name: research-issue
description: Investigate the best implementation approach for a feature or bug by analyzing the codebase and external references, then writing structured findings to artifacts/research/.
allowed-tools:
- Read
- Grep
- Glob
- WebFetch
Research Issue Skill
Research the best implementation approach for a feature or bug described in the provided issue and spec documents. Output is a structured research file, not implementation code.
Use the Task Researcher template from the repository exactly.
Place rejected-alternatives summaries inside ## Recommended Approach, not as a separate top-level header.
Investigation Areas
1. Current State Analysis
Identify implementation targets from the feature docs.
Read relevant modules end-to-end.
Document current behavior, key abstractions, extension points, and toolchain constraints.
2. Candidate Implementation Approaches
Research and compare at least two viable approaches.
Select one final recommendation with justification.
For any new dependency, confirm whether it already exists in the repo and justify adding it.
Gather authoritative external documentation to support the recommendation.
3. Behavior Semantics and Edge Cases
Extract intended behavior from feature docs.
Define success/failure conditions, ordering rules, cancellation behavior, and CI vs. local expectations.
Research comparable tools that implement similar semantics.
4. Requirements Mapping to Design
Map acceptance criteria into a concrete design.
Propose state model, transitions, internal API boundaries, and required file changes.
5. Testing Implications
Propose a test strategy consistent with repository policy (unit tests for pure logic, integration seams).
Do not write test code; describe the strategy only.
Constraints
Research only. Do not implement changes.
Ground all findings in verified evidence from the codebase and authoritative external sources.
Keep discussion of non-selected approaches brief.
Do not claim or perform nested worker delegation.
1---2name: research-issue-53description: Converted skill4---5# Converted skill67Applied rewrites:8- None910---11name: research-issue12description: Investigate the best implementation approach for a feature or bug by analyzing the codebase and external references, then writing structured findings to artifacts/research/.13allowed-tools:14 - Read15 - Grep16 - Glob17 - WebFetch18---1920# Research Issue Skill2122Research the best implementation approach for a feature or bug described in the provided issue and spec documents. Output is a structured research file, not implementation code.2324## Inputs2526Accept one or more feature documents as context:2728- `docs/features/active/<feature>/issue.md` (primary)29- `docs/features/active/<feature>/user-story.md` (when present)30- `docs/features/active/<feature>/spec.md` (when present)3132## Output3334Create or update a single research file:3536- Path: `artifacts/research/<timestamp>-<short-name>-research.md`37- Use the Task Researcher template from the repository exactly.38- Place rejected-alternatives summaries inside `## Recommended Approach`, not as a separate top-level header.3940## Investigation Areas4142### 1. Current State Analysis4344- Identify implementation targets from the feature docs.45- Read relevant modules end-to-end.46- Document current behavior, key abstractions, extension points, and toolchain constraints.4748### 2. Candidate Implementation Approaches4950- Research and compare at least two viable approaches.51- Select one final recommendation with justification.52- For any new dependency, confirm whether it already exists in the repo and justify adding it.53- Gather authoritative external documentation to support the recommendation.5455### 3. Behavior Semantics and Edge Cases5657- Extract intended behavior from feature docs.58- Define success/failure conditions, ordering rules, cancellation behavior, and CI vs. local expectations.59- Research comparable tools that implement similar semantics.6061### 4. Requirements Mapping to Design6263- Map acceptance criteria into a concrete design.64- Propose state model, transitions, internal API boundaries, and required file changes.6566### 5. Testing Implications6768- Propose a test strategy consistent with repository policy (unit tests for pure logic, integration seams).69- Do not write test code; describe the strategy only.7071## Constraints7273- Research only. Do not implement changes.74- Ground all findings in verified evidence from the codebase and authoritative external sources.75- Keep discussion of non-selected approaches brief.76- Do not claim or perform nested worker delegation.
Run npx skillmds@latest add drmoisan/research-issue-5 in your terminal (requires Node.js), paste this page's agent-chat prompt into Claude, Cursor, or any MCP-connected agent, or download the SKILL.md file and copy it into your agent's skills directory.
Converted skill It is listed under Research & Search on SkillMD.
This skill has not completed SkillMD's automated safety review yet. SkillMD never runs a skill's scripts for you; review the SKILL.md before installing.
This skill is tagged as working with Claude Code, Claude.ai, OpenAI Codex. SKILL.md is an open format, so most agents that read a skills directory can load it too.
Yes. Installing skills from SkillMD is free, and the skill stays under its author's original license.
drmoisan (@drmoisan) published this skill. Their other Agent Skills are listed on their SkillMD profile.