All authors
Claude Skills by baekenough
github.com/baekenough186 skills1 installs306 views
- Structured Dev Cycle6-stage structured development cycle with stage-based tool restrictionsVotes: 0GitHub stars: 43
- Stuck RecoveryDetect stuck loops and advise recovery strategiesVotes: 0GitHub stars: 43
- Supabase Postgres Best PracticesPostgreSQL performance optimization guidelines from Supabase. Apply when writing SQL, designing schemas, configuring RLS, or optimizing database performance.Votes: 0GitHub stars: 43
- Systematic DebuggingUse when encountering any bug, test failure, or unexpected behavior. Enforces a strict reproduce-first, root-cause-first, failing-test-first debugging workflow before fixing.Votes: 0GitHub stars: 43
- Task DecompositionAuto-decompose large tasks into DAG-compatible parallel subtasksVotes: 0GitHub stars: 43
- Token Efficiency AuditThree-layer token defense stack — audit current settings, apply safe/CI levers, and monitor statusVotes: 0GitHub stars: 43
- Typescript Best PracticesType-safe TypeScript patterns from industry standardsVotes: 0GitHub stars: 43
- Update DocsSync documentation with project structureVotes: 0GitHub stars: 43
- Update ExternalUpdate agents from external sources (GitHub, docs, etc.)Votes: 0GitHub stars: 43
- Vercel DeployDeploy applications to Vercel with auto-detection and preview URLsVotes: 0GitHub stars: 43
- Web Design GuidelinesUI code review with 100+ rules for accessibility, performance, and UXVotes: 0GitHub stars: 43
- Wiki RagUse the project wiki as RAG knowledge source — search wiki pages to answer codebase questions before exploring raw filesVotes: 0GitHub stars: 43
- WikiGenerate and maintain a persistent codebase wiki — LLM-built interlinked markdown knowledge base (Karpathy LLM Wiki pattern)Votes: 0GitHub stars: 43
- Worker Reviewer PipelineWorker-Reviewer iterative pipeline for quality-critical code with review cyclesVotes: 0GitHub stars: 43
- Alembic Best PracticesAlembic migration patterns for naming conventions, safety checks, expand-contract, env.py configuration, and CI integrationVotes: 0GitHub stars: 43
- Mock Core SkillA mock core skill for testingVotes: 0GitHub stars: 43
- Mock Harness SkillA mock harness skill for testingVotes: 0GitHub stars: 43
- Mock Package SkillA mock package skill for testingVotes: 0GitHub stars: 43
- Action ValidatorPre-action boundary checking — validates agent tool calls against declared capabilities and task contractsVotes: 0GitHub stars: 15
- Adaptive HarnessAuto-detect project context and optimize harness — deactivate unused agents/skills, suggest missing experts, generate project profileVotes: 0GitHub stars: 15
- Agent Eval FrameworkQuantitative agent evaluation using 4-metric framework (correctness/step_ratio/tool_call_ratio/latency_ratio) with ideal trajectory annotation and capability-categorical taxonomy. Use when measuring agent efficiency, comparing agent variants, or gating new agents through correctness→efficiency phases. Complements harness-eval (SE benchmarks) and evaluator-optimizer (qualitative rubric).Votes: 0GitHub stars: 15
- AgoraMulti-LLM adversarial consensus loop — 3+ LLMs compete to find flaws in designs/specs until unanimous agreement is reachedVotes: 0GitHub stars: 15
- Aws Best PracticesAWS patterns from Well-Architected FrameworkVotes: 0GitHub stars: 15
- Claude NativeMonitor Claude Code releases and auto-generate GitHub issues for each new versionVotes: 0GitHub stars: 15
- Codex ExecExecute OpenAI Codex CLI prompts and return resultsVotes: 0GitHub stars: 15
- Crg Integrationcode-review-graph (CRG) MCP wrapper — token-efficient context retrieval via AST knowledge graph. Exposes 4 core tools from CRG.Votes: 0GitHub stars: 15
- Dag OrchestrationYAML-based DAG workflow engine with topological execution and failure strategiesVotes: 0GitHub stars: 15
- De Lead RoutingRoutes data engineering tasks to the correct DE expert agent. Use when user requests data pipeline design, DAG authoring, SQL modeling, stream processing, or warehouse optimization.Votes: 0GitHub stars: 15
- Deep PlanResearch-validated planning — research → plan → verify cycle for high-confidence implementation plansVotes: 0GitHub stars: 15
- Deep VerifyMulti-angle release quality verification using parallel expert review teamsVotes: 0GitHub stars: 15
- Dev Lead RoutingRoutes development tasks to the correct language or framework expert agent. Use when user requests code review, implementation, refactoring, or debugging.Votes: 0GitHub stars: 15
- Dev ReviewReview code against language-specific best practicesVotes: 0GitHub stars: 15
- Docker Best PracticesDocker patterns for optimized containerizationVotes: 0GitHub stars: 15
- Evaluator OptimizerParameterized evaluator-optimizer loop for quality-critical output with configurable rubricsVotes: 0GitHub stars: 15
- FsdFull Self Driving — autonomous release loop that processes all auto-dev-eligible GitHub issues until none remain, by repeatedly running /pipeline auto-dev then /homework.Votes: 0GitHub stars: 15
- Gemini ExecExecute Gemini CLI prompts and return resultsVotes: 0GitHub stars: 15
- GoalDisciplined goal-to-execution workflow for any user task. Parses objective, asks only for materially missing requirements via ambiguity-gate, inspects repo via idea, plans via sdd-dev or deep-plan, executes safely under project conventions, verifies completion per R020, and reports changed files with evidence. Use when user invokes /goal <task>.Votes: 0GitHub stars: 15
- Hada Scouthada.io RSS feed monitoring for AI agent/harness articles with automated /scout analysisVotes: 0GitHub stars: 15
- Harness EvalStructured SE task evaluation using 15 benchmark definitions from claude-code-harness researchVotes: 0GitHub stars: 15
- Harness SynthesizerSynthesize code harnesses for agent action validation — AutoHarness-inspired verifier/filter/policy generationVotes: 0GitHub stars: 15
- HelpShow help information for commands and systemVotes: 0GitHub stars: 15
- HomeworkOn explicit /homework invocation, analyze the current and linked previous sessions, extract mistakes (찐빠), and report them via omcustom-feedback with a confirmation gate. Auto-activation on session cleanup/session-end signals is OPT-IN (default OFF) — requires an explicit project/user directive. Use when explicitly auditing recent work for harness gaps.Votes: 0GitHub stars: 15
- Instinct Extractor다중 세션 transcript에서 반복 실패 패턴(instinct)을 자동 채굴하여 신규 skill candidate 생성Votes: 0GitHub stars: 15
- Intent DetectionAutomatically detect user intent and route to appropriate agentVotes: 0GitHub stars: 15
- Jinja2 PromptsParameterized prompt templates using Jinja2 patterns for reusable, dynamic agent promptsVotes: 0GitHub stars: 15
- ListsShow all available commandsVotes: 0GitHub stars: 15
- Memory ManagementMemory persistence operations using claude-memVotes: 0GitHub stars: 15
- Memory RecallSearch and recall memories from claude-memVotes: 0GitHub stars: 15
- Memory SaveSave current session context to claude-memVotes: 0GitHub stars: 15
- Monitoring SetupEnable/disable OpenTelemetry console monitoring for Claude Code usage trackingVotes: 0GitHub stars: 15