expert-panel
Simulate a panel of named experts (Fowler, Beck, Bloch, Metz, Feathers, etc.) discussing the code or design decision.
Skill by timander
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/timander-expert-panel
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: design, testing
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. 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/expert-panel
What's inside
- Skill name
expert-panel- Description
- Simulate a panel of named experts (Fowler, Beck, Bloch, Metz, Feathers, etc.) discussing the code or design decision. Use when the user wants multi-perspective stress-testing.
- License
- MIT
- Instructions
- 42 lines in SKILL.md · view on GitHub
Files (1)
- SKILL.md
SKILL.md (first lines)
# Expert Panel Convene the panel below. Each expert speaks in character, cites their canonical work, and may disagree with the others. The panel converges on actionable recommendations, ranked by impact. The user makes the final decision. > *See [ACKNOWLEDGEMENTS.md](../../ACKNOWLEDGEMENTS.md) — these authors' published work shaped this skill. Credits, intent, and consent-friendly recourse live there.* ## The Panel | Expert | Perspective | Canonical citation | |---|---|---| | **Martin Fowler** | Refactoring, evolutionary design, smells | *Refactoring* (Ch. 3 smells, Ch. 6–12 catalog) | | **Kent Beck** | Simplicity, TDD, XP, "make the change easy then make the easy change" | *TDD: By Example*; *Tidy First?* | | **Joshua Kerievsky** | Patterns earn their place; refactor *toward* them | *Refactoring to Patterns* | | **Joshua Bloch** | API design, immutability, defensive coding (Java) | *Effective Java* — cite by item: 1, 2, 15–17, 18, 50, 64 | | **Robert C. Martin** | SOLID, clean code, craftsmanship | *Clean Code* (Ch. 2 names, Ch. 3 functions, Ch. 7 errors) | | **J.B. Rainsberger** | Simple design, contract tests, integration-test skepticism | "Integration Tests Are a Scam"; four rules of simple design | | **Sandi Metz** | Practical OO, small objects, composition | *POODR* | | **Michael Feathers** | Legacy code, characterization tests, seams | *Working Effectively with Legacy Code* | | **Ward Cunningham** | Simplest thing that could work; technical debt metaphor | "the simplest thing that could possibly work" | | **Kevlin Henney** | Naming, simplicity, contrarian on "clean code" rules | *97 Things Every Programmer Should Know* (ed.) | ## How the Panel Runs - Each expert speaks in character. Cite the source: *"As I wrote in Refactoring Chapter 3, this is Feature Envy…"* - Experts may agree, disagree, or build on each other. Disagreements are productive. - Keep it conversational, not a wall of quotes. - End with a **ranked recommendation list**, not a Socratic shrug. ## Language Emphasis - **Java**: Bloch leads with *Effective Java* item numbers; Fowler references Java examples; Feathers cites Java seams. - **TypeScript / JS**: Metz on OO; Beck on simplicity; Henney on naming; Fowler's catalog applies directly. - **Kotlin**: Bloch translates closely; Beck's simplicity aligns with Kotlin idioms. - **Other OO**: Full panel; Metz and Uncle Bob often contrast on class design. ## When to Invoke - Multiple perspectives on a design decision or trade-off. - A review has surfaced a real tension worth exploring. - About to commit to an approach and want it stress-tested by name.
From timander/copilot-instructions-starter-kit, MIT.
More from timander/copilot-instructions-starter-kit
- 0.474score
audience
timander
Switch the explanation level (learning / working / expert) for a stack mid-session.
SkillCFreshness: CClaude Code +9 - 0.474score
challenge
timander
Socratic questioning — challenge the user's assumptions and thinking before they commit.
SkillCFreshness: CClaude Code +9 - 0.474score
code-quality
timander
Offer to add opt-in lint, static-analysis, and coverage tooling for the project's language.
SkillCFreshness: CClaude Code +9 - 0.474score
diagnose
timander
One-shot systematic diagnosis script — understand the problem before suggesting fixes.
SkillCFreshness: CClaude Code +9 - 0.474score
kit-doctor
timander
Self-audit this Copilot kit for token cost, bloat, schema drift, and coverage gaps.
SkillCFreshness: CClaude Code +9 - 0.474score
options
timander
Present a decision as a set of options with trade-offs spelled out, so the user can pick well.
SkillCFreshness: CClaude Code +9 - 0.474score
refactor
timander
Apply the refactoring catalog (Fowler, Beck Tidy First, Feathers legacy techniques) to existing code.
SkillCFreshness: CClaude Code +9 - 0.474score
review
timander
Review code or a PR diff for correctness, design, smells, and missing tests.
SkillCFreshness: CClaude Code +9 - 0.474score
tdd
timander
Walk through Red-Green-Refactor explicitly for implementing a feature.
SkillCFreshness: CClaude Code +9
Signals
- Stars
- 0
- Forks
- 0
- Open issues
- 0
- Last commit (this folder)
- Jun 14, 2026 (4 months ago)
- Last release
- Jun 12, 2026 (4 months ago)
From GitHub (fetched Oct 24, 2026).
Details
- License
- MIT
- First seen
- Oct 24, 2026
- Last checked
- Oct 24, 2026
- Source
- GitHubgithub-graphql
More from timander
- 0.474score
audience
timander
Switch the explanation level (learning / working / expert) for a stack mid-session.
SkillCFreshness: CClaude Code +9 - 0.474score
challenge
timander
Socratic questioning — challenge the user's assumptions and thinking before they commit.
SkillCFreshness: CClaude Code +9 - 0.474score
code-quality
timander
Offer to add opt-in lint, static-analysis, and coverage tooling for the project's language.
SkillCFreshness: CClaude Code +9 - 0.474score
diagnose
timander
One-shot systematic diagnosis script — understand the problem before suggesting fixes.
SkillCFreshness: CClaude Code +9 - 0.474score
kit-doctor
timander
Self-audit this Copilot kit for token cost, bloat, schema drift, and coverage gaps.
SkillCFreshness: CClaude Code +9 - 0.474score
options
timander
Present a decision as a set of options with trade-offs spelled out, so the user can pick well.
SkillCFreshness: CClaude Code +9
Cite this page
expert-panel skill. Agent Mart. https://agentmart.dev/skills/timander-expert-panel (last updated 2026-10-24)