zoltanmaric/coppersushi / .agents/skills/goldfish
goldfish
VerifiedReview a design artifact (spec, plan, PR packet) with fresh, memoryless subagents. Invoke when the user asks — "goldfish this", "fresh eyes", "tear this apart" — or after suggesting it for a spec that has grown load-bearing and the user agrees.
| File | Kind | Size |
|---|---|---|
| SKILL.md | skill md | 2.1 KB |
SKILL.md
View on GitHub---
name: goldfish
description: Review a design artifact (spec, plan, PR packet) with fresh, memoryless subagents. Invoke when the user asks — "goldfish this", "fresh eyes", "tear this apart" — or after suggesting it for a spec that has grown load-bearing and the user agrees.
---
# goldfish — fresh-context review
Intent: an artifact written in a context-rich session always reads complete *to that
session*. The test is whether a reader with zero session context can act on it.
A goldfish is a fresh subagent given only the artifact plus what any fresh context can
legitimately reach: the repo, the wiki, linked sources. Session context is out of
bounds — don't paste in your intent or the answer you hope for.
Facets — a menu, not a mandate; pick by stakes. Run the deleter before critic and
readiness: optimizing a thing that shouldn't exist is the classic mistake.
1. **Requirement deleter** — whole before parts: should this task exist at all? Is it
the right question? Only then: which individual requirements can be cut?
2. **Comprehension** — can you explain the goal and the touched system from what you
can read?
3. **Simplifier** — of what survives, is there a simpler approach?
4. **Critic** — assume defects exist; verify claims against reality (open the code, run
the command), not against the artifact's account of it.
5. **Readiness** — does this contain what the next action needs? Missing implementation
detail is NOT a finding.
Sandbox (non-negotiable): reviewers never mutate a checkout they don't own. Read-only
subagents by default; a reviewer that must build or run gets its own disposable worktree.
Exit: findings filtered by you — a finding survives if acting on it would change what
gets built or what risk is visible. Weigh findings toward the *next action* and the
direction's validity; defects in far-future steps are usually premature — the user
works iteratively, and those steps will be re-planned before they're reached. Done when a fresh reader can act on the artifact
without rediscovering intent. If substantive findings persist after a couple of rounds,
the artifact needs rethinking, not more polish.
Related skills
| Skill | Stars | Updated | Works with | Status | Install |
|---|---|---|---|---|---|
| brainstormingobra/superpowersYou MUST use this before any creative work - creating features, building components, adding functionality, modifying behavior, or planning anything new, in software or out of it (a talk, a business, a renovation). | Stars: 322k | Updated | Claude CodeCodex | Verified | Install |
| brand-guidelinesanthropics/skillsApplies Anthropic's official brand colors and typography to any sort of artifact that may benefit from having Anthropic's look-and-feel. Use it when brand colors or style guidelines, visual formatting, or company design standards apply. | Stars: 198k | Updated | Claude CodeCodex | Verified | Install |
| frontend-designanthropics/skillsGuidance for distinctive, intentional visual design when building new UI or reshaping an existing one. Helps with aesthetic direction, typography, and making choices that don't read as templated defaults. | Stars: 198k | Updated | Claude CodeCodex | Verified | Install |
| mcp-builderanthropics/skillsGuide for creating high-quality MCP (Model Context Protocol) servers that enable LLMs to interact with external services through well-designed tools. Use when building MCP servers to integrate external APIs or services, whether in Python (FastMCP) or Node/TypeScript (MCP SDK). | Stars: 198k | Updated | Claude CodeCodex | Verified | Install |