prompt-evaluation-runn…
Use when evaluating prompts, LLM outputs, red-team suites, or model behavior with local eval configs and safe provider/cost controls.
Use when a working code path feels bloated, noisy, or over-abstracted, when asked to clean up or deslop AI-generated code, or when a reviewer-only anti-slop pass is requested.
$ npx -y skills add yeaight7/agent-powerups --skill ai-slop-cleaner --agent claude-codeHow it fires
How this skill gets triggered: by you, by Claude, or both.
/ai-slop-cleanerContext preview
The summary Claude sees to decide when to auto-load this skill.
Use when a working code path feels bloated, noisy, or over-abstracted, when asked to clean up or deslop AI-generated code, or when a reviewer-only anti-slop pass is requested.
name: ai-slop-cleaner description: Use when a working code path feels bloated, noisy, or over-abstracted, when asked to clean up or deslop AI-generated code, or when a reviewer-only anti-slop pass is requested.
Reduce AI-generated code bloat through systematic, smell-by-smell cleanup that preserves existing behavior and raises signal quality.
This skill accepts an optional **file list scope**. If a changed-files list is provided, keep the cleanup strictly bounded to those files. Do not silently expand a changed-file scope.
1. **Lock behavior with regression tests first**
2. **Create a cleanup plan before code**
3. **Categorize issues**
4. **Execute passes one smell at a time**
5. **Run quality gates**
If invoked with a `--review` flag, operate as a reviewer-only pass: 1. Do **not** start by editing files. 2. Review the cleanup plan, changed files, and regression coverage. 3. Check specifically for leftover dead code, duplicate logic, needless wrappers, and missing tests for preserved behavior. 4. Produce a reviewer verdict with required follow-ups. 5. Hand needed changes back to a separate writer pass instead of fixing and approving in one step.
AI SLOP CLEANUP REPORT ====================== Scope: [files or feature area] Behavior Lock: [targeted regression tests added/run] Cleanup Plan: [bounded smells and order] Passes Completed: 1. Dead code deletion - [concise fix] 2. Duplicate removal - [concise fix] 3. Naming/error handling cleanup - [concise fix] 4. Test reinforcement - [concise fix] Quality Gates: - Regression tests: PASS/FAIL - Lint: PASS/FAIL - Typecheck: PASS/FAIL - Tests: PASS/FAIL Changed Files: - [path] - [simplification] Remaining Risks: - [none or short deferred item]
Curated power-ups for coding agents: skills, slash commands, MCP configs, hooks, AGENTS.md templates, and workflows for serious software engineering. Claude Code, Codex, Antigravity CLI, Cursor and more
Repo: yeaight7/agent-powerups
Use when evaluating prompts, LLM outputs, red-team suites, or model behavior with local eval configs and safe provider/cost controls.
Use when creating or reviewing red-team eval plugins, attack templates, grader rubrics, safety fixtures, or model-risk test metadata.
Use when designing, running, debugging, or hardening deterministic eval suites for agent skills, prompts, tool workflows, or MCP-backed cases.
Use when designing tool definitions for a new agent or subagent, an agent shows high retry rates, ambiguous tool invocations, or silent failures, or an…
Use when routing a prompt to a local provider CLI for a second opinion, review, or plan -- you are about to call a provider directly, need the response saved…
Use when starting work in an unfamiliar area of a codebase, spawning a subagent that needs targeted file context, a first search pass missed the relevant file,…