All authors
Claude Skills by yeaight7
github.com/yeaight7200 skills5 installs224 views
- Prompt Evaluation RunnerUse when evaluating prompts, LLM outputs, red-team suites, or model behavior with local eval configs and safe provider/cost controls.Votes: 0GitHub stars: 6
- Red Team Eval AuthoringUse when creating or reviewing red-team eval plugins, attack templates, grader rubrics, safety fixtures, or model-risk test metadata.Votes: 0GitHub stars: 6
- Skill Evaluation WorkbenchUse when designing, running, debugging, or hardening deterministic eval suites for agent skills, prompts, tool workflows, or MCP-backed cases.Votes: 0GitHub stars: 6
- Agent Harness DesignDesign agent tool sets with stable names, narrow schemas, deterministic output shapes, and explicit error paths. No catch-all tools unless unavoidable.Votes: 0GitHub stars: 6
- Canonical Advisor RoutingProcess-first advisor routing with artifact captureVotes: 0GitHub stars: 6
- Context Retrieval LoopDeterministic 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.Votes: 0GitHub stars: 6
- Model RoutingVendor-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.Votes: 0GitHub stars: 6
- Tri Model ReviewMulti-model orchestration — route to two external advisors, then synthesizeVotes: 0GitHub stars: 6
- Local Rag McpUse when querying, ingesting, or maintaining a local RAG MCP corpus for semantic document retrieval with privacy controls.Votes: 0GitHub stars: 6
- Managed Codebase ContextUse when connecting to a managed codebase-context MCP/session service, checking stale maps, or safely using MCP-provided repository context.Votes: 0GitHub stars: 6
- Search Before BuildingCheck existing repo capability, external libraries, MCP options, and maintenance risk before writing custom code. Decide adopt/wrap/build with explicit criteria.Votes: 0GitHub stars: 6
- Structured Code Search McpUse when designing or using MCP-backed structured code search with search, AST query, symbol inventory, and bounded extraction workflows.Votes: 0GitHub stars: 6
- Ai Slop CleanerRun an anti-slop cleanup workflow on AI-generated code — regression-tests-first, smell-by-smell, behavior preserved.Votes: 0GitHub stars: 6
- Architecture SimplificationUse to collapse over-engineered abstractions, remove unnecessary layers, or consolidate redundant logic.Votes: 0GitHub stars: 6
- Dead Code RemovalUse to identify and safely delete unused functions, classes, exports, and files.Votes: 0GitHub stars: 6
- Dependency CleanupUse to audit and remove unused or redundant third-party dependencies from package manifests.Votes: 0GitHub stars: 6
- Incremental MigrationUse when migrating APIs, libraries, or patterns across a large codebase. Ensures safe, step-by-step progress rather than risky mega-commits.Votes: 0GitHub stars: 6
- Naming And Structure CleanupUse to enforce consistent naming conventions and file structures across a project without changing business logic.Votes: 0GitHub stars: 6
- Safe RefactorUse when code needs restructuring without changing observable behavior.Votes: 0GitHub stars: 6
- Test Preserving RefactorUse to restructure code while guaranteeing that all existing tests continue to pass.Votes: 0GitHub stars: 6
- Deploy Pipeline RunbookCoordinate multi-system deployment steps as a review-first runbook with explicit approval before any external write or promotion action.Votes: 0GitHub stars: 6
- Bigquery Cost AuditAnalyze BigQuery usage, identify cost hotspots, repeated failures, and practical optimization opportunities.Votes: 0GitHub stars: 6
- Data QualityUse 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.Votes: 0GitHub stars: 6
- Dbt Incremental Strategy AuditAudit whether a dbt incremental model uses the right incremental strategy for the repo, the data shape, and the operational constraints.Votes: 0GitHub stars: 6
- Dbt PreflightInspect changed dbt assets, estimate blast radius, identify missing tests, and recommend the narrowest safe validation plan.Votes: 0GitHub stars: 6
- Dbt StrategyUse 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.Votes: 0GitHub stars: 6
- Metric Impact AnalyzerEvaluate metric and semantic model changes for BI/reporting breakage and business meaning drift.Votes: 0GitHub stars: 6
- Semantic Layer Change ReviewUse when modifying dbt metrics or semantic models to ensure mathematical correctness and backwards compatibility.Votes: 0GitHub stars: 6
- Sql Business Logic ReviewReview SQL for business logic correctness, semantic drift, aggregation risk, and silent definition changes.Votes: 0GitHub stars: 6
- Bug HuntUse when reproducing, isolating, and fixing a bug with the smallest safe change.Votes: 0GitHub stars: 6
- Failure TriageUse when confronted with an unknown failure in CI or production to rapidly categorize the issue before deep debugging.Votes: 0GitHub stars: 6
- Flaky Test InvestigationUse to diagnose tests that pass and fail intermittently without code changes.Votes: 0GitHub stars: 6
- Incident ReadoutUse after fixing a bug to generate a blameless post-mortem summary for human review.Votes: 0GitHub stars: 6
- Log Driven DiagnosisUse when debugging complex runtime failures, distributed systems, or issues where a local debugger cannot be attached.Votes: 0GitHub stars: 6
- Minimal ReproductionUse to isolate a bug from a large application into a standalone, runnable script or single test case.Votes: 0GitHub stars: 6
- Regression BisectingUse when a bug was recently introduced but you don't know which commit caused it.Votes: 0GitHub stars: 6
- Systematic DebuggingUse when encountering any bug, test failure, or unexpected behavior, before proposing fixes.Votes: 0GitHub stars: 6
- Agent Runtime PatternsUse when optimizing agent runtime loops, card packs, MCP session lifecycle, tool-call count, or multi-agent orchestration patterns.Votes: 0GitHub stars: 6
- Agent Session ForensicsUse when diagnosing agent session history, interrupted tool loops, missing tool results, timing bottlenecks, or subagent trace correlation.Votes: 0GitHub stars: 6
- BrainstormingYou MUST use this before any creative work - creating features, building components, adding functionality, or modifying behavior. Explores user intent, requirements and design before implementation.Votes: 0GitHub stars: 6
- Context CompressionUse when conversation context is bloated, constraints are being forgotten, or a compact handoff is needed before continuing work.Votes: 0GitHub stars: 6
- Context MinimizationUse continuously during long tasks. Teaches how to read less, output less, and keep the LLM context window lean and fast.Votes: 0GitHub stars: 6
- Dispatching Parallel AgentsUse when facing 2+ independent tasks that can be worked on without shared state or sequential dependenciesVotes: 0GitHub stars: 6
- Handoff DisciplineUse 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.Votes: 0GitHub stars: 6
- No FluffUltra-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.Votes: 0GitHub stars: 6
- Repo MapUse when the task is to understand an unfamiliar codebase, locate key entry points, or summarize architecture before editing.Votes: 0GitHub stars: 6
- Strategic Context CompactionCompact context at logical phase boundaries — after research, after planning, after debugging — rather than mid-task. Preserves useful state while clearing noise.Votes: 0GitHub stars: 6
- Task IntakeUse at the beginning of a new task. Ensures you fully understand the requirements, boundaries, and acceptance criteria before writing code.Votes: 0GitHub stars: 6
- Using PowerupsUse 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.Votes: 0GitHub stars: 6
- Verification Before CompletionUse 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 alwaysVotes: 0GitHub stars: 6