Productivity & Workflow Agent Skills for DeepSeek Harness

Creates and maintains index files mapping features to file paths

Maintain project memory by reconciling current decisions, evidence, unresolved work and reusable lessons.

Open-source maintainer orchestration: Codex app workers, work recovery, dependencies, vision, releases.

Use when the user asks to run Codex CLI (codex exec, codex resume) or references OpenAI Codex for code analysis, refactoring, or automated…

Persistent memory for Claude across conversations.

Guide for setting up projects to work optimally with Claude Code.

Personal intelligence system for capturing thoughts, managing knowledge, and surfacing insights.

Create new skills, modify and improve existing skills, and measure skill performance.

Four-phase debugging framework for any technical issue.

Automate Make (Integromat) tasks via Rube MCP (Composio): operations, enums, language and timezone lookups.

Use when the user invokes $make-slide-pro or asks to create, convert, redesign, repair, audit, animate, localize, update, or certify a…

Use when the user explicitly wants a deep CTO-mode review of a Piyaz project.

Edit, update, or remove an existing custom agent.

Manage Apple Reminders on macOS through a native EventKit command with explicit confirmation for mutations and machine-readable results.

Manage persistent Codex task goals: create and inspect a goal, explain Goal mode, map ON/OFF requests to start, pause, resume, or clear…

Cross-cutting reference manager for medical manuscripts.

Use when deciding which mgsci-* sub-skill to invoke next, or when sequencing manuscript work from topic selection through rebuttal for a…

Orchestrates and routes academic manuscript development from topic selection through empirical identification and peer review for 《管理世界》…

Guides manuscript revisions and drafts point-by-point rebuttal letters tailored for Management World (《管理世界》) R&R submissions.

Activate ultra-compressed communication mode that drops ~75% token usage by eliminating articles, filler, pleasantries, and hedging while…

Report estimated context window utilization and flag when approaching the compaction threshold