ai-board-sync — ai-agents ai-board-sync, ai-engineering, community, ai-agents, ide skills, claude-code, developer-tools, devsecops, github-copilot, Claude Code, Cursor

v1.0.0

关于此技能

Turn any repo into a governed AI workspace. Quality gates, security scanning, and risk management — enforced locally via git hooks. Works with Claude Code, GitHub Copilot, Cursor, Gemini & Codex.

# 核心主题

arcasilesgroup arcasilesgroup
[4]
[0]
更新于: 4/14/2026

Killer-Skills Review

Decision support comes first. Repository text comes second.

Reference-Only Page Review Score: 3/11

This page remains useful for operators, but Killer-Skills treats it as reference material instead of a primary organic landing page.

Quality floor passed for review
Review Score
3/11
Quality Score
56
Canonical Locale
en
Detected Body Locale
en

Turn any repo into a governed AI workspace. Quality gates, security scanning, and risk management — enforced locally via git hooks. Works with Claude Code, GitHub Copilot, Cursor, Gemini & Codex.

核心价值

Turn any repo into a governed AI workspace. Quality gates, security scanning, and risk management — enforced locally via git hooks. Works with Claude Code, GitHub Copilot, Cursor, Gemini & Codex.

适用 Agent 类型

Suitable for operator workflows that need explicit guardrails before installation and execution.

赋予的主要能力 · ai-board-sync

! 使用限制与门槛

Why this page is reference-only

  • - Current locale does not satisfy the locale-governance contract.
  • - The page lacks a strong recommendation layer.
  • - The page lacks concrete use-case guidance.
  • - The page lacks explicit limitations or caution signals.

Source Boundary

The section below is supporting source material from the upstream repository. Use the Killer-Skills review above as the primary decision layer.

实验室 Demo

Browser Sandbox Environment

⚡️ Ready to unleash?

Experience this Agent in a zero-setup browser environment powered by WebContainers. No installation required.

Boot Container Sandbox

常见问题与安装步骤

以下问题与步骤与页面结构化数据保持一致,便于搜索引擎理解页面内容。

? FAQ

ai-board-sync 是什么?

Turn any repo into a governed AI workspace. Quality gates, security scanning, and risk management — enforced locally via git hooks. Works with Claude Code, GitHub Copilot, Cursor, Gemini & Codex.

如何安装 ai-board-sync?

运行命令:npx killer-skills add arcasilesgroup/ai-engineering/ai-board-sync。支持 Cursor、Windsurf、VS Code、Claude Code 等 19+ IDE/Agent。

ai-board-sync 支持哪些 IDE 或 Agent?

该技能兼容 Cursor, Windsurf, VS Code, Trae, Claude Code, OpenClaw, Aider, Codex, OpenCode, Goose, Cline, Roo Code, Kiro, Augment Code, Continue, GitHub Copilot, Sourcegraph Cody, and Amazon Q Developer。可使用 Killer-Skills CLI 一条命令通用安装。

安装步骤

  1. 1. 打开终端

    在你的项目目录中打开终端或命令行。

  2. 2. 执行安装命令

    运行:npx killer-skills add arcasilesgroup/ai-engineering/ai-board-sync。CLI 会自动识别 IDE 或 AI Agent 并完成配置。

  3. 3. 开始使用技能

    ai-board-sync 已启用,可立即在当前项目中调用。

! 参考页模式

此页面仍可作为安装与查阅参考,但 Killer-Skills 不再把它视为主要可索引落地页。请优先阅读上方评审结论,再决定是否继续查看上游仓库说明。

Imported Repository Instructions

The section below is supporting source material from the upstream repository. Use the Killer-Skills review above as the primary decision layer.

Supporting Evidence

ai-board-sync

安装 ai-board-sync,这是一款面向AI agent workflows and automation的 AI Agent Skill。支持 Claude Code、Cursor、Windsurf,一键安装。

SKILL.md
Readonly
Imported Repository Instructions
The section below is supporting source material from the upstream repository. Use the Killer-Skills review above as the primary decision layer.
Supporting Evidence

Board Sync

Purpose

Updates work item state on the project board at each lifecycle transition. Called internally by other skills (ai-brainstorm, ai-dispatch, ai-pr) and by provider-side runbooks when they need to move an item through the configured lifecycle. Fail-open: never blocks the calling skill's workflow.

When to Use

  • Called automatically by /ai-brainstorm (refinement, ready transitions)
  • Called automatically by /ai-dispatch (in_progress transition)
  • Called automatically by /ai-pr (in_review transition)
  • Manual override: /ai-board-sync <phase> <ref>

Inputs

ParameterRequiredDescription
phaseYesLifecycle phase: refinement, ready, in_progress, in_review, done
work-item-refYesWork item reference: #45 (GitHub issue) or AB#100 (ADO)
--commentNoComment to add to the work item (e.g., spec reference, PR URL). The --comment parameter is optional. "Context available" means the calling skill provides a spec URL, PR URL, or status summary in its invocation payload.

