acceptance
A skill in the LobeHub repository, version 0.10.0, for checking that delivered work actually behaves as intended in the real product and recording the evidence.
What the skill teaches
A skill in the LobeHub repository, version 0.10.0, for checking that delivered work actually behaves as intended in the real product and recording the evidence. The agent first decides whether acceptance is needed (not for docs-only or pure refactor changes) and reuses valid earlier evidence, then hands execution to a cheaper runner agent with a separate checker that reviews the plan and the evidence. Checks must be outcomes a person would accept or reject, not test or lint results, and UI changes need inspected before-and-after screenshots across the CLI, web, Electron, macOS or iOS Simulator. Results go into immutable rounds, which the lh CLI publishes to LobeHub for a signed-in user and otherwise turns into an HTML report on disk.
Capabilities
- Plan acceptance checks as user-visible outcomes
- Capture and inspect before-and-after screenshots
- Publish acceptance rounds or render a local report
About
- Publisher
- LobeHub
- Tool
- Testing
Install
The project doesn't document install steps that we could confirm. See the project's own instructions
What's inside
- LICENSE
- agents/openai.yaml
- references/acceptance-checker.md
- references/agent-browser.md
- references/auth-web.md
- references/axe.md
- references/common-mistakes.md
- references/computer-use.md
- references/delegation.md
- references/evidence.md
- references/flows.md
- references/interaction-cost.md
- references/legacy-plan-handoff.md
- references/plan-format.md
- references/probe-mock-patterns.md
- references/project-adapter.md
- references/publication-recovery.md
- references/recording-cdp.md
- references/recording-ios-simulator.md
- references/recording-native-macos.md
- references/report-schema.md
- references/report.md
- references/resource-guard.md
- references/screenshot-helpers.md
- references/sim-use.md
MCP servers and skills can run code on your computer and act on your data. Review the source before installing.
This skill includes scripts that your agent may run.
Details
| Fact | Value | Source |
|---|---|---|
| Type | Skill | |
| Tool | Testing | |
| Publisher | LobeHub | source |
| Official status | Not stated in its documentation | |
| Needs an API key or sign-in | Not stated in its documentation | |
| Includes scripts | Yes | source |
| Platforms | Not stated in its documentation | |
| AI clients | Not stated in its documentation | |
| Licence | Apache-2.0 | source |
| Pricing | Not stated in its documentation | |
| Activity | Last commit Nov 11, 202684,974 GitHub starsDownload data not available (not on npm or PyPI) | source |
| Links | Repository Website |
More from LobeHub
17 skills
- add-model-provider (Skill)
- agent-testing-bot (Skill)
- alint-ruleset (Skill)
- deep-review (Skill)
- docs-changelog (Skill)
- lobe-design (Skill)
Also listed under: Testing
Sources
- Skill file (SKILL.md)github.com/lobehub/lobehub · Backs: LicenceNov 15, 2026
- GitHub repositorygithub.com/lobehub/lobehub · Backs: Publisher, ActivityNov 11, 2026
- Skill file (SKILL.md)github.com/lobehub/lobehub · Backs: LicenceNov 10, 2026
- Folder in the repository (acceptance)github.com/lobehub/lobehub · Backs: Includes scriptsNov 10, 2026