Claude Skills by yeaight7

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.

Design agent tool sets with stable names, narrow schemas, deterministic output shapes, and explicit error paths. No catch-all tools unless unavoidable.

Process-first advisor routing with artifact capture

Deterministic 3-cycle loop for gathering codebase context before acting. Broad search → exact source and tests → target-specific docs and setup. Stop after enough context or report what is still missing.

Vendor-neutral routing guide for choosing the right model tier by task type. Mechanical work uses a smaller/faster model; implementation uses a standard model; architecture, security, and release audit use the most capable model.

Multi-model orchestration — route to two external advisors, then synthesize

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

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

Check existing repo capability, external libraries, MCP options, and maintenance risk before writing custom code. Decide adopt/wrap/build with explicit criteria.

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

Run an anti-slop cleanup workflow on AI-generated code — regression-tests-first, smell-by-smell, behavior preserved.

Use to collapse over-engineered abstractions, remove unnecessary layers, or consolidate redundant logic.

Use to identify and safely delete unused functions, classes, exports, and files.

Use to audit and remove unused or redundant third-party dependencies from package manifests.

Use when migrating APIs, libraries, or patterns across a large codebase. Ensures safe, step-by-step progress rather than risky mega-commits.

Use to enforce consistent naming conventions and file structures across a project without changing business logic.

Use when code needs restructuring without changing observable behavior.

Use to restructure code while guaranteeing that all existing tests continue to pass.

Coordinate multi-system deployment steps as a review-first runbook with explicit approval before any external write or promotion action.

Analyze BigQuery usage, identify cost hotspots, repeated failures, and practical optimization opportunities.

Use when adding or reviewing data quality tests for dbt models in warehouse-backed analytics projects. Covers dbt generic tests, singular tests (assert_*.sql), accepted-values macros, dbt_utils patterns, cross-system consistency tests, and warehouse-oriented validation. Use when writing data tests, creating assert_*.sql files, testing business logic, or validating referential integrity.

Audit whether a dbt incremental model uses the right incremental strategy for the repo, the data shape, and the operational constraints.

Inspect changed dbt assets, estimate blast radius, identify missing tests, and recommend the narrowest safe validation plan.

Use when creating or modifying dimensional dbt models in warehouse-backed analytics projects. Covers a four-layer warehouse architecture (sources/staging/core/marts), naming conventions, no-alias SQL rule, surrogate-key and missing-record patterns, incremental strategies, deduplication, and common project macros. Use when building fact tables, dimension tables, staging models, writing SQL, or designing tests.

Evaluate metric and semantic model changes for BI/reporting breakage and business meaning drift.

Use when modifying dbt metrics or semantic models to ensure mathematical correctness and backwards compatibility.

Review SQL for business logic correctness, semantic drift, aggregation risk, and silent definition changes.

Use when reproducing, isolating, and fixing a bug with the smallest safe change.

Use when confronted with an unknown failure in CI or production to rapidly categorize the issue before deep debugging.

Use to diagnose tests that pass and fail intermittently without code changes.

Use after fixing a bug to generate a blameless post-mortem summary for human review.

Use when debugging complex runtime failures, distributed systems, or issues where a local debugger cannot be attached.

Use to isolate a bug from a large application into a standalone, runnable script or single test case.

Use when a bug was recently introduced but you don't know which commit caused it.

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.

Use when optimizing agent runtime loops, card packs, MCP session lifecycle, tool-call count, or multi-agent orchestration patterns.

Use when diagnosing agent session history, interrupted tool loops, missing tool results, timing bottlenecks, or subagent trace correlation.

You MUST use this before any creative work - creating features, building components, adding functionality, or modifying behavior. Explores user intent, requirements and design before implementation.

Use when conversation context is bloated, constraints are being forgotten, or a compact handoff is needed before continuing work.

Use continuously during long tasks. Teaches how to read less, output less, and keep the LLM context window lean and fast.

Use when facing 2+ independent tasks that can be worked on without shared state or sequential dependencies

Use when completing a task or running out of context limit. Ensures the next session or human engineer has exactly what they need to resume work instantly.

Ultra-compressed communication mode. Cuts token usage ~75% by dropping filler, articles, and pleasantries while keeping full technical accuracy. Use when user says "no fluff", "be concise", "use less tokens", or similar.

Use when the task is to understand an unfamiliar codebase, locate key entry points, or summarize architecture before editing.

Compact context at logical phase boundaries — after research, after planning, after debugging — rather than mid-task. Preserves useful state while clearing noise.

Use at the beginning of a new task. Ensures you fully understand the requirements, boundaries, and acceptance criteria before writing code.

Use when starting work in a repository with Agent Powerups installed, when a task may match a reusable local skill, command, workflow, hook recipe, AGENTS.md template, or MCP feature.

Use when about to claim work is complete, fixed, or passing, before committing or creating PRs - requires running verification commands and confirming output before making any success claims; evidence before assertions always