Chalk Labs
Need help deploying deployment-test?
Chalk Labs sets up agents like this inside real teams: connected to your tools, tested on your data, with a human in the loop where it matters.
Install
Works with Claude Code, Claude apps, Codex, Cursor, Gemini CLI, GitHub Copilot, VS Code, OpenCode, Goose, Windsurf. Read the repository before you give any tool access to your data.
npx agentmarket install skill/xx-trader-deployment-test
Asks which of your tools to add it to (Claude Code, Codex, Cursor, VS Code, Windsurf, Gemini CLI, Claude Desktop) and shows the change first. See https://agentmart.dev/cli.
Get the weekly diff
The weekly diff: one email a week with new agent tools, notable updates and grade changes, plus security alerts for tools you follow. Double opt-in, one-click unsubscribe.
About
Use cases: testing
Reviews
Write a reviewNo reviews yet. Installed it? Reviews come from verified installers only. How reviews work
Permissions
What this skill can do and what it asks for, from its SKILL.md. Checked Oct 25, 2026.
- Tools
- No tools found
- Secrets
- None asked for
- Install scripts
- None found
Network hosts it talks to 1
codeload.github.com· found in install command
Files it touches
~/.claude/skills/deployment-test
What's inside
- Skill name
deployment-test- Description
- 兼容入口：使用项目注入的验证命令和验收断言检查已部署版本
- License
- MIT
- Instructions
- 22 lines in SKILL.md · view on GitHub
Files (1)
- SKILL.md
SKILL.md (first lines)
# 部署后验收 本 Skill 保留 `deployment-test` 名称供控制面能力绑定使用，实际验证统一进入 [project-delivery-pipeline](../project-delivery-pipeline/SKILL.md) 的验证和部署验收阶段。 ## 验收矩阵 | 层级 | 项目提供的输入 | 最低证据 | | --- | --- | --- | | 进程或容器 | 状态命令 | 目标实例与版本一致 | | 接口 | 请求命令与断言 | 状态、结构和关键字段符合契约 | | 页面 | 浏览器测试命令 | 真实交互断言和失败截图 | | 数据 | 只读核对命令 | 写入、读取或迁移结果符合项目约束 | | 回滚 | 回滚命令与复验 | 旧版本恢复且健康检查通过 | ## 规则 - 不预设服务、端口、接口、账号或页面选择器。 - 不使用模拟 UI 结果替代浏览器执行证据。 - 测试账号和密钥只从目标环境的 Secret Store 注入。 - 任一必选断言失败时，结果保持失败并返回对应阶段。
From XX-Trader/openclaw-hardflow-backup-20260302, MIT.
More from XX-Trader/openclaw-hardflow-backup-20260302
- 0.524score
engineering-cybernetics-experience-loop
XX-Trader
Use when any runtime-host Hermes agent consolidates work experience under Qian Xuesen's Engineering Cybernetics standard: store only bottom-level logic in…
SkillBFreshness: BClaude Code +9 - 0.523score
config-watchdog
XX-Trader
配置变更安全兜底技能。用于定期快照 OpenClaw 配置文件、 检测意外变更、JSON 格式校验、必要时自动回滚。 当怀疑配置被意外修改或 JSON 损坏时使用。
SkillBFreshness: BClaude Code +9 - 0.522score
cross-runtime-memory-distiller
XX-Trader
Hermes / OpenClaw 共用的跨宿主记忆蒸馏技能。 从 Claude / Gemini / OpenClaw / Hermes 多源会话中提取归一化事件， 经清洗、打分、分类后写入热记忆（USER.md / MEMORY.md）， 同时产出蒸馏报告、控制面桥接记录和技能候选草稿。
SkillBFreshness: BClaude Code +9 - 0.521score
api-registry-manager
XX-Trader
API 注册表管理 Skill。负责项目外部 API 和来源的注册、查询、更新、删除。 每个项目维护独立的 API_REGISTRY.json 和 SOURCE_REGISTRY.json， 记录第三方依赖的接口定义、文档地址、版本信息。 是 project-agent 的核心组件之一，也是 API watch…
SkillBFreshness: BClaude Code +9 - 0.520score
control-plane-ops
XX-Trader
通用控制面巡检技能，用于 Task Center、Cron、调度注册表、运行快照和故障恢复。
SkillBFreshness: BClaude Code +9 - 0.518score
failure-learning
XX-Trader
失败学习回写 Skill。当模型反复失败时，分析根因、检索外部方案、 回写到需求/方案/模型执行规约文档，形成闭环纠偏。 核心约束：失败学习触发后，一定要与人沟通，不允许 AI 自行闷头解决。
SkillBFreshness: BClaude Code +9 - 0.515score
