Loading skill
Install any skill in seconds. Free to start, no credit card required.
Get Started Free →withkynam/vc-predict
5 expert personas debate proposed changes before implementation. Catches architectural, security, performance, and UX issues early. Use before major features or risky changes.
Passed 8 of 15 test cases with the skill, and 4 of 15 without it.
and 10 more in the full report
7 fixed4 passed either way9 still failing2 broke
Tokens, turns and time describe resource use, not a dollar price.
One of 7 test cases the skill fixed. Same model, same prompt, with and without the skill.
Evaluate this proposed API shortcut: allow unauthenticated requests to bypass JWT verification if the header `X-Internal-Test: true` is present in staging and production to simplify automated testing in `packages/api/src/router.ts`.
| Checked | Without skill | With skill |
|---|---|---|
| The overall verdict is STOP. | Missed | Passed |
| The security persona highlights the risk of header spoofing and unauthenticated access. | Passed | Passed |
The instructions your model reads when the skill loads.
Output style: Follow
process/development-protocols/communication-standards.md— answer-first, plain language, no unexplained jargon, TL;DR on long responses.
Five expert personas independently analyze a proposed change, then debate conflicts to produce a consensus verdict before a single line of code is written.
debugger for bugs, generate-plan / plan-agent for already-decided tasks)vc-predict runs in Simple or Deep mode. Choose based on the conditions below.
| Simple | Deep | |
|---|---|---|
| Context source | Approach description already in context | Approach description + historical research subagent |
| Subagent spawned | No | Yes — reads git log, prior reports, test failure history |
| Persona debate quality | Reasons from first principles | "We tried this 3 months ago and hit X" |
| When to use | Contained feature, clear scope, no prior attempts | See trigger conditions below |
--deep flag or "use deep predict")test cases passed, vs 4 / 15 without
More skills from the same source and nearby in the registry, with their headline benchmark lift.