Zengxiansheng007
- 19 skills
- 0 followers
- 7 hours ago last updated
- ▌ UI Test · zengxiansheng007 bundlePlan, execute, review, repair, and stabilize Agent-driven Web UI tests using Codex orchestration, Midscene-first exploration, Playwright verification, Solution D evidence, failure attribution, governed execution-experience capture and Playwright/Hybrid regression assets. Use when the user asks to 运行或设计 UI 测试, 使用 Midscene/Playwright 测试真实页面, 分析 UI 测试失败, 生成测试报告, 沉淀或消费 checkpoint/UI 测试经验, 治理语义只读 POST, or 沉淀回归脚本.
- ▌ Research · zengxiansheng007 bundleRoute public research requests to official AnySearch by default or research-guided when the user explicitly selects Claude or Codex. Preserve research quality, pause immediately on non-quota AnySearch faults, and resume only on the user's instruction. Use when performing research, evidence gathering, and source-based comparisons.
- ▌ Write Prd · zengxiansheng007 bundleRoute business ideas and source materials into PRD, architecture design, development plan, or test plan skills with prerequisite checks, artifact state governance, RTM consistency, grill escalation, and change-impact reopening. Use when writing, reviewing, routing, or updating PRDs and delivery plans.
- ▌ Grill System · zengxiansheng007 bundleStress-test plans, requirements, test designs, implementation choices, risks, failures, and handoffs through a routed one-question-at-a-time grilling workflow. Use when the user asks to grill, challenge, harden, clarify, pre-review, premortem, design test cases, prepare implementation, diagnose why a plan failed, or decide whether work is ready for an agent.
- ▌ UI Test Plan · zengxiansheng007 bundleCreate and review UI-test planning packets from PRD, design, Figma, HTML prototype, live URL, code evidence, and knowledge base sources. Use for test-point decomposition, coverage matrix design, ambiguity discovery, automation candidate screening, and execution readiness before Midscene exploration.
- ▌ UI Test Review · zengxiansheng007 bundleReview UI automation execution quality after Midscene exploration, Playwright verification, and Solution D evidence collection. Use for classifying business defects versus test-asset issues, generating repair plans, deciding rerun scope, and promoting stable experience into Memory or regression scripts.
- ▌ UI Test Verify · zengxiansheng007 bundleConvert UI exploration results into deterministic Playwright verification and bounded fallback. Use when validating Midscene output, hardening recorded Playwright scripts, replacing weak locators, checking assertions, or deciding whether a UI flow can become a stable regression script.
- ▌ Domain Modeling · zengxiansheng007 bundleBuild and sharpen a project's domain model. Use when the user wants to pin down domain terminology or a ubiquitous language, record an architectural decision, or when another skill needs to maintain the domain model.
- ▌ Research Guided · zengxiansheng007 bundleUse when the research router selects this branch, the user explicitly chooses Claude or Codex, or invokes research-guided. Execute the preserved research workflow when the research router selects this branch, the user explicitly chooses Claude or Codex retrieval, or invokes research-guided. Default to Claude first except explicit Codex selection; generic research requests belong to the research router.
- ▌ UI Test Explore · zengxiansheng007 bundlePrepare and review Midscene-first UI exploration from a ui-test-packet. Use for semantic browser exploration, prompt packet shaping, weak locator discovery, visible-state observation, and preserving successful or failed exploration strategies before deterministic Playwright verification.
- ▌ UI Test Evidence · zengxiansheng007 bundleBuild Solution D evidence indexes for UI automation runs. Use for screenshots, JSON snapshots, API responses, contract checks, task-state polling, downstream validation, failure attribution, redaction policy, and Codex-readable evidence reports.
- ▌ Jmeter Tps Runner · zengxiansheng007 bundleRun an explicitly authorized existing JMeter JMX, search each HTTP request independently for the highest quality-qualified TPS within a confirmed concurrency range, and summarize all official reports. Use for repeated JMeter non-GUI load runs, bounded coarse/fine concurrency search, or per-request TPS reports. Never treat an example path as an execution target.
- ▌ Development System · zengxiansheng007 bundleReusable Codex development hub and top-level router. Use when Codex must turn a user goal into a requirement anchor, research-backed PRD, development plan, test plan, landed implementation review, RAG writeback, publish manifest, A2A handoff packet, Claude/Midscene execution review loop, or gap-to-requirement decision cycle.
- ▌ UI Test A2a Handoff · zengxiansheng007 bundleConvert ui-test-packet into a stable A2A-compatible handoff_packet, prompt_packet, and artifact_refs bundle for Codex to keep refining Midscene requests. Use when the user asks for a UI-test交接协议层, prompt转换层, packet to packet mapping, failure_history preservation, retry_history preservation, or artifact reference hygiene. Do not use for real A2A transport, browser execution, or checkpoint runtime.
- ▌ Write Requirements Prd · zengxiansheng007 bundleTurn business ideas, notes, rules, permissions, and source docs into a development-ready PRD with explicit scope, business rules, states, acceptance criteria, RTM, change governance, and grill-based ambiguity control. Use when creating, reviewing, or repairing a PRD from business sources.
- ▌ UI Test Execution Report · zengxiansheng007 bundleGenerate governed UI automation execution reports from step-scoped Midscene, Playwright, screenshot, API, and JSON evidence. Use when creating human HTML reports with screenshots and JSON embedded in the test-step table, plus Agent-readable evidence indexes and execution summaries.
- ▌ Handoff Feedback Reviewer · zengxiansheng007 bundleValidate Claude Code feedback packets for the handoff-system loop. Use when Codex receives Claude output and must classify untraced actions, requirement drift, risk gates, validation failures, loop limits, and completion readiness.
- ▌ UI Test Checkpoint Schema · zengxiansheng007 bundleValidate, bundle, and review UI-test checkpoint schema artifacts for staged exploration and reusable regression promotion. Use for stage 2.2 checkpoint packets, CP0-CP6 granularity, checkpoint evidence readiness, staleness policy, promotion gates, and checkpoint bundle validation.
- ▌ UI Test Checkpoint Runtime · zengxiansheng007 bundlePlan, validate, and execute R0/R1 read-only cross-session UI checkpoint recovery by system, module, and function button. Use when Codex needs to load a checkpoint registry, validate auth-reference freshness without exposing state, plan fresh current-session login/module/page/button recovery, produce a dry-run report, or perform explicitly approved public-site Playwright verification. Do not use for R2/R3 writes, private-site execution without approval, credential creation, or historical browser-state reuse.