Agent skills

Use when coordinating complex tasks across multiple AI agents with a centralized handoff document for planning, execution tracking, and…

Use when choosing which AI model to use for a task — pick the right model family and tier based on cost, speed, context needs, and…

Trace, complete, and interpret the Pareto frontier across competing objectives using repeated single-objective cuOpt solves (weighted-sum…

Multi-person lip-sync is Free Mode only — face detection, audio split, manual role-track pairing.

Structure a decision or design challenge through multiple perspectives before committing to action.

Convert master assets into platform-variant exports with safe-zone enforcement.

Unified multi-project management skill for GitHub, Azure DevOps, and Jira.

Survey existing cloud architecture for lock-in depth and portability gaps.

Synchronize conventions and policies across all repositories in the workspace with branch consistency enforcement

Coordinate development workflows across multiple Git repositories with synchronized branching, batch commits, cross-repo operations, and…

Orchestrates long-running task lifecycles with Multica from initial planning to automated patrol and PR merge.

Build standalone HTML prototypes for new, modified, or migrated pages.

Batch multiple smart contract queries into a single call using Nethereum Multicall (.NET).

Coordinating text, image, voice, and tool-use modalities in a single interaction.

Draft the Multiple PD/PI Leadership Plan for grants with more than one principal investigator — governance, roles by aim, decision-making…

This skill should be used for advanced LLM evaluation: LLM-as-judge systems, direct scoring, pairwise comparison, rubric calibration…

This skill should be used when long-running agent sessions need context compression, structured summarization, compaction, token-per-task…

This skill should be used for improving context efficiency: context budgeting, observation masking, prefix or KV-cache strategy…

This skill should be used when agent work needs file-backed context: durable scratchpads, tool-output offloading, just-in-time discovery…

This skill should be used when designing hosted or background agent infrastructure: sandboxed execution, remote coding environments, warm…

This skill should be used for project-level decisions about LLM-powered systems: whether an LLM is the right primitive for the task at…