AI & Agents Agent Skills for Perplexity

Orchestrate multi-agent workflows for feature development using planning agents, context handoff, and stage management

Audit a project and recommend the highest-value skills to add or update.

Caching strategies for LLM prompts including Anthropic prompt

A comprehensive collection of battle-tested prompts inspired by [awesome-chatgpt-prompts](https://github.com/f/awesome-chatgpt-prompts)…

Structured prompt template creation with variables, formatting, and version control

Locate an existing OpenProse installation via env var, AIWG config, local install, plugin manifest, or global CLI.

Reference guide for using PROXY_MODE with external AI models.

Build production-ready AI agents with PydanticAI — type-safe tool use, structured outputs, dependency injection, and multi-model support.

Queue processing with fresh context per phase.

Regenerate CLAUDE.md for Claude Code with hook file architecture

Select and execute the canonical refresh, existing-project extraction, or legacy AIWG context regeneration branch

Regenerate .windsurfrules for Windsurf with preserved team directives

Peer messaging contract. Required reading when you see a `[relay from=...]` line in your input, when you need to hand off a subtask, ask…

Cleanly remove openwolf from cwd (.wolf/, hooks, rules, CLAUDE.md snippet, PM2, registry).

Automate Replicate AI model operations -- run predictions, upload files, inspect model schemas, list versions, and manage prediction…

Use when an evaluation run must merge research, findings, documentation, and repair outputs into one verified result.

Use when an evaluation run requires bounded iterative refinement with trace and cleanup evidence.

Analyzes feedback logs to identify patterns and suggest improvements to review skills.

Review and analyze a skill against best practices for length, intent scope, and trigger patterns

Recursive Language Models (RLM) CLI - enables LLMs to recursively process large contexts by decomposing inputs and calling themselves over…

Run reproducible DeepSWE coding-agent benchmark evaluations through OpenRouter and mini-swe-agent.