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 package manifests carry unused or redundant third-party dependencies that slow builds, widen the security surface, or complicate updates.
$ npx -y skills add yeaight7/agent-powerups --skill dependency-cleanup --agent claude-codeHow it fires
How this skill gets triggered: by you, by Claude, or both.
/dependency-cleanupContext preview
The summary Claude sees to decide when to auto-load this skill.
Use when package manifests carry unused or redundant third-party dependencies that slow builds, widen the security surface, or complicate updates.
name: dependency-cleanup description: Use when package manifests carry unused or redundant third-party dependencies that slow builds, widen the security surface, or complicate updates.
Bloated dependencies slow down builds, increase security surface area, and complicate updates. Audit manifests against actual imports, remove unused packages via the package manager (so lockfiles stay correct), and validate with the build.
1. **Audit the manifest.** List declared dependencies:
npm ls --depth=0 # JavaScript/TypeScript pip list --not-required # Python: packages nothing else depends on
2. **Verify usage — manifest vs imports.** For any suspect dependency, perform a global search across the codebase:
grep -rn "from ['\"]lodash\|require(['\"]lodash" . grep -rn "^import requests\|^from requests" . # Python import forms npx depcheck # JS/TS: automated manifest-vs-import report, if available
Search build scripts, configs, and CI files too — not just src/.
3. **Remove with the package manager.** If there are zero usages, use the native command (e.g., `npm uninstall lodash` or `pip uninstall ...`). Do not just manually edit the manifest unless absolutely necessary, to ensure lockfiles are updated correctly.
4. **Consolidate duplicates.** If multiple libraries serve the exact same purpose (e.g., `moment` and `date-fns`), flag it to the user for future consolidation. Do not attempt a massive library migration autonomously.
5. **Validate.** Run the build and test suite to ensure the removed dependency wasn't implicitly required by a build script or runtime environment.
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,…