28,473 skills sorted by stars.
Llm subsystem in TTA.dev: execute and related code. 171 symbols | 30 files | Cohesion: 67%
USE FOR RAG/LLM grounding. Returns pre-extracted web content (text, tables, code) optimized for LLMs. GET + POST. Adjust...
Convene an internal "council" of distinct senior-engineer personas to analyze a problem, stress-test an approach, and pr...
Orchestrate multi-LLM parallel debate and synthesis. Dispatches prompts to available omega CLI wrappers in parallel, col...
Provider-agnostic multi-LLM deliberation. Three phases — independent responses, cross-model anonymized ranking, chairman...
Run Fireworks-hosted open-weight model councils that compare responses and synthesize a final answer.
Diagnoses LLM output failures including hallucinations, constraint violations, format errors, and reasoning issues. Prov...
Measure an LLM feature instead of vibe-checking it. Five modes. ANALYZE: read 20–30 real outputs, write one line each, g...
Design, run and interpret evaluations of LLM-based systems - build a task-specific golden set, pick metrics (exact match...
Claude acts as manager/architect while delegating all coding to external LLM CLIs (Gemini, Codex, Qwen). Claude never wr...
Expert guide for LLM observability in production — token cost tracking, hallucination rate monitoring, latency analysis,...
Explain and apply the foundational LLM Wiki architecture and knowledge-management strategy. Use for setup, architecture,...
Karpathy's LLM Wiki — build and maintain a persistent, interlinked markdown knowledge base. Ingest sources, query compil...
Karpathy's LLM Wiki: build/query interlinked markdown KB.
Use when the user wants a compiled markdown wiki, Karpathy llm-wiki ingest/query/lint, or to file sources into interlink...
Guide users through setting up a personal LLM-maintained wiki — a persistent, compounding knowledge base where the LLM i...
Build and maintain an LLM-curated personal knowledge base — the "LLM Wiki" pattern from Andrej Karpathy's April 2026 gis...
Build and maintain a structured LLM-generated wiki for any codebase. Use when the user asks to analyze/understand/docume...
Build and maintain a personal knowledge base (wiki) using LLMs. Instead of RAG-style retrieval, the LLM incrementally co...
Answer questions from the compiled Wiki. Use whenever the user asks a knowledge question that this vault might cover.
Generates and maintains a standards-compliant llms.txt file for any website — either by crawling the live site OR by rea...
LLVM IR and pass pipeline skill. Use when working directly with LLVM Intermediate Representation (IR), running opt passe...
Use when working with LLVM IR as a user: emitting IR from clang, running opt passes, lowering with llc, reading IR, or f...
Indexes and queries project research graphs backed by hex-research MCP. Use for hypotheses, goals, benchmark runs, evide...
Reviews completed code and delivery evidence before acceptance or release. Use to find defects and verify readiness; not...
Audits cross-cutting code health across security, delivery, maintainability, dependencies, diagnosability, concurrency,...
Audits implemented architecture fitness, boundaries, contracts, dependency topology, structure, and configuration owners...
Complete story workflow orchestrator for Agile
Fixes tasks in To Rework and returns them to To Review. Applies reviewer feedback only for the selected task.
Designs a risk-based test strategy and prioritized scenarios without changing code. Use when requirements need a test pl...
Modernizes a bounded capability to reduce demonstrated maintenance cost; not routine upgrades or performance tuning.
Audits implemented architecture boundaries, dependencies and ownership; not target design or plan review.
Coordinates 4 documentation audit workers (structure, semantic, fact-check, code comments). Delegates parallel audits, a...
Checks compiler/linter errors, deprecation warnings, type errors, failed tests, build config issues. Returns findings wi...
Checks build, lint, type, test, and CI delivery gate failures. Use when auditing whether the project can reliably ship.
Checks evidence-backed duplication, over-abstraction, and unused extensibility. Use when auditing DRY/KISS/YAGNI risk.
Checks local maintainability hotspots: complexity, long methods, god modules, signatures, algorithms, and constants. Als...
Checks dependency health and generic custom utility/integration replacement opportunities. Use when auditing dependency...
Finds code that can be safely deleted: unreachable, unused, obsolete compatibility, and commented-out code. Use when pru...
Checks diagnosability through structured logs, metrics, traces, correlation IDs, and useful log levels. Use when auditin...
Checks runtime lifecycle and config validation: bootstrap, shutdown, probes, cleanup, env sync, and fail-fast startup. U...
L3 Worker. Audits project physical structure: file hygiene, ignore file quality, framework convention compliance, domain...
Checks file hygiene, ignore files, framework conventions, domain/layer organization, naming. Use when auditing project s...
Universal project bootstrapper: CREATE new or TRANSFORM existing project to production-ready structure
Upgrades .NET NuGet packages with breaking change handling
Upgrades Python pip/poetry/pipenv dependencies with breaking change handling
Documents implemented current-state architecture from repository evidence. Use for onboarding or migration baselines; no...
Coordinates project structure: SCAFFOLD new or RESTRUCTURE existing to Clean Architecture