Test-First Bug Fix Skill: Reproduce, Fix, Prove (SKILL.md)
A SKILL.md that forces your coding agent to reproduce a bug with a failing test before changing code, apply the smallest fix, and prove it with the test suite.
341 prompts · last added
152 results for “describe light by source” · page 4 of 7
A SKILL.md that forces your coding agent to reproduce a bug with a failing test before changing code, apply the smallest fix, and prove it with the test suite.
Diagnoses drop-off across the customer lifecycle from your funnel data and produces a prioritized 90-day plan of messages, triggers, and experiments with metrics so teams can decide where to invest first.
Turns your product facts, customer evidence, and competitor notes into a tested positioning statement, messaging hierarchy, and proof-gap list so a marketing team can decide what to say and what to validate first.
Diagnoses where a workflow slows down using your process steps and metrics, then ranks causes and produces a 30-day improvement plan with owners, measures, and risks.
Turns a new role and what you know about the team into a 30-60-90 day plan: learning goals, relationships to build, one early win, and questions to agree with your manager in week one.
Produces an onboarding guide for one folder of a codebase: what it does, how data moves through it, the files to read first and the traps a new developer should avoid.
Turns a side-business idea into a one-page plan: customer, offer, price, channel, costs, and the cheapest 30-day test that would prove people will pay.
Compares competitor homepage copy with your positioning to map overlap, find unclaimed angles, and propose one sharper differentiating line.
Turns pasted customer reviews into evidence-based personas, jobs-to-be-done, objections and a bank of exact customer phrases ready to reuse in copy.
Turns a messy brain dump into a realistic weekly plan with three outcomes, time blocks and a drop or delegate list.
Explains each pasted lab value and its reference range in plain English and ends with questions to bring to your doctor, without diagnosing.
Stress-tests a plan with five strong objections, hidden assumptions, the likeliest failure path and the evidence that would change the verdict.
Gives a funny but kind roast of your resume or LinkedIn profile, followed by the five fixes that would improve it most, ranked.
Creates a simple full-body program for three gym days a week, with sets, reps, rest, how to add weight, and easier swaps for each exercise.
Audits an existing multi-agent pipeline for failure modes and produces retry limits, fallback paths, escalation triggers, and a test plan. Supports the decision on what to harden before wider rollout.
Turns a set of abstracts into a comparison matrix of methods, samples, findings and limits, then maps where studies agree, conflict and leave gaps for your review.
Turns one article into ten posts for LinkedIn, X, Instagram and email, each built on a different idea from the piece, written natively for the platform rather than as a summary.
Designs a three-agent content pipeline where a researcher, writer and editor pass structured handoffs, with the exact fields each agent receives and returns and checks between stages.
Builds a negotiation script for a job offer: your anchor number with a reason, word-for-word replies to common pushback, and a walk-away line, using market data you supply.
Makes ChatGPT ask up to 7 clarifying questions one at a time, confirm a one-paragraph brief, and only then produce the work.
Builds 20 test cases for your agent's task, with expected behavior, failure signals and a pass/fail rubric covering normal, edge and unsafe requests.
Guides you through a homework problem with one hint or question at a time, revealing each step only after you attempt the current one.
Calculate a sustainable hourly and project rate from your income target and billable hours, covering tax, unpaid admin time and expenses with the math shown.
Rewrites resume bullets to mirror a job posting's keywords only where they are true, and lists the requirements you cannot honestly claim.
Guide
Nothing that fits? Write a prompt with AI.
341 copy-ready prompts for productivity, writing, business and coding and more. Each one sets the role, the steps and the output format, and marks the parts you fill in with curly brackets.
Most are written for ChatGPT (285), Gemini (260), Claude (217) and Claude Code (42); the number is how many prompts list that tool. Each prompt page lists its tools, and most text prompts also work in any capable chat model.
Words in curly brackets, such as {audience}, are the parts you replace with your own details. Choose “Ready to use (no blanks)” in the filters to see prompts you can paste as they are.
By how often they are copied, unless you choose another order. Newest shows the latest additions first. Trending ranks prompts by copies, opens and saves over the last two weeks.
No. Every prompt is free to copy or open in your AI tool. A free account lets you save prompts to your vault.
Yes. Write with AI asks what you need, builds a short form for it, and writes the prompt as you fill it in.