Chalk Labs
Need help deploying team-assemble?
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/sswym-team-assemble
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
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/team-assemble
What's inside
- Skill name
team-assemble- Description
- 动态组装适合任务的智能体团队,请求批准,然后执行分阶段生命周期。
- License
- MIT
- Instructions
- 49 lines in SKILL.md · view on GitHub
Files (1)
- SKILL.md
SKILL.md (first lines)
## 目的 当固定的仅工程团队不足且名册应适应任务形状时,使用此技能。 ## 触发条件 - 用户要求"作为一个团队来做" - 任务混合领域(例如研究 + 实现 + 报告) - 团队组成和模型预算必须在执行之前明确 ## 工作流程 1. 分析任务形状(领域、输出目标、风险姿态)。 2. 分别选择领域专家和格式专家。 3. 当广度高时生成并行研究通道(`oma-researcher` xN)。 4. 分配决策通道(`oma-consultant` 或 `oma-architect`)和质量通道(`oma-reviewer`、`oma-verifier`、`oma-debugger`)。 5. 按角色分配模型配置文件: - 判断/门控:`glm-5` - 实现密集型:`glm-4.7` - 广泛的低风险探索:`glm-4.7` 6. 请求批准门控:"继续使用此团队?(yes/no)"。 7. 获得批准后,运行带有明确交接的分阶段管道(`team-plan -> team-prd -> team-exec -> team-verify -> team-fix`)。 ## 输出模板 ```markdown ## 团队适应性分析 - ... ## 提议的团队 | 角色 | 智能体 | 原因 | 模型 | 通道 | | --- | --- | --- | --- | --- | ## 协作协议 - ... ## 批准门控 - 检测到批准: - 提示: ## 执行摘要(仅在批准时) - ... ``` ## 注意事项 - 保持角色分配最小化并解释每个角色存在的原因。 - 倾向于明确的验证/修复触发器而不是模糊的质量声明。
From sswym/oh-my-agent, MIT.
More from sswym/oh-my-agent
- 0.509score
team
sswym
在子智能体之间协调完整的 oma 阶段管道,用于复杂交付(plan -> prd -> exec -> verify -> fix)。
SkillDFreshness: D★ 75Claude Code +9 - 0.506score
rules
sswym
根据任务信号注入条件性规则包(测试、迁移、安全、文档、性能)。
SkillDFreshness: D★ 75Claude Code +9 - 0.506score
doctor
sswym
运行 oma 就绪性诊断,检查命令、技能、状态文件和团队/钩子安全姿态。
SkillDFreshness: D★ 75Claude Code +9 - 0.506score
hooks
sswym
操作 oma 的扩展原生钩子管道,具有确定性触发器、安全门控和效率预算。
SkillDFreshness: D★ 75Claude Code +9 - 0.506score
intent
sswym
在执行开始前分类用户意图并将工作路由到正确的 oma 阶段。
SkillDFreshness: D★ 75Claude Code +9 - 0.506score
loop
sswym
强制执行重复的执行-验证-修复循环,直到验收标准通过或阻塞问题明确。
SkillDFreshness: D★ 75Claude Code +9 - 0.506score
memory
sswym
使用 MEMORY.md 索引、主题文件和模块化规则包管理持久化项目内存。
SkillDFreshness: D★ 75Claude Code +9 - 0.506score
mode
sswym
检查或切换 oma 操作模式/配置文件以调整速度、深度、自主性或严格质量门控。
SkillDFreshness: D★ 75Claude Code +9 - 0.506score
prd
sswym
将请求转换为 PRD 级别的范围、可衡量的验收标准和交付约束。
SkillDFreshness: D★ 75Claude Code +9 - 0.506score
ralplan
sswym
创建严格的、质量优先的执行计划,具有明确的门控和可回滚的排序。
SkillDFreshness: D★ 75Claude Code +9 - 0.506score
reasoning
sswym
控制 oma 推理努力水平以平衡深度、严谨性、延迟和令牌成本。
SkillDFreshness: D★ 75Claude Code +9 - 0.506score
deep-init
sswym
使用深度仓库映射、验证钩子和风险热点初始化长时间会话上下文。
SkillDFreshness: D★ 75Claude Code +9
Signals
- Stars
- 75
- Forks
- 13
- Open issues
- 1
- Last commit (this folder)
- Apr 12, 2026 (6 months ago)
From GitHub (fetched Oct 24, 2026).
Details
- License
- MIT
- Repository
- github.com/sswym/oh-my-agent
- First seen
- Oct 24, 2026
- Last checked
- Oct 24, 2026
- Source
- GitHubgithub-graphql
More from sswym
- 0.509score
team
sswym
在子智能体之间协调完整的 oma 阶段管道,用于复杂交付(plan -> prd -> exec -> verify -> fix)。
SkillDFreshness: D★ 75Claude Code +9 - 0.506score
deep-init
sswym
使用深度仓库映射、验证钩子和风险热点初始化长时间会话上下文。
SkillDFreshness: D★ 75Claude Code +9 - 0.506score
approval
sswym
设置 oma 批准姿态(`suggest`、`auto`、`full-auto`)并带有明确的风险护栏。
SkillDFreshness: D★ 75Claude Code +9 - 0.506score
hud
sswym
控制 oma 可视化 HUD 配置文件,并在正常、紧凑或隐藏模式下保持状态输出可读。
SkillDFreshness: D★ 75Claude Code +9 - 0.506score
doctor
sswym
运行 oma 就绪性诊断,检查命令、技能、状态文件和团队/钩子安全姿态。
SkillDFreshness: D★ 75Claude Code +9 - 0.506score
hooks
sswym
操作 oma 的扩展原生钩子管道,具有确定性触发器、安全门控和效率预算。
SkillDFreshness: D★ 75Claude 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 team-assemble 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
team-assemble skill. Agent Mart. https://agentmart.dev/skills/sswym-team-assemble (last updated 2026-10-24)