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 unused functions, classes, exports, or files need to be identified and safely deleted.
$ npx -y skills add yeaight7/agent-powerups --skill dead-code-removal --agent claude-codeHow it fires
How this skill gets triggered: by you, by Claude, or both.
/dead-code-removalContext preview
The summary Claude sees to decide when to auto-load this skill.
Use when unused functions, classes, exports, or files need to be identified and safely deleted.
name: dead-code-removal description: Use when unused functions, classes, exports, or files need to be identified and safely deleted.
Dead code increases maintenance overhead and confuses developers. Verify a symbol is truly unused across the entire repository, then delete it outright — never comment it out.
1. **Verify unused — search the entire repository.** Do not assume code is dead just because the current file doesn't use it:
grep -rn "symbolName" . --include="*.ts" --include="*.tsx" # all references grep -rn "from ['\"].*module-name" src/ # import sites git log -3 --oneline -- path/to/suspect-file # recent touches
Ecosystem tools can shortcut the inventory when available (e.g., knip or ts-prune for TypeScript exports, vulture for Python).
2. **Check for dynamic invocation.** Be wary of dynamically invoked code — reflection, dependency injection by string name, ORM mappers, route tables, config-driven dispatch:
grep -rn "\"symbolName\"\|'symbolName'" . # string-keyed references
If there is any doubt, leave it alone or ask the user.
3. **Delete aggressively.** Once confirmed unused, delete the code. Do not comment it out.
4. **Prune dependencies.** If you delete the only code that was using an imported module, remove the import statement as well.
5. **Run tests.** Always run tests and/or type checkers (e.g., `tsc --noEmit`) after removal to ensure you didn't accidentally break a hidden dependency.
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,…