# agent-powerups

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

- Tier: Indexed (plain plugin)
- Category: Development
- Page: https://www.flowy.sh/listings/yeaight7-agent-powerups
- Source: https://github.com/yeaight7/agent-powerups
- Price: free and open source

## Summary
agent-powerups is a Claude Code plugin with 200 hand-picked skills for development work, indexed on Flowy. Install it with the command on its page. It includes prompt-evaluation-runner, red-team-eval-authoring, skill-evaluation-workbench. Its skills do not fire on their own yet. Request auto-invocation to have Flowy route them as you prompt. Free and open source.

## Install (Claude Code)
```
npx -y skills add yeaight7/agent-powerups
```

## Skills
- prompt-evaluation-runner
- red-team-eval-authoring
- skill-evaluation-workbench
- agent-harness-design
- canonical-advisor-routing
- context-retrieval-loop
- model-routing
- tri-model-review
- context-retrieval-loop
- local-rag-mcp
- managed-codebase-context
- search-before-building
- structured-code-search-mcp
- ai-slop-cleaner
- architecture-simplification
- context-retrieval-loop
- dead-code-removal
- dependency-cleanup
- incremental-migration
- naming-and-structure-cleanup
- safe-refactor
- test-preserving-refactor
- deploy-pipeline-runbook
- bigquery-cost-audit
- data-quality
- dbt-incremental-strategy-audit
- dbt-preflight
- dbt-strategy
- metric-impact-analyzer
- semantic-layer-change-review
- sql-business-logic-review
- bug-hunt
- failure-triage
- flaky-test-investigation
- incident-readout
- log-driven-diagnosis
- minimal-reproduction
- regression-bisecting
- systematic-debugging
- agent-harness-design
- agent-runtime-patterns
- agent-session-forensics
- brainstorming
- context-compression
- context-minimization
- context-retrieval-loop
- dispatching-parallel-agents
- handoff-discipline
- no-fluff
- repo-map
- strategic-context-compaction
- task-intake
- using-powerups
- verification-before-completion
- writing-plans
- agent-readable-docs
- api-doc-review
- architecture-decision-records
- context-docs
- context-retrieval-loop
- doc-consistency-check
- handoff-discipline
- readme-hardening
- review-comment-style-mining
- gh-address-comments
- github-ci-failure-triage
- pr-review-ci-loop
- baseline-comparison-review
- dataset-split-review
- experiment-tracking-review
- ml-leakage-check
- model-evaluation-reporting
- reproducible-training-runs
- training-pipeline-debugging
- mcp-server-builder
- defuddle
- graphify
- markitdown-file-intake
- memory-build-workflow
- memory-optimization-workflow
- memory-query-workflow
- search-before-building
- using-powerups
- ai-regression-testing
- change-impact-check
- ci-failure-readout
- gh-address-comments
- pre-release-verification
- prompt-evaluation-runner
- receiving-code-review
- red-team-eval-authoring
- requesting-code-review
- risk-based-review
- skill-evaluation-workbench
- test-driven-development
- verification-before-completion
- agent-config-security-audit
- filesystem-mcp-guardrails
- hook-safety-review
- mcp-risk-review
- red-team-eval-authoring
- secret-leak-preflight
- hard-won-skill-extractor
- skill-authoring-guide
- autonomous-delivery-pipeline
- codebase-migration-batches
- parallel-execution-engine
- persistent-completion-loop
- subagent-team-orchestration
- requirements-clarifier
- agent-runtime-patterns
- agent-session-forensics
- browser-automation-safety
- filesystem-mcp-guardrails
- local-rag-mcp
- managed-codebase-context
- structured-code-search-mcp
- agent-config-security-audit
- agent-harness-design
- agent-readable-docs
- agent-runtime-patterns
- agent-session-forensics
- ai-regression-testing
- ai-slop-cleaner
- api-doc-review
- architecture-decision-records
- architecture-simplification
- ask-claude
- ask-codex
- ask-gemini
- autonomous-delivery-pipeline
- baseline-comparison-review
- bigquery-cost-audit
- brainstorming
- browser-automation-safety
- bug-hunt
- build-fix-minimal-diff
- canonical-advisor-routing
- change-impact-check
- changelog-generator
- ci-failure-readout
- codebase-migration-batches
- context-compression
- context-docs
- context-minimization
- context-retrieval-loop
- data-quality
- dataset-split-review
- dbt-incremental-strategy-audit
- dbt-preflight
- dbt-strategy
- dead-code-removal
- defuddle
- dependency-cleanup
- deploy-pipeline-runbook
- dispatching-parallel-agents
- doc-consistency-check
- environment-doctor
- experiment-tracking-review
- failure-triage
- filesystem-mcp-guardrails
- finishing-a-development-branch
- flaky-test-investigation
- gh-address-comments
- github-ci-failure-triage
- graphify
- handoff-discipline
- hard-won-skill-extractor
- hook-safety-review
- incident-readout
- incremental-migration
- json-canvas
- local-rag-mcp
- log-driven-diagnosis
- managed-codebase-context
- markitdown-file-intake
- mcp-risk-review
- mcp-server-builder
- memory-build-workflow
- memory-optimization-workflow
- memory-query-workflow
- metric-impact-analyzer
- minimal-reproduction
- ml-leakage-check
- model-evaluation-reporting
- model-routing
- naming-and-structure-cleanup
- no-fluff
- parallel-execution-engine
- persistent-completion-loop
- pr-review-ci-loop
- pr-triage
- pre-release-verification
- prompt-evaluation-runner
- readme-hardening
- receiving-code-review
- red-team-eval-authoring
- regression-bisecting
- relay-claude
- relay-codex

## FAQ

### What is agent-powerups?
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

### How do I install agent-powerups?
Run these in Claude Code: npx -y skills add yeaight7/agent-powerups. Then prompt normally.

### Does agent-powerups auto-invoke its skills?
Not yet. It is indexed on Flowy as a plain plugin. Request auto-invocation on its page and Flowy will route its skills for you as you prompt.

### Is agent-powerups free?
Yes. Flowy is free and open source, with nothing gated. You can read every skill in full before you install.