Evaluates LLMs across 60+ academic benchmarks (MMLU, HumanEval, GSM8K, TruthfulQA, HellaSwag).
Evaluates LLMs across 100+ benchmarks from 18+ harnesses (MMLU, HumanEval, GSM8K, safety, VLM) with multi-backend execution.
Open-source AI observability platform for LLM tracing, evaluation, and monitoring.
Managed vector database for production AI applications.
Coordinate long-running, multi-milestone projects across multiple turns, from conversational discovery through evidence-based completion.
This skill should be used when coordinating multiple subagents, implementing orchestrator patterns, or managing parallel agent workflows.
Use when automating one PRD (plan → review plan → code → review code → commit) in one parent chat with cold subagents that die, asking…
Multi-agent workflow coordination with routing, state management, and failure recovery
You are the master controller of the AI Dev Factory.
Plan iterations, delegate to SDLC agents, and compile iteration status
Process a full or partial refund on an order and optionally create a replacement draft order for the customer.
Load this skill before performing ANY task on the OrderMitra codebase — writing code, designing schema, adding a dependency, changing an…
When to activate: organizational design, org structure, restructuring, span of control, matrix organization, team topologies, reporting…
Cross-functional organizational health check scoring 8 dimensions on a traffic-light scale.
Configure multi-tenant organizations, manage members and invitations, define custom roles and permissions, set up teams, and implement…
Use when deciding which orgstud-* sub-skill to invoke next, or when sequencing manuscript work from topic through rebuttal for an…
Trigger on 存入 Obsidian or 存入obsidian when the user attaches or has just attached files, pastes URLs, names inbox materials, or sends the…
Use when turning a screened, coded corpus into an analytic spine that advances theory or policy for a Review of Educational Research (RER)…
Use when imposing an analytical structure or taxonomy on a literature for a Journal of Economic Literature (JEL) survey — the "spine" that…
Applies Anthropic's official brand colors and typography to any sort of artifact that may benefit from having Anthropic's look-and-feel.
Manage application configuration across environments with layered config loading, environment variables, secrets management, and validation.