Jev Done Check

SkillDev tools

Lets your agent double-check whether claimed finished work actually has supporting evidence before calling it done.

Available today. Use it from your connected AI after setup.

Add ahel to your AI once: Claude, ChatGPT, Cursor, Claude Code or Codex. Then ask it to use this.

Then ask your AI: use the Jev Done Check skill

About this skill

[omh] Completion claim tested by Jev: Jev done check: does the gathered evidence support the completion claim? It can only object. Use when the user says: jev-done-check, jev done check, ask jev if this is done, jev evidence check.

What this skill tells your AI

The instructions your AI receives, as published by rlaope/oh-my-hermes in skills/omh-jev-done-check/SKILL.md and read by ahel’s review.

Required: each completion claim, observed evidence, and the goal. Output: objections per claim, or no_objection.

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. Preset: references/preset.md.

Procedure

  1. Name what leaves the machine: each claim, an excerpt of observed output, and the goal.
  2. Call omh_jev_ask with preset: done_check/v1 and state {claim, evidence_excerpt, goal}, one ask per claim, at most 6.
  3. Report each objection with its claim and rule; fix or withdraw an objected claim before reporting completion.

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: 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 not_observed with rule: not_answered:<status>, never Jev's 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
235
Last commit
Sep 2026
Advanced
Item type
skill
Key
omh-jev-done-check
Source
github.com/rlaope/oh-my-hermes