菜单
Map a web UI and generate a Claude automation skill via parallel reconnaissance, synthesis, and iterative validation.
用 Codex 或 Claude 帮你安装 复制这段 Prompt，粘贴到 Codex、Claude 或其他助手里，让它检查 Skill 页面并帮你完成安装。
Release pipeline for already-done local work. Dispatches /ground-state pre-flight, runs the project test suite, drafts a commit message for user approval, pushes, and opens a PR with a structured verification summary. Use when local changes are ready to hand off to review — e.g. 'ship this', 'push and open a PR', 'release this work'. Add --verify to trigger an adversarial verifier wave on the diff before a human reads the PR.
Surface recurring friction from Claude Code's native telemetry and identify actionable skill opportunities. Use when the user runs /forge-friction.
Bootstraps a dispatchable Claude sub-agent skill for every coding agent CLI installed on this machine (codex, aider, cursor, etc.). Use when the user wants to delegate tasks to locally-installed agent CLIs or expand the plugin's agent fleet.
Set up a scheduled headless Claude run that sends summaries to Telegram. Use when the user wants to automate a recurring task via launchd (macOS) with push-notified results.
Reference convention for sub-agent I/O schemas. Loaded by orchestrator skills via /agent-workflow-amplifiers:contract and into agents (e.g., qualify) via the `skills:` field.
Before starting any non-trivial implementation (multi-file edits, new features, config changes, anything that writes), dispatch a parallel pre-flight reconnaissance wave to triangulate git state, project infrastructure, and prior-session memory. Produces a 5-line ground-truth snapshot that grounds the implementation and catches wrong-branch edits, assumed-no-CI, stale origin, and missed memory context before the first edit.
基于 SOC 职业分类
| name | appmap |
| description | Map a web UI and generate a Claude automation skill via parallel reconnaissance, synthesis, and iterative validation. |
| argument-hint | <URL or app description> |
!awk '/^---$/{c++; next} c>=2' "${CLAUDE_SKILL_DIR}/../contract/SKILL.md"
Wave 1 (parallel): Dispatch two sub-agents. One maps the $ARGUMENT UI in Chrome: navigation structure, key pages/forms, interaction patterns, CSS selectors, and automatable workflows. The other researches $ARGUMENT's public API, docs, authentication, rate limits, and architectural patterns. Both return structured findings.
Synthesis: Merge Wave 1 outputs into a skill plan: list of automatable workflows (with interaction patterns and selectors), recommended API calls to supplement UI workflows, and implementation priorities.
Wave 2 (parallel): For each top-priority workflow, dispatch a sub-agent to implement it in the generated skill and unit-test it against the live UI. Agents operate in isolated tabs and return pass/fail results per workflow.
Verification: One final sub-agent runs the complete generated skill end-to-end against $ARGUMENT, validating all workflows together. If any workflow fails, re-dispatch failing workflow agents in Wave 2 and re-verify (max 2 retries; after that, report partial results with failing workflows noted).
