dag-best-practices
HomeRail DAG review and execution best practices.
Skill by xiaotianfotos
Chalk Labs
Need help deploying dag-best-practices?
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/xiaotianfotos-dag-best-practices
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: agent-building
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/dag-best-practices
What's inside
- Skill name
dag-best-practices- Description
- HomeRail DAG review and execution best practices. Use when designing, running, or reviewing HomeRail fan-out/fan-in DAGs, especially model-backed DAG audits, environment checks, and agent handoff evidence.
- License
- MIT
- Instructions
- 46 lines in SKILL.md · view on GitHub
Files (1)
- SKILL.md
SKILL.md (first lines)
# HomeRail DAG 最佳实践 一句话原则:先统一事实,再分头检查,最后只按证据下结论。 ## DO - 先建立唯一事实源。用 seed 节点拿到代码、版本、输入参数和外部证据,再把同一份事实交给所有下游节点。 - 让每个节点只回答一个清晰问题,例如源码是否干净、构建是否通过、运行时是否健康、数据是否保留。 - 让节点真的检查事实。该跑命令就跑命令,该读文件就读文件,该查 API 就查 API,不要只复述提示词。 - 让节点输出结构化 handoff。至少包含结论、证据、缺口、阻塞原因;失败时给出可行动的修复方向。 - 让 fan-in 节点只做裁决。它可以汇总和判断,但不应该重新做所有检查,也不应该替上游补证据。 - 把 hard gate 和 advisory 分开。必须通过的检查失败就阻塞;参考意见只能提示风险,不能替代证据。 - 把运行环境差异当成默认存在。宿主机、容器、本地、远端、CI 看到的路径、网络、权限、工具链可能都不同。 - 把会改变运行时的动作放在 DAG 外或明确隔离。部署、迁移、重启服务这类动作不要破坏正在执行 DAG 的基础设施。 - 给长期状态留 baseline。涉及升级、迁移、用户数据、配置和历史记录时,先记录基准,再用后续运行对比。 - 留下可复查的证据。每次运行都应该能回答:看了什么、跑了什么、结果是什么、为什么通过或阻塞。 - 用小 smoke 验证流程,用真实任务验证能力。快速 smoke 证明线路能通,真实模型和真实命令才证明任务完成质量。 - 使用执行环境真的能访问的地址、路径和凭证。给容器节点的输入,要从容器视角验证可用。 ## DO NOT - 不要让节点各自使用不同事实源。版本不一致时,后面的汇总没有意义。 - 不要把模糊自然语言当成节点间协议。节点间传递要用结构化字段,不要靠读聊天猜含义。 - 不要让一个节点承担太多职责。职责越混,失败原因越难定位。 - 不要把没输出结果的节点算作成功。没有 handoff 就是缺证据。 - 不要自动补 handoff 后继续判通过。自动补只能说明节点没有按契约完成。 - 不要让 fan-in 节点靠感觉补全缺失信息。缺少证据就阻塞,而不是猜测通过。 - 不要把参考意见当成硬结论。LLM review、人工建议、摘要和 smoke 都不能替代 hard gate 的实际证据。 - 不要把快速跑通说成完整完成。smoke 是线路检查,不是质量证明。 - 不要默认所有环境都一样。宿主机能访问,不代表容器能访问;本机能跑,不代表 CI 能跑。 - 不要只保存最终结论,不保存过程证据。没有过程,结论无法复查。 - 不要隐藏不确定性。没查到、没权限、环境不可达、证据不足,都应该明确写进结果。 - 不要把 token、本机路径、私有地址、临时目录写死在可复用模板里。需要这些值时,通过运行参数或环境配置传入。 ## 快速检查 - 有没有唯一事实源? - 每个节点的问题是否足够单一? - 每个节点是否会产生结构化 handoff? - fan-in 是否只基于 handoff 和 evidence 下结论? - hard gate 和 advisory 是否分清? - smoke 和真实验证是否分清? - 运行环境的网络、路径、权限是否从执行节点视角验证过? - 失败时是否能直接看出原因和下一步?
From xiaotianfotos/homerail, MIT.
More from xiaotianfotos/homerail
- 0.779score
homerail-dag-ops
xiaotianfotos
Design, start, supervise, inspect, and continue HomeRail DAG workflows from any agent with CLI or HTTP access.
