Jev Ask
SkillDev toolsLets your agent send yes/no or multiple-choice questions to Jev and get back probability numbers instead of prose.
Use Jev Ask in Claude, ChatGPT or Ahel Desktop
Free. Sign in, add Jev Ask and connect your AI. About a minute.
Also: Claude Code · Cursor · Codex
Then ask your AI: use the Jev Ask skill
Details
Instructions available. Your AI can read the instructions. Execution depends on the setup they require.
Account requirements not reviewed. Check the skill instructions before use; Ahel provides instructions and does not run this skill.
No other account needed.
Add Ahel to your AI once: Claude, ChatGPT, Cursor, Claude Code or Codex. Then ask it to use this.
About this skill
[omh] User named Jev for yes/no or pick-one probabilities: Jev ask: typed yes/no, pick-one, or scored questions to Jev with your own key; returns probabilities, never prose. Use when the user says: jev-ask, ask jev, jev question, jev score.
What this skill tells your AI
The instructions your AI receives, as published by rlaope/oh-my-hermes in skills/omh-jev-ask/SKILL.md and read by Ahel’s review.
Required: text to judge and independent typed questions. Output: Jev's probabilities, served model, and cost, or a non-answer status.
Read omh-routing/references/jev-rail.md before the first ask: consent, what leaves the machine, limits, and non-answer statuses. Prepared OMH routing is not execution or approval. Shared product, routing, compatibility, and evidence rules: omh-routing/references/skill-common-rail.md.
Contract: references/full-contract.md.
Procedure
- Check the rail: the user asked for Jev in this turn, and say in one line what
statewill carry. - Write independent, self-contained questions over one
state: Noul withcriteria.true/criteria.false, Choice with anunknownoption, Score with ordered levels. - Call
omh_jev_askwithquestions(default modeljev-latest; pinjev-1.13.0when a threshold was tuned). - Report each number verbatim with the served model, attempts, and
cost_usdpluscost_source; 0.4 to 0.6 is uncertain.
Completion Checklist
- Preserve workflow intent and stop conditions; load the full contract before claiming completion.
- Reply in the user's own words and the host's own voice: its SOUL.md persona owns reply language, tone, speech level, and sentence endings, progress updates included (where it sets no language, use the one the user wrote in), and OMH shapes structure and content only; OMH's record terms (surface, lane, wrapper, handoff, evidence boundary, not_observed) stay in records and tool calls, never in the sentence the user reads unless they ask about one; and when a stop condition or a decision the user owns ends the turn, offer the next action as a question rather than declaring what will not be done.
- Report the tool's status, ask_id, served model, and cost source; a non-answer is reported as its status and is never an answer.
- Record observed delegation results; use Hermes-native subagent/delegation features when available: native subagents -> Hermes delegation when available, otherwise sequential lanes.
Recovery Notes
- Tool missing,
consent_not_observed, or refused: follow the rail's recovery section; never simulate an answer.
Workflow Lane
advisory local context
Signals
- GitHub stars
- 3k
- Forks
- 237
- Last commit
- Oct 2026
Advanced
- Item type
- skill
- Key
omh-jev-ask- Source
- github.com/rlaope/oh-my-hermes
github.com/rlaope/oh-my-hermes