Plans a framework, database, or API migration from your current setup to a target one, honoring the compatibility window, downtime limit, and behavior you say must be preserved.
- Takes old/new stack, current and target setup, and hard constraints as input
- Outputs an ordered migration checklist, tackling the riskiest changes first
- Generates code transformations for common patterns and lists breaking changes
- Includes a rollback plan and validation tests to confirm the migration worked
Fill in the feature you want built, the language, and up to three specific requirements, and get an implementation request structured enough that nothing important gets skipped. It explicitly asks for error handling, edge cases, performance, and framework best practices to be considered up front, and instructs the output to keep existing comments intact and explain its own logic inline.
Builds a full year of content planning from an industry, target
audience, business goals, and known seasonal trends, mapping each of the
12 months to a theme, three content pillars, five key topics, seasonal
tie-ins, relevant industry events, and recommended content types. Meant
to be revisited quarterly, swapping in real performance data as each
quarter closes so the calendar stays grounded instead of becoming a
one-time planning exercise.
Give it a raw feature idea along with product context, target users, technical stack, and constraints, and get back more than a task list. It clarifies the problem statement, surfaces assumptions and open research questions, scopes an MVP with explicit out-of-scope items, then works through user stories, technical design, data model needs, implementation phases, and risks before ending with a validation plan.
Turns a messy file or module you want to clean up into a step-by-step refactoring plan, built around your stated goal, available tests, and time budget rather than a full rewrite.
Each step comes with a risk level and a way to verify it before moving on, plus tests to add, a rollback plan, and an explicit list of what not to touch yet. Meant for code that already works but is getting harder to change safely.
Plans a single newsletter issue for a given {audience} around one {topic} and {main_message}, rather than a scattered list of links.
- Inputs: audience, topic, main message, links or resources, offer/CTA, tone, length
- Output: subject line and preview text options, an opening paragraph, a section outline, link placement notes, a CTA section, and a plain-text version
- Keeps the issue built around one main idea with no filler intro
- Suited to recurring publications like weekly product or content updates
Describe your dream life a set number of years from now, and this two-part prompt first tells
a vision-casting story of a day as your future self, then builds a concrete weekly and daily
schedule to get you there.
- Takes a timeframe and a detailed dream-life description across life domains
- Factors in your working style and schedule constraints
- Produces a narrative day-in-the-life piece
- Follows up with an actionable weekly/daily routine
For when you have a video title but no real structure yet — this expands a rough idea into a full outline, not a finished script.
Provide the title, audience, core problem, promise, points to cover, available examples, and tone, and it returns a hook angle, open loop, detailed section-by-section outline, expected viewer takeaways per section, evidence needed, transition notes, retention risks, and CTA placement.
Turns a broad, pasted research topic into a structured question map that separates core questions from background questions, lists assumptions that still need validating, names the likely source types to consult, and lays out a practical research sequence to follow. Flags which claims will require primary sources rather than secondary summaries. Best used at the very start of an open-ended research project, before committing time to any one direction, to scope an unfamiliar subject with a clear path instead of unfocused reading.