Menu
SkillsMP has collected 9 skills from bradfrost/skills. Open a skill to review its source and details.
Showing 9 of 9 collected skills.
The AI limits interview — run by /setup-brad-frost-skills, or directly any time. A short guided interview that establishes your personal limits for AI usage — quiet hours, a sessions-per-day ceiling, how sessions end — then wires them into whatever your tools…
START HERE after installing Brad Frost's skills — run this once to get everything set up. Finds which of the skills you installed, runs the setup each one needs (the limits interview), and tells you how to use the ones that need no setup. Use when the user…
End every AI session definitively — the task that started the session is the task that ends it, loose ends get filed rather than dangled, and every substantive response closes with a compact Signal Flags block instead of a trailing "want me to also…?" hook.…
Enforce the sessions-per-day ceiling the user set for themselves — count sessions honestly, refuse new ones past the limit with the same terse message every time, and make raising the limit a deliberate, logged act. Use when the user asks "how many sessions…
Make the environmental cost of AI usage visible — floor estimates built from published per-prompt figures, rendered as lightbulb time (💡), with an optional weekly energy budget that informs but never blocks. Use when the user asks "how much energy did this…
Honor the quiet hours the user set for themselves — the hours where AI tools are off-limits so "one more prompt" stops costing sleep. Enforced as refused tool calls where hooks exist, advisory everywhere else, with a deliberate logged override path. Use when…
Produce a design-system adoption plan for a product — tear down its bespoke UI, map every custom pattern to its design-system replacement, estimate the effort, and hand back a prioritized, phased build schedule. Use when the user wants to adopt, migrate to,…
Run a design system multi-point inspection — assess a design system across 10 stations (coverage, best practices, accessibility, shared language, testing, orchestration, governance, feedback, machine-readable docs, agent access) and produce a red/yellow/green…
Run a product multi-point inspection — assess a shipping product (app, website, or feature) as-built across 10 stations and produce a red/yellow/green inspection report with a prioritized work order. Use when the user asks to inspect, assess, audit, or…