Productivity & Workflow Agent Skills for ChatGPT

Review project task tracking and stigmergic signals to identify and explain the next task to work on

Let the model choose which skill(s) to apply to the request on its own — read the task, pick the best-fitting skills from the library, and…

Turn a skill OR a plain-language activity into a continuous loop that repeats until YOU quit — no round count, no ceiling, it just keeps…

The intensified version of a goal — don't just reach the requirement, then push far past it.

Work a punch list to completion autonomously — overnight, through a todo list, or until a product is polished — parking decisions and…

Use when the user wants a multi-perspective review of an EB-2 NIW question, document, or strategy — a 4-persona council (former USCIS…

Use when the user wants a structured review of a specific EB-2 NIW document — petition letter, recommendation letter, business plan…

Use when the user wants a strict EB-2 NIW case review from an officer-style perspective: test Dhanasar prongs, identify red flags, score…

Scope, implement, fix, simplify, groom, review, continue, or finish a concrete Workbench outcome, from one change through several epics.

Use as the entry point for any New Media & Society (NM&S) manuscript.

Use when requirements, KPI definitions, permissions, financial treatment, statuses, date semantics, exception handling, or acceptance…

Finalize artifacts from the accepted result while preventing rejected session-only alternatives and correction history from leaking into…

Use when reviewing a product artifact or implementation handoff that contains proposed or implied screens, navigation, roles, workflows…

Use when planning, implementing, debugging, or reviewing work where the solution could expand beyond the user's requested outcome…

Never burn time blocking on a wait. Forbids foreground `sleep`/idle-polling to wait for a long job (a download, fetch, build, backtest…

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.

Design an auditable playbook when no narrower one fits: a large migration, an ambitious multi-part change, or work a human reviews after…

Index of the engineering principles. Load it whenever work is non-trivial: designing types or a signature, refactoring, debugging…

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

Keep a reviewable decision trail for long-running or unattended work: a TSV log with one row per decision (what, why, evidence, result).