Agent skills for Perplexity

Diagnose and fix an open bug tracked under bugs/ in the current repo, the test-driven way, then close it.

Diagnose and fix software bugs through evidence-based investigation.

Diagnoses software bugs and performance regressions through disciplined, reproducible red-to-green feedback loops.

Turn a vague, intermittent, or environment-specific bug report into a minimal evidence-backed reproduction before proposing a fix.

Automate Bugbug tasks via Rube MCP (Composio).

Automate Bugsnag tasks via Rube MCP (Composio).

Design and implement a distinctive, adaptive SwiftUI dashboard with FreakUI charts and data-display components.

Build and operate a live game using Unity Services — battle passes, progression, cloud saves, leaderboards, matchmaking, economies, remote…

Build a compact Coval test set from product requirements, observed conversation failures or a coverage gap.

Write the title and abstract for a talk or conference session, before any outline or slides exist.

Build AI that answers questions about your database.

Find, evaluate, and assemble the smallest compatible set of AI Agent Skills for an end-to-end natural-language goal.

Build a durable analytical report with an answer-first narrative, evidence-backed findings, charts or tables, caveats, recommendations…

Build and deploy an MCP server from an OpenAPI / Swagger spec using the mcp-use TypeScript SDK.

Build or refactor an AppKit app feature on top of SwiftASB using explicit application, window, document, thread, and turn ownership with…

Build or rebuild the SDLC artifact index for agent-navigable discovery

This skill succeeds when: 1. Build script executes and returns exit code 2. Build result communicated to user (success or failure message)…

Art-direct and implement distinctive, motion-rich marketing, editorial, portfolio, and landing websites with original reference-inspired…

Use when you need to rebuild the BSP overlay — DT, OOT modules, or kernel — from changes under bsp_sources/.

Use when encountering dependency conflicts, CocoaPods/SPM resolution failures, "Multiple commands produce" errors, or framework version…

Checks build, lint, type, test, and CI delivery gate failures.