Audit an existing portfolio case study for missing evidence or unverified claims.
Turn raw project notes and screenshots into a polished, scannable case study.
Tailor an existing case study to a specific job description without changing the facts.
Prepare interview-ready talking points and likely questions from a case study.
| getkishore92/proofcase | 0-bingwu-0/live-interpreter | 010zx00x1/faresnipe | |
|---|---|---|---|
| Stars | 2 | 2 | 2 |
| Language | — | Python | Python |
| Setup difficulty | easy | moderate | easy |
| Complexity | 2/5 | 2/5 | 2/5 |
| Audience | designer | general | general |
Figures from each repo's GitHub metadata at analysis time.
Install with the Skills CLI (npx skills add) into a compatible agent like Claude Code, Codex, or Cursor.
Proofcase is an Agent Skill, meaning it is a set of instructions and reference files that an AI coding or writing assistant can load and follow, rather than a standalone application you run yourself. Its purpose is to turn messy project work, such as notes, screenshots, code repositories, or presentations, into a portfolio case study that is honest about what actually happened, built for product designers, UX researchers, product managers, software developers, and design engineers. The core idea is evidence first, narrative second. When you give Proofcase a case study or raw project material, it builds a record of who owned what, where the claims come from, how confident each claim is, and what the actual outcomes were. If proof for something is missing, it stays marked as missing rather than being filled in with guesses. It will ask you directly for facts it cannot verify on its own, and it will not invent research, ownership, or impact that was not provided. Proofcase adjusts the depth of a case study to match seniority, from junior through staff, lead, or manager level, and it can tailor an existing case study to a specific job description without changing the underlying facts. It also removes generic filler often seen in portfolios, like unnecessary process diagrams or workshop photos, when they do not explain a real decision. The skill produces a scorecard comparing the original and revised case study, rating things like overall clarity and how easily an AI system could extract the role, decisions, and outcomes from the writing, sometimes called scannability. It also flags likely interview questions based on the material. You install Proofcase using the Skills command line tool, which supports agents including Codex, Claude Code, and Cursor, or by cloning the repository and copying the skill folder into the right directory for your agent. Once installed, you interact with it through plain text prompts, for example asking it to audit an existing case study or build one from raw project files.
An AI agent skill that turns project notes, screenshots, and code into honest, evidence-backed portfolio case studies.
Setup difficulty is rated easy, with roughly 5min to a first successful run.
Mainly designer.
This repo across BitVibe Labs
Don't trust strangers blindly. Verify against the repo.