Skip to content
Agentmart
Submit a tool

research-domain

Research user goals, domain terminology and rules, and common risks to inform software orientation and exploratory testing; reuse existing application…

Skill by testobsessed

IndexedMIT
Write a review

Install

Works with Claude Code, Claude apps, Codex, Cursor, Gemini CLI, GitHub Copilot, VS Code, OpenCode, Goose, Windsurf. Read the repository before you give any tool access to your data.

npx agentmarket install skill/testobsessed-research-domain

Asks which of your tools to add it to (Claude Code, Codex, Cursor, VS Code, Windsurf, Gemini CLI, Claude Desktop) and shows the change first. See https://agentmart.dev/cli.

Get the weekly diff

The weekly diff: one email a week with new agent tools, notable updates and grade changes, plus security alerts for tools you follow. Double opt-in, one-click unsubscribe.

We use your email only for this newsletter. Privacy

About

Research user goals, domain terminology and rules, and common risks to inform software orientation and exploratory testing; reuse existing application research before gathering more.

Use cases: testing, research

No reviews yet. Installed it? Reviews come from verified installers only. How reviews work

Permissions

What this skill can do and what it asks for, from its SKILL.md. Checked Oct 25, 2026.

Tools
No tools found
Secrets
None asked for
Install scripts
None found

Network hosts it talks to 1

  • codeload.github.com · found in install command

Files it touches

  • ~/.claude/skills/research-domain

What's inside

Skill name
research-domain
Description
Research user goals, domain terminology and rules, and common risks to inform software orientation and exploratory testing; reuse existing application research before gathering more.
License
MIT
Instructions
13 lines in SKILL.md · view on GitHub

Files (1)

  • SKILL.md

SKILL.md (first lines)

# Researching the Domain

Build useful domain context for exploration: what users are trying to accomplish, terminology and domain rules, and common risks or failure patterns. Follow the current question; these topics have no fixed order. Documentation and repository access are useful, but neither is required.

Before researching, reuse caller-provided context and any existing application index, reading only relevant linked research entries. If domain research already exists, reuse it and record gaps or contradictions. Do not automatically research more because the cache is incomplete, old, or contradictory; further research requires an explicit caller request. Within exploration, gather initial research only when a domain question needs answering to choose or interpret the next experiment. A standalone research request supplies its own research question.

When no cached domain research exists, initial research has a five-minute ceiling unless the caller specifies otherwise. Stop once enough context exists for the current question; the ceiling is not a duration to fill. Stay within any enclosing session or run deadline, leaving time for behavioral probes and closure. Prioritize supplied canonical software documentation, then available repository material, then external sources as needed. Record source identity and applicable product/version; distinguish documented rules, domain conventions, and inferred expectations. Treat each source as fallible.

Use exploratory-session-log to record research as it happens, unless the user explicitly opts out of persistence. Reuse the active session and logging guidance already in context; index reusable entries at session closure or handoff. When sufficient context exists or the time limit is reached, preserve partial results and unanswered questions and return to the caller's work. Do not extend research to fill every section. Research is input to hypotheses and experiments, not runtime proof.

If exploratory-session-log is unavailable, use the caller's shared record location: append dated research entries with scope, sources, interpretation, and gaps, indexing reusable entries at closure or handoff. Disabling logging changes persistence, not research authority: otherwise-authorized research may still use available sources under the same scope and time limits. When logging is disabled, keep notes in the current context and return results directly; do not create a persistent cache or records.

From testobsessed/exploratory-testing-skills, MIT.

More from testobsessed/exploratory-testing-skills

Signals

Stars
0
Forks
0
Open issues
0
Last commit (this folder)
Oct 4, 2026 (24 days ago)

From GitHub (fetched Oct 24, 2026).

Details

License
MIT
First seen
Oct 24, 2026
Last checked
Oct 24, 2026

More from testobsessed

Cite this page

research-domain skill. Agent Mart. https://agentmart.dev/skills/testobsessed-research-domain (last updated 2026-10-24)