jev-me
Agent skill that grills a plan as a design-tree interview, using Jev for typed judgments along the way.
This repository is mostly documentation or write-up rather than runnable code.
Overview
jev-me is a small agent skill in the style of grill-me prompts: it interrogates a plan or idea as a design-tree interview, and uses Jev ad hoc for typed judgments during the questioning. It is installed with the skills CLI and invoked with a /jev-me command inside a coding agent.
The README is only a few lines, so details of which judgments Jev makes are not documented. It needs a TYPESAFE_API_KEY exported in the environment. It is best seen as a lightweight demo of mixing a conversational interview with typed decision calls.
What the decision model decides
| Type | Question | Answers |
|---|---|---|
| Other | Typed judgments about the plan during the interview (not documented)(inferred) | — |
How it works
- Install the skill with npx skills add
- Export TYPESAFE_API_KEY
- Type /jev-me and describe the plan
- The agent interviews you, calling Jev for typed judgments
Strengths
- Quick to install as a skill
- Combines open questioning with typed decision calls
Caveats
- Very sparse README; behaviour is not documented
- Requires a TypeSafe API key
Getting started
npx skills add jon-devlapaz/jev-me, then type /jev-me with TYPESAFE_API_KEY exported.At a glance
- Type
- Demo
- Status
- prototype
- Runtime
- Agent skill
- Has code
- yes
- License
- MIT
Use cases and integrations
How curated lists describe it
A grill-me style interrogation of your idea, with Jev doing the grilling.
hellogumbo/awesome-jev
Frequently asked questions
What does jev-me do?
It interviews you about a plan as a design tree, using Jev for typed judgments.
How do I run it?
Install it with npx skills add jon-devlapaz/jev-me and type /jev-me.
Does it need a key?
Yes, TYPESAFE_API_KEY must be exported.
Related projects
Agent Zero plugin adding a typesafe_query tool that asks Jev Choice, Noul and Score questions and shows probability cards in chat.
ProjectbetaPythonCLI and MCP tool that finds hard-coded judgment calls in your code, scores how well Jev fits, and replaces strong fits with a fallback.
ProjectbetaTypeScriptMCP server exposing a judge tool for typed noul, choice and score questions over JSON state, backed by Jev.
MCP serverbetaTypeScriptLocal MCP server that lets an agent delegate a decision to Jev and get a recommended choice with percentages.
MCP serverbetaTypeScript- Building with Jev★ 155
Agent skill for writing and improving programs that call Jev: question design, state structure, thresholds and diagnosing wrong answers.
Agent skillproduction Go MCP server giving any client typed Jev decisions via OpenRouter or TypeSafe, with validated answers and no paid retries.
MCP serverproductionGo