bob-matt-research
Investigate a topic or explore a codebase using primary sources, then save grounded findings in a Markdown report.
Skill by Matt Pocock
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/mattdurham-bob-matt-research
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.
About
Use cases: documents, research
Reviews
Write a reviewNo 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 and code. 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/bob-matt-research
What's inside
- Skill name
bob-matt-research- Description
- Investigate a topic or explore a codebase using primary sources, then save grounded findings in a Markdown report.
- License
- MIT
- Metadata
- author: Matt Pocock · source: https://github.com/mattpocock/skills/tree/49dd158d1076134a641b33efb035946536778336/skills/engineering/research · upstream-commit: 49dd158d1076134a641b33efb035946536778336
- Instructions
- 7 lines in SKILL.md · view on GitHub
Files (3)
- LICENSE
- SKILL.md
- openai.yaml · agents/
SKILL.md (first lines)
Establish the question and scope from the request; ask only when a missing detail would materially change the investigation. Investigate against primary sources: official documentation, source code, specifications, and first-party APIs. Follow claims back to the source that owns them. Work directly or delegate bounded, independent questions when that will help; collect delegated results before drawing conclusions. For codebase exploration, trace the relevant entry points, component relationships, data flow, dependencies, and tests. Read documented contracts and design decisions, then check them against the implementation. Challenge the initial explanation by looking for counterexamples, stale documentation, missing assumptions, and edge cases. Distinguish demonstrated behavior from intended behavior, inference, and unanswered questions. Keep the investigation read-only except for its report; do not change source code, specifications, or external systems. Write the findings to one Markdown report with source citations or file locations, the answer to the question, and remaining uncertainties. Save it at the requested path or where the repository keeps research notes; otherwise choose a sensible location and say where. Summarize the useful findings for the user without treating speculation or unverified claims as facts.
From mattdurham/bob, MIT.
More from mattdurham/bob
- 0.632score
bob-generate-okf
mattdurham
Create or update an OKF knowledge catalog linking the project’s packages, decisions, patterns, and confirmed planned work to authoritative sources.
SkillAFreshness: A★ 10Claude Code +9 - 0.632score
bob-internal-go-coding
mattdurham
Consult Go-specific guidance for ownership, concurrency, external sizes, and error handling when implementing or reviewing those hazards.
SkillAFreshness: A★ 10Claude Code +9 - 0.627score
bob-audit
mattdurham
Check documented guarantees against implementation and tests; report violations and unverified claims without modifying the codebase.
SkillAFreshness: A★ 10Claude Code +9 - 0.627score
go-presubmit-reviewer
mattdurham
Go-specific pre-submit reviewer targeting patterns that survive generic review but cause problems in production — pool lifetimes, concurrency races, int64/int…
SkillAFreshness: A★ 10Claude Code +9 - 0.627score
bob-generate-overview
mattdurham
Explain an existing codebase element in a self-contained offline HTML report grounded in code, tests, and specifications.
SkillAFreshness: A★ 10Claude Code +9 - 0.624score
bob-code-review
mattdurham
Review changes without modifying them; report findings and draft remediation plans or comments.
SkillAFreshness: A★ 10Claude Code +9 - 0.624score
bob-matt-implement-spec
Matt Pocock
Implement the result of /bob-matt-to-spec and /bob-matt-to-tickets in code.
SkillAFreshness: A★ 10Claude Code +9 - 0.621score
bob-challenge-idea
mattdurham
Adversarial idea review — interactive intake followed by 8 specialist agents in parallel attacking assumptions, prior art, scope explosion, scale, operational…
SkillAFreshness: A★ 10Claude Code +9 - 0.619score
bob-cleanup
mattdurham
Simplify code and documentation while preserving behavior and public contracts, then verify and review the changes.
SkillAFreshness: A★ 10Claude Code +9 - 0.617score
commit-agent
mattdurham
Creates commits and pull requests with proper git workflow
SkillAFreshness: A★ 10Claude Code +9 - 0.610score
bob-matt-diagnosing-bugs
Matt Pocock
Diagnosis loop for hard bugs and performance regressions.
SkillAFreshness: A★ 10Claude Code +9 - 0.605score
bob-matt-code-review
Matt Pocock
Review the changes since a fixed point (commit, branch, tag, or merge-base) along two axes: Standards (does the code follow this repo's documented coding…
SkillAFreshness: A★ 10Claude Code +9
Signals
- Stars
- 10
- Forks
- 3
- Open issues
- 1
- Last commit (this folder)
- Oct 13, 2026 (14 days ago)
From GitHub (fetched Oct 24, 2026).
Details
- License
- MIT
- Repository
- github.com/mattdurham/bob
- First seen
- Oct 24, 2026
- Last checked
- Oct 24, 2026
- Source
- GitHubgithub-graphql
More from Matt Pocock
- 0.624score
bob-matt-implement-spec
Matt Pocock
Implement the result of /bob-matt-to-spec and /bob-matt-to-tickets in code.
SkillAFreshness: A★ 10Claude Code +9 - 0.615score
diagnosing-bugs
Matt Pocock
Diagnosis loop for hard bugs and performance regressions.
SkillAFreshness: A★ 16Claude Code +9 - 0.610score
bob-matt-diagnosing-bugs
Matt Pocock
Diagnosis loop for hard bugs and performance regressions.
SkillAFreshness: A★ 10Claude Code +9 - 0.610score
domain-modeling
Matt Pocock
Build and sharpen a project's domain model.
SkillBFreshness: B★ 140Claude Code +9 - 0.610score
grilling
Matt Pocock
Grill the user relentlessly about a plan, decision, or idea.
SkillAFreshness: A★ 16Claude Code +9 - 0.609score
writing-for-agents
Matt Pocock
Writing documents for agents.
SkillAFreshness: A★ 16Claude Code +9
Cite this page
bob-matt-research skill. Agent Mart. https://agentmart.dev/skills/mattdurham-bob-matt-research (last updated 2026-10-24)