Process

  1. Read config -- read .ai-engineering/manifest.yml work_items section:

    • provider -- determines which CLI to use
    • state_mapping -- maps lifecycle phase to provider-specific state name
    • github_project -- Projects v2 field IDs and option IDs (GitHub only)
    • custom_fields -- any custom fields to update per transition
  2. Validate -- check that the requested phase has a mapping:

    • If state_mapping.<phase> is null: log info "State mapping not configured for <phase>, skipping", return success
    • If github_project.number is null and provider is github: check for labels fallback
  3. Update state -- based on provider:

    GitHub Projects v2 (primary): a. Read github_project.owner from manifest for the --owner flag. b. Get the project item ID for the issue:

    gh project item-list <number> --owner <github_project.owner> --format json | jq '.items[] | select(.content.number == <issue_number>)'
    

    c. Update the status field:

    gh project item-edit --project-id <project_id> --id <item_id> --field-id <status_field_id> --single-select-option-id <option_id>
    

    GitHub Labels (fallback): a. Remove existing status-* labels:

    gh issue edit <number> --remove-label "status-refinement,status-ready,status-in-progress,status-in-review,status-done"
    

    b. Add new status label:

    gh issue edit <number> --add-label "status-<phase>"
    

    Azure DevOps: a. Update work item state:

    az boards work-item update --id <number> --state "<mapped_state>" -o json
    
  4. Add comment (if --comment provided or if context available):

    • GitHub: gh issue comment <number> --body "<comment>"
    • Azure DevOps: az boards work-item update --id <number> --discussion "<comment>"
    • Include context: spec reference, PR URL, or transition reason
  5. Update custom fields (if configured for this transition):

    • Read custom_fields from manifest for fields that should update on this phase
    • Example: set "Start Date" on in_progress transition, set "Target Date" on ready
    • Respect hierarchy policy: feature-level records remain read-only even if the provider exposes writable fields
  6. Return result -- report success or failure to caller:

    • Success: { "status": "updated", "phase": "<phase>", "ref": "<ref>", "provider_state": "<mapped>" }
    • Skipped: { "status": "skipped", "reason": "no state mapping configured" }
    • Failed: { "status": "failed", "error": "<message>", "remediation": "<hint>" }

Fail-Open Protocol

This skill NEVER blocks the calling skill's workflow:

  1. If provider CLI is not authenticated: log warning with gh auth login or az login hint, return success
  2. If project item not found: log warning "Issue #N not found in project #M", return success
  3. If field update fails: log warning with error details, return success
  4. If network error: log warning, return success

The calling skill checks the return status for logging but NEVER stops its own execution based on board-sync failure.

Lifecycle Phase Reference

PhaseTriggerTypical Caller
refinementWork item fetched for brainstormai-brainstorm (step 1)
readySpec written and approvedai-brainstorm (step 4)
in_progressImplementation beginsai-dispatch (step 2.5)
in_reviewPR createdai-pr (step 12.5)
donePR mergedGitHub/ADO automation (close rules)

Common Mistakes

  • Blocking the calling skill when board-sync fails (violates fail-open)
  • Using provider-specific state names instead of lifecycle phase names
  • Not checking if state_mapping is configured before attempting update
  • Attempting Projects v2 update without first looking up the project item ID

Scripts

  • scripts/board-sync-github.sh <project-number> --owner <github_project.owner> -- query GitHub Projects v2 items and summarize work item states. Read owner from github_project.owner in manifest. Path is relative to the skill directory (.claude/skills/ai-board-sync/).

Integration

  • Called by: ai-brainstorm, ai-dispatch, ai-pr (internal calls, not user-facing)
  • Reads: .ai-engineering/manifest.yml (work_items section)
  • Writes: external only (provider board state, work item comments)
  • Pair: /ai-board-discover (discover writes the config this skill reads; run discover if sync fails)

$ARGUMENTS

相关技能

寻找 ai-board-sync 的替代方案 (Alternative) 或可搭配使用的同类 community Skill?探索以下相关开源技能。

查看全部

openclaw-release-maintainer

Logo of openclaw
openclaw

Your own personal AI assistant. Any OS. Any Platform. The lobster way. 🦞

333.8k
0
AI

widget-generator

Logo of f
f

为prompts.chat的信息反馈系统生成可定制的插件小部件

149.6k
0
AI

flags

Logo of vercel
vercel

React 框架

138.4k
0
浏览器

pr-review

Logo of pytorch
pytorch

Python中具有强大GPU加速的张量和动态神经网络

98.6k
0
开发者工具