counts, file counts, dependency counts)
External Sources
- Use
web/fetchto read official documentation, changelogs, or specifications - Use
web/githubRepoto inspect upstream repositories for README, examples, or release notes - Do NOT rely solely on training knowledge for version-specific behavior, API signatures, or configuration options — verify against the source
- Cite every external source with a URL or repository reference
Evidence Standards
- Every claim must link to a specific file, line, URL, or commit
- Distinguish verified facts from inferences
- Note contradictions between sources
- Record what you searched for and didn't find (negative evidence)
Output
## Context Anchors
- **Issue:** #<number> - <title>
- **Phase:** 2 — Gather Evidence
## Findings
### <Topic 1>
<Finding with source citation>
**Source:** <file path, URL, or commit>
### <Topic 2>
<Finding with source citation>
**Source:** <file path, URL, or commit>
## Negative Evidence
- Searched for <X>, not found in <scope>
## Next Step
Synthesize findings into a research summary.
**Approval Required:** No
Phase 3: Synthesize
Produce Research Summary
- Combine findings into a coherent picture
- Identify patterns, gaps, and contradictions
- State implications for the original research question
- List open questions that remain unanswered
Output
## Context Anchors
- **Issue:** #<number> - <title>
- **Phase:** 3 — Synthesize
## Research Summary
<Coherent synthesis of findings>
## Key Insights
1. <insight 1>
2. <insight 2>
3. <insight 3>
## Open Questions
- <question that remains unanswered>
## Sources
| Source | Type | Key Finding |
| ------ | ------------------- | ----------------- |
| <ref> | <internal/external> | <what it told us> |
## Next Step
Research complete. Findings available for design, planning, or decision-making.
**Approval Required:** Yes
⛔ CHECKPOINT
STOP. Do not proceed until human confirms the research summary is accurate and sufficient.
Error Handling
| Error | Recovery |
|---|---|
| Research question too broad | Narrow scope, break into sub-questions |
| External source unavailable | Note the gap, try alternative sources |
| Contradictory evidence | Document both sides, flag for human judgment |
| Insufficient evidence | State what's missing, recommend additional investigation |
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?