Agent skills for Perplexity

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.

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…

Complete methodology for solving multi-step time series forecasting competitions where lag features cause systematic underprediction at…

Use when working with the multi-tenant architecture — customer DB switching, FQDN routing, tenant isolation, or cross-tenant operations.

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).

Manage e-commerce operations across multiple marketplaces and channels.

MultiGlossar configuration and exclusion rules - glossar_starttag/glossar_endtag scope selection, glossar_ignoretags with tag/class locks…

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

Orchestrates end-to-end multiplatform Chinese content production with automated research, A/B drafting, visual generation, and QA packaging.

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…