manual-gates
按《个人AI项目执行手册》（7阶段27节点、规模自适应三轨）驱动开发节奏：在 AI 项目开发、写代码、做功能、冲刺规划、节点验收、阶段评审时使用。触发词包括"边开发边检查""按手册执行""节点验收""阶段门禁""plan_next""gate_report""set_mode""快速轨""开发前先看验收标准"以及任何…
Skill by liulanghan2100
Chalk Labs
Need help deploying manual-gates?
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/liulanghan2100-manual-gates
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: design, testing, 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
- Runs as
- Python package
Network hosts it talks to 1
codeload.github.com· found in install command
Files it touches
~/.claude/skills/manual-gates
What's inside
- Skill name
manual-gates- Description
- 按《个人AI项目执行手册》（7阶段27节点、规模自适应三轨）驱动开发节奏：在 AI 项目开发、写代码、做功能、冲刺规划、节点验收、阶段评审时使用。触发词包括"边开发边检查""按手册执行""节点验收""阶段门禁""plan_next""gate_report""set_mode""快速轨""开发前先看验收标准"以及任何围绕该手册节点的规划/检查/复盘请求。通过 7 个分工 MCP（strategy/design/data_ai/planning/dev/qa/ops）完成规划、验收与门禁判断，让开发始终带着验收标准进行。
- License
- unknown
- Instructions
- 297 lines in SKILL.md · view on GitHub
Before installing
- Ships executable scripts
Files (16)
- SKILL.md
- gate.py · scripts/
- README.md · scripts/manual_mcp/
- __init__.py · scripts/manual_mcp/
- common.py · scripts/manual_mcp/
- learned.json · scripts/manual_mcp/
- learning.py · scripts/manual_mcp/
- manual_data.py · scripts/manual_mcp/
- run_data_ai.py · scripts/manual_mcp/
- run_design.py · scripts/manual_mcp/
- run_dev.py · scripts/manual_mcp/
- run_ops.py · scripts/manual_mcp/
- run_planning.py · scripts/manual_mcp/
- run_qa.py · scripts/manual_mcp/
- run_strategy.py · scripts/manual_mcp/
- state.py · scripts/manual_mcp/
The license isn't open source, so the instructions aren't shown here. Read SKILL.md on GitHub
More from liulanghan2100/sundhsunny
- 0.524score
offline-upgrade
liulanghan2100
Run and manage the user's local offline Agent upgrade lane.
SkillBFreshness: BClaude Code +9 - 0.524score
industrial-expert-dev
liulanghan2100
Industrial automation software expert workflow for PLC, HMI, barcode scanner, machine vision, marking/printing, MES traceability, device communication…
SkillBFreshness: BClaude Code +9 - 0.524score
knowledge-base
liulanghan2100
Manage and query the user's local personal Agent knowledge base.
SkillBFreshness: BClaude Code +9 - 0.524score
campaign-plan
liulanghan2100
Generate a full campaign brief with objectives, audience, messaging, channel strategy, content calendar, and success metrics.
SkillBFreshness: BClaude Code +9 - 0.519score
canvas
liulanghan2100
Use when creating, reading, updating, or deleting Daimon Blueprint Canvases and when placing, moving, resizing, ordering, removing, or inspecting Widget…
SkillBFreshness: BClaude Code +9 - 0.519score
binding
liulanghan2100
Use when creating, reading, validating, repairing, deleting, or troubleshooting Daimon Blueprint automation_widget Bindings between Automation artifact…
SkillBFreshness: BClaude Code +9 - 0.519score
blueprint
liulanghan2100
Use when choosing between Daimon Blueprint Automation, Widget, Binding, and Canvas tools or routing a request to the correct Blueprint domain skill.
SkillBFreshness: BClaude Code +9 - 0.519score
bug-intake
liulanghan2100
Convert scan findings, review failures, intake gaps, user bug reports, or failed acceptance checks into structured bug tickets with severity, reproduction…
SkillBFreshness: BClaude Code +9 - 0.519score
cangjie-thinking-distiller
liulanghan2100
Distill a person's real decision samples into a reusable, testable, and feedback-driven thinking protocol.
SkillBFreshness: BClaude Code +9 - 0.519score
automation
liulanghan2100
Use when creating, reading, updating, deleting, running, cancelling, scheduling, condition-triggering, or inspecting Daimon Blueprint Automations and their…
SkillBFreshness: BClaude Code +9 - 0.516score
nuwa-runbook
liulanghan2100
女娲蒸馏产线适配版——把一个思维对象（方法论/框架/领域知识）按门禁流程蒸馏成可调用的 SKILL.md。当用户说「蒸馏XX」「把XX做成skill」「女娲」时触发。全程强制走 manual-gates 27 节点门禁，调研不落盘等于没做，一手信源占比不达标则诚实降级。
SkillBFreshness: BClaude Code +9 - 0.516score
darwin-runbook
liulanghan2100
达尔文进化循环适配版——对已有 SKILL.md 做评估-变异-选择的受控进化。当用户说「评估XX skill」「优化XX skill」「达尔文」时触发。9维rubric做triage，keep/revert走paired多数决，每轮只改一个维度，仅owner可触发，绝不自评自改。
SkillBFreshness: BClaude Code +9
Signals
- Stars
- 0
- Forks
- 0
- Open issues
- 0
- Last commit (this folder)
- Sep 16, 2026 (1 month ago)
From GitHub (fetched Oct 24, 2026).
Details
- License
- License unknown
- Repository
- github.com/liulanghan2100/sundhsunny
- First seen
- Oct 24, 2026
- Last checked
- Oct 24, 2026
- Source
- GitHubgithub-graphql
More from liulanghan2100
- 0.524score
offline-upgrade
liulanghan2100
Run and manage the user's local offline Agent upgrade lane.
SkillBFreshness: BClaude Code +9 - 0.524score
campaign-plan
liulanghan2100
Generate a full campaign brief with objectives, audience, messaging, channel strategy, content calendar, and success metrics.
SkillBFreshness: BClaude Code +9 - 0.524score
knowledge-base
liulanghan2100
Manage and query the user's local personal Agent knowledge base.
SkillBFreshness: BClaude Code +9 - 0.524score
industrial-expert-dev
liulanghan2100
Industrial automation software expert workflow for PLC, HMI, barcode scanner, machine vision, marking/printing, MES traceability, device communication…
SkillBFreshness: BClaude Code +9 - 0.519score
binding
liulanghan2100
Use when creating, reading, validating, repairing, deleting, or troubleshooting Daimon Blueprint automation_widget Bindings between Automation artifact…
SkillBFreshness: BClaude Code +9 - 0.519score
automation
liulanghan2100
Use when creating, reading, updating, deleting, running, cancelling, scheduling, condition-triggering, or inspecting Daimon Blueprint Automations and their…
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 manual-gates 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
manual-gates skill. Agent Mart. https://agentmart.dev/skills/liulanghan2100-manual-gates (last updated 2026-10-24)