SkillBFreshness: B★ 998Claude Code +9 - 0.774score
homerail-pr-review
xiaotianfotos
Run HomeRail's built-in read-only pull request review DAG.
SkillBFreshness: B★ 998Claude Code +9 - 0.774score
homerail-install-ops
xiaotianfotos
Install, configure, start, verify, update, and troubleshoot a local-source HomeRail deployment for AI-agent use.
SkillBFreshness: B★ 998Claude Code +9 - 0.769score
homerail-cli
xiaotianfotos
HomeRail CLI syntax, flags, configuration, and command reference.
SkillBFreshness: B★ 998Claude Code +9 - 0.764score
homerail-dag-patterns
xiaotianfotos
Compatibility entry for callers that already refer to HomeRail DAG Patterns.
SkillBFreshness: B★ 998Claude Code +9 - 0.716score
homerail-shared
xiaotianfotos
Shared HomeRail rules for AI agents operating the local-source release candidate: service roles, environment variables, secrets, provider boundaries, Docker…
SkillCFreshness: C★ 998Claude Code +9 - 0.713score
homerail-pr-closeout
xiaotianfotos
Determine whether a GitHub pull request can leave Draft or is ready for its owner to merge, using immutable validation, review, CI, dependency, and approval…
SkillCFreshness: C★ 998Claude Code +9 - 0.709score
pr-closeout
xiaotianfotos
Present an evidence-grounded pull request closeout decision after review, CI, or real-machine validation.
SkillCFreshness: C★ 998Claude Code +9 - 0.708score
voice-generative-ui
xiaotianfotos
Design and maintain truthful HomeRail generative UI for voice or text.
SkillCFreshness: C★ 998Claude Code +9 - 0.707score
topic-outline
xiaotianfotos
Create and revise a structured topic outline from an evolving brief, audience, angle, thesis, sections, questions, and sources.
SkillCFreshness: C★ 998Claude Code +9 - 0.704score
generate-video-cover
xiaotianfotos
Generate a video cover through the sandboxed GPU runtime and Manager Artifact Broker.
SkillCFreshness: C★ 998Claude Code +9 - 0.704score
compose-release-notes
xiaotianfotos
Create or replace a complete semantic release-notes snapshot.
SkillCFreshness: C★ 998Claude Code +9
Signals
- Stars
- 998
- Forks
- 226
- Open issues
- 19
- Last commit (this folder)
- Jul 7, 2026 (4 months ago)
From GitHub (fetched Oct 24, 2026).
Details
- License
- MIT
- Repository
- github.com/xiaotianfotos/homerail
- First seen
- Oct 24, 2026
- Last checked
- Oct 24, 2026
- Source
- GitHubgithub-graphql
More from xiaotianfotos
- 0.779score
homerail-dag-ops
xiaotianfotos
Design, start, supervise, inspect, and continue HomeRail DAG workflows from any agent with CLI or HTTP access.
SkillBFreshness: B★ 998Claude Code +9 - 0.774score
homerail-pr-review
xiaotianfotos
Run HomeRail's built-in read-only pull request review DAG.
SkillBFreshness: B★ 998Claude Code +9 - 0.774score
homerail-install-ops
xiaotianfotos
Install, configure, start, verify, update, and troubleshoot a local-source HomeRail deployment for AI-agent use.
SkillBFreshness: B★ 998Claude Code +9 - 0.769score
homerail-cli
xiaotianfotos
HomeRail CLI syntax, flags, configuration, and command reference.
SkillBFreshness: B★ 998Claude Code +9 - 0.764score
homerail-dag-patterns
xiaotianfotos
Compatibility entry for callers that already refer to HomeRail DAG Patterns.
SkillBFreshness: B★ 998Claude Code +9 - 0.716score
homerail-shared
xiaotianfotos
Shared HomeRail rules for AI agents operating the local-source release candidate: service roles, environment variables, secrets, provider boundaries, Docker…
SkillCFreshness: C★ 998Claude 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 dag-best-practices 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
dag-best-practices skill. Agent Mart. https://agentmart.dev/skills/xiaotianfotos-dag-best-practices (last updated 2026-10-24)