Productivity & Workflow Agent Skills

Wire integration tools into an agent: discover what's connected, attach the right tool, point it at a credential slot.

Use when auditing an ESEC/FSE research-track submission for HotCRP readiness, covering the mandatory paper-registration step, the ACM…

Use when planning an ESEC/FSE project timeline from venue fit through paper registration, submission, the journal-style Major Revision…

What differs when a consultation panelist is Sakana AI's Fugu model, reached through the Codex CLI interface as `codex-fugu`: attribution…

Use when you have an approved implementation plan and want to execute the complete development lifecycle - from workspace setup through…

Use FuseForge for coordinated selection, confirmed greenfield setup, approved specialist Design integration, and read-only consult across…

Use FuseForge in Cursor for selection, confirmed greenfield setup, approved specialist Design integration, and read-only consult without…

When the user wants to know who they actually know inside an account, who is missing, and how much money depends on one person staying…

Gather Slack messages, Gmail messages, and calendar events from the previous calendar day for a configured set of sources.

Run substantial AI-agent work as a quality-bar gauntlet with Unlazy-style acceptance gates, Depth Tree decomposition, runnable checks…

Build and test with the gauntlet-loop technique.

Use as the entry point for any Global Change Biology (GCB) manuscript.

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

Use as the entry point for any Global Environmental Change (GEC) manuscript.

Sketch types, signatures, and module structure before code, then stay in the loop while implementation fills in.

Spawn N parallel candidates at the same task, pick a base, graft the strongest parts of the losers into it.

Reconstruct your recent working context from your own chat history, live state, and the shared record (user reports, prior fixes…

Spawn three parallel review subagents over the active transcript, surface learnings, and route each to a concrete edit on an existing skill.

Fan out N parallel workers, drain them, and return one report.

Use when you need help with anything

Default process for handling open-ended tasks that touch files, the shell, or the web.