Productivity & Workflow Agent Skills for Microsoft Copilot

Downloads official academic paper PDFs, distinguishes preprints from published versions, handles institutional access, and maintains a…

Reviews academic manuscripts from a peer reviewer's perspective to identify critical flaws, novelty gaps, and submission readiness.

Sales execution across pipeline, discovery, demos, negotiation, and closing.

Diagnoses overdue invoices and cash conversion bottlenecks by aging receivables, mapping customer risk exposure, and prioritizing…

Route plain-language requests for Claude Code, Cursor, Copilot, OpenClaw ACP, OpenCode, Gemini CLI, Qwen, Kiro, Kimi, iFlow, Factory…

Add a Component Readiness triage record link to a JIRA issue description

Deep research where agents adversarially fact-check each other's findings instead of one agent confidently citing sources it never verified.

Notion-as-source-of-truth dispatch board for running your work like an AI agency.

Coordinate a spec-first initiative across one ticket Executor and one independent Verifier.

Audit or rewrite Codex prompts, AGENTS.md files, skill instructions, and sub-agent briefs when guidance is bloated, conflicting, stale, or…

Use when a project's CLAUDE.md has grown past what anyone reads and you want the agent to learn durable facts from its own sessions…

Aggregates, reconciles, and finalizes multi-agent engineering task results into comprehensive project-level integration reports.

Maintains and synchronizes local AI agent underlying rules, system prompts, and configuration files across platforms.

Use after completing any non-trivial task.

Use when: (1) Starting a long-running experiment that may span multiple sessions/disconnects, (2) Resuming work after a break and needing…

Operate as an agentic engineer using eval-first execution, decomposition, and cost-aware model routing.

Build persistent multi-agent operating systems on Claude Code.

Use the Obsidian CLI when a task depends on Obsidian's index or running application state, such as resolved links or properties, Bases, or…

Patterns and architectures for autonomous Claude Code loops — from simple sequential pipelines to RFC-driven multi-agent DAG systems.

Generate AGENTS.md (cross-tool agent context — Codex CLI, Aider, Cursor, etc.) and wire CLAUDE.md as a symlink so Claude Code reads the…

Generate or update repository-specific AGENTS.md instruction files from real repo evidence.