// Open a concise GitHub follow-up for reusable browser-use limitations. Use when browser automation is blocked by a likely tool-side issue that is worth fixing separately, especially for clicks, dropdowns, file inputs, focus traps, or other repeatable agent/browser failures.
ALWAYS use this skill when working with convex or kitcn. Covers both setup and e2e feature paths using cRPC + ORM + auth + React.
Codex autoreview/code review closeout: local dirty changes, PR branch vs main, parallel tests.
Fallback browser automation with persistent Chrome state. Use only when Browser Use is unavailable or blocked.
Work heavyweight framework or library tasks with planning-first research, selective deep analysis, and rigorous handoff
Work a task end-to-end with lean context gathering, implementation, and verification
Read every doc in www and packages/kitcn/skills/kitcn, sync to active changeset(s), and track with checkmarks.
| description | Open a concise GitHub follow-up for reusable browser-use limitations. Use when browser automation is blocked by a likely tool-side issue that is worth fixing separately, especially for clicks, dropdowns, file inputs, focus traps, or other repeatable agent/browser failures. |
| argument-hint | [browser block summary] |
| disable-model-invocation | true |
| name | agent-browser-issue |
| metadata | {"skiller":{"source":".agents/rules/agent-browser-issue.mdc"}} |
Handle $ARGUMENTS.
Use this only for likely reusable agent/browser tooling bugs. Do not use it for:
Capture only the minimum:
Open a GitHub issue with:
agent:browserBody shape:
## URL
<url>
## Action
<what the agent tried>
## Block
<what failed>
## Expected
<what should have happened>
## Actual
<what happened instead>
## Repro
1. ...
2. ...
3. ...
agent-native-reviewer and note that gap in the issue