Chalk Labs
Need help deploying stream-coding?
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/noobke-stream-coding
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/stream-coding
What's inside
- Skill name
stream-coding- Description
- 想要文档优先的开发方法论时使用 — Stream Coding:先写清楚再写代码,80% 时间花在文档上
- License
- MIT
- Instructions
- 51 lines in SKILL.md · view on GitHub
Agent Skills spec issues
- name: missing
Files (1)
- SKILL.md
SKILL.md (first lines)
# Stream Coding — 文档优先开发 **核心理念:** "当代码失败时,修复 spec——不是代码。" Stream Coding 是文档优先的方法论,让 AI 生成的代码具有确定性。 ## 时间分配 - **40%** 战略思考(Phase 1)— 写代码前解决难题 - **40%** AI 就绪文档(Phase 2)— Spec 写完整到 AI 零决策 - **5%** 对抗审查(Phase 2.5)— 不同 AI 攻击 spec - **10%** 执行(Phase 3)— 代码自动流出 - **5%** 质量(Phase 4)— 测试和验证 ## 五个阶段 ### Phase 1: 战略思考 回答 7 个问题: 1. 问题是什么? 2. 谁在用? 3. 成功标准是什么? 4. 有什么约束? 5. 有什么替代方案? 6. 最大风险是什么? 7. 最小可行方案是什么? ### Phase 2: AI 就绪文档 写确定性 spec: - 每个功能的精确行为 - 输入/输出类型 - 错误语义 - 边界情况 - **零歧义** — 两个开发者读同一份 spec 应该写出相同代码 ### Phase 2.5: 对抗审查 用不同 AI 攻击 spec,找到漏洞,修复后再写代码。 ### Phase 3: 执行 Spec → 代码。AI 按 spec 生成,不做决策。 ### Phase 4: 质量 - 验证 spec 中的每个需求 - 运行测试 - 手动抽查 ## 红线 **绝不在 spec 未完成时写代码。** **绝不手动修改代码而不更新 spec。**(会产生 Divergence — 技术债务)
From noobke/reasonix-skills, MIT.
More from noobke/reasonix-skills
- 0.504score
find-docs
noobke
需要任何库/框架/SDK 的最新文档时使用 — 用 Context7 CLI 拉取最新 API 参考和代码示例,不要靠训练数据
SkillCFreshness: C★ 3Claude Code +9 - 0.504score
planning-with-files
noobke
复杂多步骤任务时使用 — 用 task_plan.md + findings.md + progress.md 持久化追踪进度,不怕 /clear
SkillCFreshness: C★ 3Claude Code +9 - 0.504score
gh-fix-ci
noobke
GitHub Actions CI 失败时使用 — 用 gh CLI 检查 PR checks、拉日志、总结失败原因、生成修复方案
SkillCFreshness: C★ 3Claude Code +9 - 0.501score
frontend-design
noobke
需要高质量前端界面时使用 — 精致的排版、间距、动效。适合 Landing Page、App UI、Demo 原型
SkillCFreshness: C★ 3Claude Code +9 - 0.501score
get-api-docs
noobke
写第三方 API/SDK 集成代码前使用 — 用 chub CLI 获取最新的 API 文档,不要依赖训练数据
SkillCFreshness: C★ 3Claude Code +9 - 0.501score
git-worktrees
noobke
开始需要隔离的功能开发时使用 — 用 git worktree 创建隔离工作空间,保护当前分支
SkillCFreshness: C★ 3Claude Code +9 - 0.501score
agent-browser
noobke
需要浏览器自动化时使用 — 导航、填表、截图、抓取、端到端测试
SkillCFreshness: C★ 3Claude Code +9 - 0.501score
api-client-gen
noobke
需要从 OpenAPI spec 生成类型安全的 API 客户端时使用
SkillCFreshness: C★ 3Claude Code +9 - 0.501score
autoresearch
noobke
需要自主目标驱动迭代时使用 — 修改→验证→保留/丢弃的自动循环,支持多种模式
SkillCFreshness: C★ 3Claude Code +9 - 0.501score
brainstorming
noobke
写代码前先对齐需求 — 探索用户意图、约束和方案,产出设计文档后才开始实现
SkillCFreshness: C★ 3Claude Code +9 - 0.501score
doc-writer
noobke
需要从代码生成文档时使用 — 自动生成 API 文档、README 或模块说明
SkillCFreshness: C★ 3Claude Code +9 - 0.501score
executing-plans
noobke
有实施计划时使用 — 加载计划、批判性审阅、逐任务执行、完成时汇报
SkillCFreshness: C★ 3Claude Code +9
Signals
- Stars
- 3
- Forks
- 0
- Open issues
- 0
- Last commit (this folder)
- May 28, 2026 (5 months ago)
From GitHub (fetched Oct 24, 2026).
Details
- License
- MIT
- Repository
- github.com/noobke/reasonix-skills
- First seen
- Oct 24, 2026
- Last checked
- Oct 24, 2026
- Source
- GitHubgithub-graphql
More from noobke
- 0.504score
planning-with-files
noobke
复杂多步骤任务时使用 — 用 task_plan.md + findings.md + progress.md 持久化追踪进度,不怕 /clear
SkillCFreshness: C★ 3Claude Code +9 - 0.504score
gh-fix-ci
noobke
GitHub Actions CI 失败时使用 — 用 gh CLI 检查 PR checks、拉日志、总结失败原因、生成修复方案
SkillCFreshness: C★ 3Claude Code +9 - 0.504score
find-docs
noobke
需要任何库/框架/SDK 的最新文档时使用 — 用 Context7 CLI 拉取最新 API 参考和代码示例,不要靠训练数据
SkillCFreshness: C★ 3Claude Code +9 - 0.501score
db-migration
noobke
需要数据库迁移时使用 — 生成 migration 文件,含 up 和 down(回滚)
SkillCFreshness: C★ 3Claude Code +9 - 0.501score
get-api-docs
noobke
写第三方 API/SDK 集成代码前使用 — 用 chub CLI 获取最新的 API 文档,不要依赖训练数据
SkillCFreshness: C★ 3Claude Code +9 - 0.501score
frontend-design
noobke
需要高质量前端界面时使用 — 精致的排版、间距、动效。适合 Landing Page、App UI、Demo 原型
SkillCFreshness: C★ 3Claude 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 stream-coding 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
stream-coding skill. Agent Mart. https://agentmart.dev/skills/noobke-stream-coding (last updated 2026-10-24)