yeaight7/agent-powerups

yeaight7/agent-powerups

Skill Claude CodeCodex

Use when evaluating prompts, LLM outputs, red-team suites, or model behavior with local eval configs and safe provider/cost controls.

yeaight7/agent-powerups

Skill Claude CodeCodex

Use when creating or reviewing red-team eval plugins, attack templates, grader rubrics, safety fixtures, or model-risk test metadata.

yeaight7/agent-powerups

Skill Claude CodeCodex

Use when designing, running, debugging, or hardening deterministic eval suites for agent skills, prompts, tool workflows, or MCP-backed cases.

yeaight7/agent-powerups

Skill Claude CodeCodex

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 existing agent harness needs a quality review.

yeaight7/agent-powerups

Skill Claude CodeCodex

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 for later, or want a single consistent way to invoke codex/gemini/claude.

yeaight7/agent-powerups

Skill Claude CodeCodex

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, or the file scope of a task is unclear.

yeaight7/agent-powerups

Skill Claude CodeCodex

Use when selecting a model for a new task or subagent, deciding whether to escalate after a failed attempt, or designing a multi-agent pipeline with mixed task complexity.

yeaight7/agent-powerups

Skill Claude CodeCodex

Use when a request needs parallel external perspectives — combined backend and UI work, code review from multiple angles, or cross-validation where different models may disagree.

yeaight7/agent-powerups

Skill Claude CodeCodex

Use when querying, ingesting, or maintaining a local RAG MCP corpus for semantic document retrieval with privacy controls.

yeaight7/agent-powerups

Skill Claude CodeCodex

Use when connecting to a managed codebase-context MCP/session service, checking stale maps, or safely using MCP-provided repository context.

yeaight7/agent-powerups

Skill Claude CodeCodex

Use when about to add a new helper, utility, or abstraction, a task sounds like a solved problem, a new external dependency is being considered, or custom code is proposed without checking what already exists.

yeaight7/agent-powerups

Skill Claude CodeCodex

Use when designing or using MCP-backed structured code search with search, AST query, symbol inventory, and bounded extraction workflows.

yeaight7/agent-powerups

Skill Claude CodeCodex

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.

yeaight7/agent-powerups

Skill Claude CodeCodex

Use when a codebase carries over-engineered abstractions, unnecessary layers, or redundant logic that should be collapsed without changing behavior.

yeaight7/agent-powerups

Skill Claude CodeCodex

Use when unused functions, classes, exports, or files need to be identified and safely deleted.

yeaight7/agent-powerups

Skill Claude CodeCodex

Use when package manifests carry unused or redundant third-party dependencies that slow builds, widen the security surface, or complicate updates.

yeaight7/agent-powerups

Skill Claude CodeCodex

Use when migrating APIs, libraries, or patterns across a large codebase and a single mega-commit would be too risky to review or merge.

yeaight7/agent-powerups

Skill Claude CodeCodex

Use when naming conventions or file structure drift across a project and need to be made consistent without changing business logic.

yeaight7/agent-powerups

Skill Claude CodeCodex

Use when code needs restructuring without changing observable behavior.

yeaight7/agent-powerups

Skill Claude CodeCodex

Use when code needs restructuring and observable behavior must stay unchanged, with existing tests kept green at every step.

yeaight7/agent-powerups

Skill Claude CodeCodex

Use when a release spans multiple systems or vendors, order of operations matters with rollback planned up front, or a failed step in one system could corrupt state in a downstream system.

yeaight7/agent-powerups

Skill Claude CodeCodex

Use when reviewing BigQuery spend, query failure patterns, or scan inefficiencies -- identifying which jobs, users, or projects drive cost, or preparing optimization recommendations for a cost review.