acceptance
Self-evidence for delivery verification in any repository, with or without LOBE_OPERATION_ID or a preconfigured verify plan. Discover an existing plan when present; otherwise author checks and publish a standalone acceptance. Pick the proving surface (CLI / web / desktop / iOS Simulator), capture real evidence, and submit it with the lh CLI. Triggers on 'verify the task', 'collect evidence', 'prove it works', 'upload evidence', 'verify plan', 'requiredEvidence', or any run that must self-certify its delivery. Missing LobeHub environment IDs never make this skill inapplicable.
Profile →npx skills add lobehub/lobehub --skill acceptance --agent claude-code
Same command for any agent — swap --agent for codex, cursor, copilot.
Weekly change comes from our own snapshots, not the repository page — it measures attention, not adoption.
# Verify (Builder Self-Evidence) You are the **builder** for a delivery. A separate review step judges it against either an existing **verify plan** or checks you author before testing. Some criteria demand **evidence** (a screenshot, a DOM snapshot, CLI output…). A criterion that declares `requiredEvidence` **cannot pass on your text alone**: if the artifact is missing, the structural gate marks it `uncertain` and the delivery is held. ## Applicability invariant This skill applies whenever the delivery needs real verification. Environment IDs select a path; they are not prerequisites: - `$LOBE_OPERATION_ID` means a verify plan already exists. Discover and satisfy it. - No `$LOBE_OPERATION_ID` means you author the checks and publish a structured report round. - `$LOBEHUB_TOPIC_ID` or `--subject` groups rounds under an existing LobeHub object. - No topic or subject means `lh acceptance run ingest` creates a standalone acceptance automatically. Never report that this skill is inapplicable merely because `$LOBE_OPERATION_ID`, `$LOBEHUB_TOPIC_ID`, or a Task ID is absent. Continue with the standalone path. So while you do the work, capture the proof and submit it. The loop: ``` discover
- Applicability invariant
- Two entry points — an operation id is NOT required
- Rounds are immutable — repair means a NEW round
- Prerequisites
- Step 1 — Discover the plan (what to prove)
- Step 2 — Pick the surface by what you changed
- Step 3 — Capture, then submit each artifact
- Step 4 — Self-check coverage (do not skip)
- Final handoff (mandatory)
- Portability rules
- Reference map
lh verify plan state "$LOBE_OPERATION_ID" --json CHECK_ITEM_ID is the plan item id for this criterion (from Step 1). file artifact already captured by the selected surface lh acceptance run result submit --operation "$LOBE_OPERATION_ID" --item "$CHECK_ITEM_ID" \ inline text artifact (stdout / computed value) — no file lh acceptance run result list --operation "$LOBE_OPERATION_ID" --json # checkItemId → checkResultId lh acceptance run evidence list "$CHECK_RESULT_ID" --json
What does the acceptance skill do?
Self-evidence for delivery verification in any repository, with or without LOBE_OPERATION_ID or a preconfigured verify plan. Discover an existing plan when present; otherwise author checks and publish a standalone acceptance. Pick the proving surface (CLI / web / desktop / iOS Simulator), capture real evidence, and submit it with the lh CLI. Triggers on 'verify the task', 'collect evidence', 'prove it works', 'upload evidence', 'verify plan', 'requiredEvidence', or any run that must self-certify its delivery. Missing LobeHub environment IDs never make this skill inapplicable.
How do I install it?
Run `npx skills add lobehub/lobehub --skill acceptance --agent claude-code` — it drops the skill into your project so the agent can pick it up. Swap the --agent value for codex, cursor or copilot if you use one of those.
Where does this skill come from?
From lobehub/lobehub, a repository with 81,252 stars. We read it straight from the repository tree rather than a submitted listing, so what you see here is what is actually published.
Is a popular skill a good skill?
Not necessarily. Stars measure attention, not adoption — a repository can trend for a week and be abandoned. That is why we show the weekly change from our own snapshots next to the total, instead of a single flattering number.