db-deploy
XX-Trader
兼容入口：按目标项目提供的部署、烟测和回滚命令执行交付流水线部署阶段
SkillBFreshness: BClaude Code +9 - 0.515score
auto-fix
XX-Trader
兼容入口：将缺陷复现、隔离修改、验证、审查和可选发布交给通用项目交付流水线
SkillBFreshness: BClaude Code +9 - 0.512score
feature-development
XX-Trader
兼容入口：按目标仓库契约完成需求、方案、实现、验证和审查
SkillBFreshness: BClaude Code +9 - 0.487score
agent-manager
XX-Trader
agent-manager 技能
SkillBFreshness: BClaude Code +9 - 0.411score
dual-ai-review
XX-Trader
双 AI 对抗式审查 Skill。用于需求审查、方案审查、代码审查三个阶段， 强制要求 2 个不同模型的 AI 互相探讨、互相质疑，产出联合审查结论。 不是单 AI 走过场，而是通过对抗发现单模型盲点。 当 coordinator 需要审查需求/方案/代码时，必须按此 Skill 执行。
SkillDFreshness: DClaude Code +9 - 0.401score
deepdive-lite
XX-Trader
用于规划者的轻量深度思考流程。复杂问题触发，低风险任务直达执行，控制 token 与时延。
SkillDFreshness: DClaude Code +9
Signals
- Stars
- 0
- Forks
- 0
- Open issues
- 0
- Last commit (this folder)
- Aug 14, 2026 (2 months ago)
From GitHub (fetched Oct 24, 2026).
Details
- License
- MIT
- First seen
- Oct 24, 2026
- Last checked
- Oct 24, 2026
- Source
- GitHubgithub-graphql
More from XX-Trader
- 0.524score
engineering-cybernetics-experience-loop
XX-Trader
Use when any runtime-host Hermes agent consolidates work experience under Qian Xuesen's Engineering Cybernetics standard: store only bottom-level logic in…
SkillBFreshness: BClaude Code +9 - 0.523score
config-watchdog
XX-Trader
配置变更安全兜底技能。用于定期快照 OpenClaw 配置文件、 检测意外变更、JSON 格式校验、必要时自动回滚。 当怀疑配置被意外修改或 JSON 损坏时使用。
SkillBFreshness: BClaude Code +9 - 0.522score
cross-runtime-memory-distiller
XX-Trader
Hermes / OpenClaw 共用的跨宿主记忆蒸馏技能。 从 Claude / Gemini / OpenClaw / Hermes 多源会话中提取归一化事件， 经清洗、打分、分类后写入热记忆（USER.md / MEMORY.md）， 同时产出蒸馏报告、控制面桥接记录和技能候选草稿。
SkillBFreshness: BClaude Code +9 - 0.521score
api-registry-manager
XX-Trader
API 注册表管理 Skill。负责项目外部 API 和来源的注册、查询、更新、删除。 每个项目维护独立的 API_REGISTRY.json 和 SOURCE_REGISTRY.json， 记录第三方依赖的接口定义、文档地址、版本信息。 是 project-agent 的核心组件之一，也是 API watch…
SkillBFreshness: BClaude Code +9 - 0.520score
control-plane-ops
XX-Trader
通用控制面巡检技能，用于 Task Center、Cron、调度注册表、运行快照和故障恢复。
SkillBFreshness: BClaude Code +9 - 0.518score
failure-learning
XX-Trader
失败学习回写 Skill。当模型反复失败时，分析根因、检索外部方案、 回写到需求/方案/模型执行规约文档，形成闭环纠偏。 核心约束：失败学习触发后，一定要与人沟通，不允许 AI 自行闷头解决。
SkillBFreshness: BClaude Code +9
Done for you
Rather not set it up yourself?
Chalk Labs scopes, builds and runs agents for your team: the task audit, the eval harness, the integrations and the weekly ops report. Fixed scope, priced before we start.
See how we build AI agents →Read the case studies
Chalk Labs is a two-founder AI and growth studio. We build AI agents, CRMs and MVPs for Web3 and AI companies, and have shipped 50+ product and token launches.
- launches shipped
- 50+
- launches shipped
- media placements
- 500+
- media placements
- founders on every account
- 2
- founders on every account
Press we've placed: Forbes · CoinDesk · Decrypt · Cointelegraph · The Block
Rahil Jain, Co-founder, Chalk Labs. Ex-Goldman Sachs engineer. You talk to the person who builds it.
Get deployment-test running in your business
Tell us what you want to automate. A founder replies within one working day with a plan, not a pitch deck.
Cite this page
deployment-test skill. Agent Mart. https://agentmart.dev/skills/xx-trader-deployment-test (last updated 2026-10-24)