Agent skills for Perplexity

Fetch and explain Fedify documentation on a specific topic.

Canonical feedback template for every learner answer in the Fluent system — celebrate correct parts, correct mistakes with category and…

User correction, thumbs up/down, inline editing, and reinforcement signals.

Design confirmations, status updates, and notifications that tell users an action registered.

Feedback synthesis — cluster support tickets, NPS verbatims, app store reviews, and churn surveys by theme, separate signal from noise…

Extract Feishu (Lark) Docs, Wiki pages/collections, spreadsheets, and Minutes (妙记) transcripts into faithful local Markdown via the…

Read and extract content from Feishu (Lark) documents using the official Feishu Open API

Send notifications to Feishu/Lark. Internal utility used by other skills, or manually via /feishu-notify. Use when user says "send to Feishu

Manage Feishu Wiki documents by creating, updating, and organizing content directly through Claude Code commands.

Fetch JIRA issue details including status, assignee, comments, and progress classification

Fetch a Prow job run summary from Sippy showing all failed tests grouped by SIG with error messages

Fetch pull requests that are new in a given OpenShift payload compared to the previous payload

Fetch unresolved review comments from a PR and evaluate with receive-feedback skill

Fetch and return key data from a Prow job's prowjob.json artifact given a Prow job URL

Fetch detailed information about a Component Readiness regression from the Sippy API

Fetch existing triages and untriaged regressions related to a given regression

Fetch an OpenShift CI test report by name to get pass rates, test ID, and Jira component from Sippy

Fetch test runs from Sippy API including outputs for AI-based similarity analysis

Few-shot example generation and optimization for improved LLM performance

Processes video and audio files through FFmpeg commands and local transcription APIs for professional-grade multimedia management.

Enforces a mandatory 9-item context refresh before writing to prevent AI focus degradation in long-form fiction.