review-panel

Plugin review-panel from marketplace scott-cc in citadelgrad/scott-cc. Commands read from the repo's manifest — 14 days ago.

Skills (34)

• abstraction-quality

  Use when adjacent layers feel redundant, when decorator/wrapper patterns

• adr-skill

  Use when you need to propose, write, update, accept/reject, deprecate,

• adversarial-reviewer

  Use when code, a PR, diff, or design needs a precision-oriented adversarial review backed by reproducible target/control evidence.

• catalog-steward

  Maintains plugins/review-panel/reviewers/persona-catalog.md over time — finds coverage holes and evaluates candidate skills for catalog inclusion. Advisory only; never auto-edits the catalog. Not a per-diff review lens; do not cast this as a review-panel seat.

• code-evolution

  Use when reviewing changes to existing code (diffs, PRs, or recently

• comments-docs

  Use when the user asks to review comments or documentation, when comments

• complexity-recognition

  Use when code feels harder to work with than it should but the specific

• data-steward

  Use when a diff touches migration files, ORM/model definitions, schema

• deep-modules

  Use when a module's interface has too many parameters or methods, when\

• design-it-twice

  Use when the user asks to design something twice, or before committing

• design-review

  Use when reviewing a file, module, or PR for overall design quality\

• diagnose

  Use when someone describes a problem but doesn't know which skill to

• domain-modeling

  Use when reviewing a type/interface/schema definition, an entity or\

• error-design

  Use when the user asks to review error handling, when a module throws

• general-vs-special

  Use when the user asks to check interface generality, when a module has

• grill-my-taste

  Use when the user wants to build or extend TASTE.md. Grilling session

• grill-the-schema

  Use when the user wants to stress-test their data layer or has no DATA-MODEL.md\

• grill-with-docs

  Use when the user wants to stress-test a plan against their project's

• improve-codebase-architecture

  Use when the user wants to improve architecture, find refactoring opportunities,

• information-hiding

  Use when the user asks to check information hiding, when modules seem

• mental-models-adversarial

  Use when a diff introduces a new algorithm, heuristic, threshold, retry/backoff

• mental-models-economics

  Use when a diff adds a new dependency or vendor, includes a TODO/FIXME/HACK

• mental-models-simplifier

  Use when a diff is primarily a performance optimization, introduces\

• mental-models-systems

  Use when a diff touches concurrency, queues/message buses, caching,\

• module-boundaries

  Use when deciding whether to combine or separate two specific modules,

• naming-obviousness

  Use when the user asks to check naming, when names feel vague or imprecise,

• ponytail-audit

  Use when the user says \"audit this codebase\", \"audit for over-engineering\"\

• ponytail-review

  Use when the user says \"review for over-engineering\", \"what can we\

• pull-complexity-down

  Use when callers must do significant setup, handle errors the module

• red-flags

  Use when reviewing a PR for design quality, evaluating unfamiliar code

• review-panel

  Use when a diff, PR, or branch needs a comprehensive verification pass before merge, when invoked as an automated Foundry/CI gate (mode:agent), or when the user asks for a "review panel" or "full review." Casts diverse reviewer seats, runs them concurrently, deduplicates and validates findings, fixe

• strategic-mindset

  Use when the user asks to evaluate design investment, when code was written

• taste-review

  Use when TASTE.md exists at the repo root and diffs need reviewing against

• tdd

  Use when implementing a feature or bug fix test-first, when the user requests red-green-refactor, or when behavior needs a durable regression test through a public interface.

Slash commands (1)

• /review-panel:review-panel

  Run the review-panel orchestrator against a diff, PR, or branch — human-interactive by default, or unattended machine output with --mode=agent; narrow the review scope with --lite, --medium, or --auto

Subagents (1)

• clean-room-alternative

  Generates a design alternative in isolation, without seeing the first design. Used by the design-it-twice skill when a first design already exists in conversation.

Hooks (1)

• SessionStart

  python3 ${CLAUDE_PLUGIN_ROOT}/hooks/session-identity.py

Similar plugins