research
"Researches an open-ended question — options, possible solutions, prior art, trade-offs, or how something works — and produces a durable, evidence-backed, adversarially-validated report that recommends an option without committing the team to any artifact. Use when you want to research approaches, weigh options, survey prior art or the state of the art, or understand how something works before committing to a direction. Does not diagnose a bug, failure, or root cause — use investigate. Does not specify a feature — use plan-a-feature. Does not create or update a coding standard — use coding-sta
npx skills add testdouble/han --skill research --agent claude-code
Same command for any agent — swap --agent for codex, cursor, copilot.
Weekly change comes from our own snapshots, not the repository page — it measures attention, not adoption.
What it does
Researches an open-ended question — options, possible solutions, prior art, trade-offs, or how something works — and produces a durable, evidence-backed, adversarially-validated report that recommends an option without committing the team to any artifact.
How it works
- Classifies the request and selects a research band (small/medium/large) based on size signals, defaulting to small when unsure.
- Gathers evidence from web sources and codebase inputs, treating fetched content as data to evaluate rather than instructions.
- Dispatches a research wave with agents:
han-research:research-analyst(andhan-core:codebase-explorerif relevant), thenhan-core:adversarial-validatorafter synthesis. - Produces a single, fixed report structure per run, including a Summary, Research Results, Options to Consider (if applicable), Recommendation with its evidence basis, Validation, and a Sources registry.
- Labels each claim with its evidence status and notes the basis for the recommendation; can operate in strict or exploratory mode based on user request.
When to use it
Use for open-ended questions where you want to compare approaches, survey prior art, or understand how something works before choosing a direction.
What it can touch
- Tools: Read, Glob, Grep, Agent, WebSearch, WebFetch, Bash(find *).
- The workflow references web sources and codebase evidence but does not include codebase contents in agent briefs.
Caveats
- Does not diagnose bugs, failures, or root causes, nor specify features or coding standards; those are routed to sibling skills.
- Evidence mode defaults to strict unless explicitly relaxed by the user.
- The report is a recommendation, not a commitment to a particular artifact.
## Project Context - git installed: !`which git 2>/dev/null || echo "not installed"` - CLAUDE.md: !`find . -maxdepth 1 -name "CLAUDE.md" -type f` - project-discovery.md: !`find . -maxdepth 3 -name "project-discovery.md" -type f` - personal config directory: !`echo "${CLAUDE_CONFIG_DIR:-$HOME/.claude}"` - project .han/config.md: !`cat .han/config.md 2>/dev/null || echo ""` As your first action, use the Read tool on `.han/config.md` inside the `personal config directory` path above. A read that returns no file is no personal configuration: continue silently. When that file or the `project .han/config.md` probe supplies content, apply it per [config-rule.md](../../references/config-rule.md), which governs precedence between the two files, relative-path resolution, and what to do with a file that reads but cannot be used. ## Operating Principles Read these before dispatching anything. They constrain every step below. - **Open-ended and output-agnostic only.** This skill answers a question with researched options and a recommendation. It never produces a feature spec, a coding standard, a gap report, an architecture assessment, or code. A request for any of those is routed to the siblin
- Project Context
- Operating Principles
- Step 1: Capture the Question and Resolve Context
- Step 2: Classify the Request
- Step 3: Detect Signals and Classify Size
- Step 4: Build the Roster and Announce It
- Step 5: Dispatch the Research Wave in Parallel
- Step 6: Compile the Sources Registry
- Step 7: Synthesize, then Validate
- Step 8: Re-evaluate, Render, and Present
What does the research skill do?
"Researches an open-ended question — options, possible solutions, prior art, trade-offs, or how something works — and produces a durable, evidence-backed, adversarially-validated report that recommends an option without committing the team to any artifact. Use when you want to research approaches, weigh options, survey prior art or the state of the art, or understand how something works before committing to a direction. Does not diagnose a bug, failure, or root cause — use investigate. Does not specify a feature — use plan-a-feature. Does not create or update a coding standard — use coding-sta
How do I install it?
Run `npx skills add testdouble/han --skill research --agent claude-code` — it drops the skill into your project so the agent can pick it up. Swap the --agent value for codex, cursor or copilot if you use one of those.
Where does this skill come from?
From testdouble/han, a repository with 154 stars. We read it straight from the repository tree rather than a submitted listing, so what you see here is what is actually published.
Is a popular skill a good skill?
Not necessarily. Stars measure attention, not adoption — a repository can trend for a week and be abandoned. That is why we show the weekly change from our own snapshots next to the total, instead of a single flattering number.