surfwright

Use SurfWright CLI for deterministic browser control. Prefer JSON, explicit handles, and typed error codes.

Safety Notice

This listing is imported from skills.sh public index metadata. Review upstream SKILL.md and repository scripts before running.

Copy this and send it to your AI assistant to learn

Install skill "surfwright" with this command: npx skills add marcohefti/surfwright/marcohefti-surfwright-surfwright

SurfWright Skill

Deterministic browser control with JSON-first outputs and explicit handles.

Discovery (Two Lanes)

  • Action first: run mission commands directly.
  • Fast lane bootstrap: surfwright contract --profile browser-core.
  • Do not probe with which, help flags, or repeated skill file reads.
  • Use surfwright contract --command <id> only after a command-id miss.
  • Use surfwright contract --commands <id1,id2,...> for small miss batches.
  • Use surfwright contract --full only for deep-lane catalog discovery.

Runtime Rules

  • Keep default JSON output; do not parse prose.
  • Confirm required JSON schema via surfwright contract --command <id> only after a command-id miss.
  • Start headless unless explicitly instructed otherwise.
  • For workspace extension workflows, verify open/session payload appliedExtensions[*].state == runtime-installed before proceeding.
  • Treat non-zero exits as typed failures and branch on code (retryable when present).
  • Use one unique --agent-id per task.
  • Treat daemon queue overload codes (E_DAEMON_QUEUE_TIMEOUT, E_DAEMON_QUEUE_SATURATED) as backpressure.
  • If daemon transport is unreachable and continuity matters, use SURFWRIGHT_DAEMON=0.
  • For non-trivial plans, prefer run --plan <file> (or --plan -) over inline --plan-json.
  • For complex JavaScript, prefer target eval --script-file / --script-b64.
  • Prefer typed primitives over eval when possible: target count, target attr, target click --nth, target click --count-after.

Source Transparency

This detail page is rendered from real SKILL.md content. Trust labels are metadata-based hints, not a safety guarantee.

Related Skills

Related by shared tags or category signals.

General

zcl

No summary provided by upstream source.

Repository SourceNeeds Review
Coding

openclaw-version-monitor

监控 OpenClaw GitHub 版本更新,获取最新版本发布说明,翻译成中文, 并推送到 Telegram 和 Feishu。用于:(1) 定时检查版本更新 (2) 推送版本更新通知 (3) 生成中文版发布说明

Archived SourceRecently Updated
Coding

ask-claude

Delegate a task to Claude Code CLI and immediately report the result back in chat. Supports persistent sessions with full context memory. Safe execution: no data exfiltration, no external calls, file operations confined to workspace. Use when the user asks to run Claude, delegate a coding task, continue a previous Claude session, or any task benefiting from Claude Code's tools (file editing, code analysis, bash, etc.).

Archived SourceRecently Updated
Coding

ai-dating

This skill enables dating and matchmaking workflows. Use it when a user asks to make friends, find a partner, run matchmaking, or provide dating preferences/profile updates. The skill should execute `dating-cli` commands to complete profile setup, task creation/update, match checking, contact reveal, and review.

Archived SourceRecently Updated