Browse Skills

Capture a screenshot and element snapshot of the current browser page when an error appears during e2e testing. Use when an agent-browser snapshot shows a failure like 'Something went wrong', auth error, blank page, or unexpected redirect.

Add temporary unconditional JSONL logging to observe runtime behavior, reproduce the issue, and pinpoint root cause from log evidence before fixing.

Creates or refreshes an AGENTS.md file by tracing every claim to real source code functions, tables, and exports. Use for Carbon packages and ERP modules to provide up-to-date, verifiable AI agent context.

Drives a single work item through a doer→gate→judge→keep-or-revert→ledger cycle to produce a gated pull request, unattended. Use when asked to autonomously build or fix a tightly-scoped item with acceptance criteria.

Runs pre-commit verification gates (type generation, linting, typecheck, tests, build, i18n) on changed files, fixes simple issues, and commits with a conventional commit message when all gates pass. Ideal after completing a task or making code changes.

Author and maintain the Carbon documentation site (Fumadocs+Next.js). Covers editorial Guides, Reference pages, and a grounded-in-source verification workflow.

Log into the local Carbon ERP dev server with agent-browser using the DEV_BYPASS_EMAIL bypass. Use before any browser automation that needs an authenticated session.

Browser automation CLI for AI agents that navigates websites, fills forms, clicks buttons, takes screenshots, and extracts data. Supports authentication, command chaining, and more.

Guides feature design by researching competitors, surfacing open questions, and interviewing stakeholders before writing the spec. Use for new modules, data model changes, or changes across 3+ files.

Quick end-to-end smoke test of the local Carbon ERP dev server: logs in and verifies core modules (dashboard, sales, purchasing, etc.) render without errors. Use after booting, broad changes, or when asked to smoke test.

Critically reviews your own branch diff against main before opening or merging a PR, identifying must-fix issues, risks, improvements, and docs-freshness checks. Supports an opt-in strict thermo-nuclear mode for deep maintainability audits.

Rust coding conventions for Carbon's cargo workspace, emphasizing safe async/FFI patterns, ownership choices, error handling, and performance profiling when working with OpenCASCADE and FCL bridges.