メニュー
Browser Agent Driver CLI operator for browser automation, UI/design audits, auth state, showcases, and benchmark runs. Triggers: "run bad", "browser agent", "design audit", "webbench", "automate this site".
Codex または Claude でインストール この Prompt をコピーして Codex、Claude、または他のアシスタントに貼り付けると、Skill ページを確認してインストールできます。
SOC 職業分類に基づく
Raise the ceiling, don't climb toward it. When a target is nearly hit or a metric has plateaued, question the target itself: name the binding constraint, separate the physics floor from the assumed floor, design the regime change that makes 10x reachable, commit through the valley. Triggers: 'breakout', '10x this', 'raise the ceiling', 'why are we capped', 'think way bigger', 'this metric is a cage'.
Prove that a merged change is actually live and production behavior is measured against the deployed artifact. Use after merge, before claiming deployed/live/validated, for Cloudflare Pages/Workers deploys, cache claims, perf claims, and release closeout.
Diagnose and improve eval harnesses built on @tangle-network/agent-eval or similar trace-first systems. Use when success/failure rates, scorecard deltas, judge outputs, promotion gates, benchmark rows, or improvement campaigns may be contaminated by harness bugs, evaluator drift, routing/auth failures, missing traces, or invalid baselines.
Goal-pursuit loop: measure, diagnose, experiment, verify, compare, and iterate against a measurable target. Triggers: evolve, optimize, make this better, push to target.
Split one messy experiment branch into N clean, independent branches — one logical change each, built from the merge-base, disjoint change-sets, each an isolated reviewable PR. Triggers: 'finalize', 'split this branch', 'atomize this', 'make reviewable PRs', 'decompose this mess'.
Read repo/session state and choose the single next skill: exploit (evolve/polish), explore (pursue/meta-harness/breakout), bootstrap (eval-agent), diagnose (diagnose/eval-harness-diagnose), or step back (reflect). One dispatch, then exit.
| name | bad |
| description | Browser Agent Driver CLI operator for browser automation, UI/design audits, auth state, showcases, and benchmark runs. Triggers: "run bad", "browser agent", "design audit", "webbench", "automate this site". |
Use the bad CLI for real browser work: automation, evidence capture, design audits, site rips, auth-state setup, showcases, and browser benchmarks.
Do not fake browser results; every claim must come from a run artifact, screenshot, DOM extract, trace, or saved report.
bad --version.@tangle-network/browser-agent-driver or run it from source; stop if neither is available.bad --help or the specific subcommand help before relying on flags.bad run executes a browser task from a goal, URL, or case file.bad design-audit scores product/visual/trust issues, extracts tokens, compares sites, or rips a page.bad showcase captures hero shots, full-page screenshots, walkthroughs, dark mode, and retina assets.bad auth captures, validates, or injects authenticated browser state.bad runs lists historical runs and helps resume or fork prior work.See references/full-reference.md for the full CLI command catalog, auth patterns, config shape, and examples.
bad design-audit --rip or the current equivalent from bad design-audit --help.ui-test when the task is specifically QA of a product UI or PR.product-design-audit when the user wants redesign decisions, not only browser evidence.