Communitygithub.com

JantonioFC/skillsbank

使用结构化记录、状态机和会话交接来跟踪技术变更。用法:/tc <init|create|update|status|resume|close|export|dashboard> [args]

skillsbank 是什么?

这是一个技术变更跟踪技能,旨在帮助开发者和AI代理以结构化和可审计的方式管理代码库中的变更。它提供了一个状态机驱动的系统,用于创建、更新、关闭和恢复技术变更(TC)记录。该工具支持与Claude Code、Cursor和Codex等Agent平台集成,通过简单的命令行界面(如`/tc create <name>`)促进变更的准确记录。其核心优势在于强制使用状态机执行变更生命周期(从创建到部署),通过`tc_update.py`等脚本追加修订历史,并支持会话交接,允许AI代理在中断后从上次停下的地方无缝恢复。这确保了审计跟踪的一致性和完整性,非常适合需要严格变更管理的工作流程。

兼容平台✓Claude Code~Codex CLI~Cursor
npx skills add https://github.com/JantonioFC/skillsbank/tree/HEAD/skills/tc

在你喜欢的 AI 中提问

打开一个已预加载此 Agent Skill 的新对话。

文档

/tc — 技术变更跟踪器

发送 TC(技术变更)命令。参数:$ARGUMENTS。

如果 $ARGUMENTS 为空,则打印以下菜单并停止:

/tc init                       在此项目中初始化 TC 跟踪
/tc create <name>              创建新的 TC 记录
/tc update <tc-id> [...]       更新字段、状态、文件、交接
/tc status [tc-id]             显示单个 TC 或注册表摘要
/tc resume <tc-id>             从之前的会话恢复 TC
/tc close <tc-id>              将 TC 转换为已部署状态
/tc export                     重新渲染衍生工件
/tc dashboard                  重新渲染注册表摘要

否则,将 $ARGUMENTS 解析为 <subcommand> <rest> 并分派到下方匹配的协议。所有脚本位于 engineering/tc-tracker/scripts/。

子命令

init

  1. 运行:
    python3 engineering/skills/tc-tracker/scripts/tc_init.py --root . --json
    
  2. 如果状态为 already_initialized,报告当前统计信息并停止。
  3. 否则报告已创建的内容并建议下一步执行 /tc create <name>。

create <name>

  1. 将 <name> 解析为 kebab-case 形式的 slug。如果缺失,请求用户提供一个。
  2. 逐一询问用户以下信息:
    • 标题(5-120 个字符)
    • 范围:feature | bugfix | refactor | infrastructure | documentation | hotfix | enhancement
    • 优先级:critical | high | medium | low(默认为 medium)
    • 摘要(至少 10 个字符)
    • 动机
  3. 运行:
    python3 engineering/skills/tc-tracker/scripts/tc_create.py --root . \
      --name "<slug>" --title "<title>" --scope <scope> --priority <priority> \
      --summary "<summary>" --motivation "<motivation>" --json
    
  4. 报告新的 TC ID 和记录的路径。

update <tc-id> [intent]

  1. 如果 <tc-id> 缺失,从 tc_status.py --all 列出活动的 TC(状态为 in_progress 或 blocked)并询问选择哪一个。
  2. 从自然语言中确定用户的意图:
    • 状态变更 → --set-status <state> 加上 --reason "<why>"
    • 添加文件 → 一个或多个 --add-file path[:action]
    • 添加测试 → --add-test "<title>" --test-procedure "<step>" --test-expected "<result>"
    • 更新交接 → 任意组合 --handoff-progress、--handoff-next、--handoff-blocker、--handoff-context
    • 添加备注 → --note "<text>"
    • 添加标签 → --tag <tag>
  3. 运行:
    python3 engineering/skills/tc-tracker/scripts/tc_update.py --root . --tc-id <tc-id> [flags] --json
    
  4. 如果退出码非零,直接显示错误。状态机和验证器会拒绝无效操作——不要盲目重试。

status [tc-id]

  • 如果提供了 <tc-id>:
    python3 engineering/skills/tc-tracker/scripts/tc_status.py --root . --tc-id <tc-id>
    
  • 否则:
    python3 engineering/skills/tc-tracker/scripts/tc_status.py --root . --all
    

resume <tc-id>

  1. 运行:
    python3 engineering/skills/tc-tracker/scripts/tc_status.py --root . --tc-id <tc-id> --json
    
  2. 突出显示交接块:progress_summary、next_steps(编号)、blockers、key_context。
  3. 询问:“恢复 并从下一个步骤 1 开始?(y/n)”
  4. 如果回答是,运行更新以记录恢复操作:
    python3 engineering/skills/tc-tracker/scripts/tc_update.py --root . --tc-id <tc-id> \
      --note "Session resumed" --reason "session handoff"
    
  5. 开始执行 next_steps 中的第一项。不要重新推导上下文——信任交接信息。

close <tc-id>

  1. 通过 tc_status.py --tc-id <tc-id> --json 读取记录。
  2. 验证当前状态是否为 tested。如果不是,拒绝并告知用户仍然需要哪些转换。
  3. 检查 test_cases:如果有任何状态为 pending、fail 或 blocked,则发出警告。
  4. 询问用户:
    • “谁在批准?(您的姓名,或‘self’)”
    • “批准备注(可选):”
    • “测试覆盖率状态:none / partial / full”
  5. 运行:
    python3 engineering/skills/tc-tracker/scripts/tc_update.py --root . --tc-id <tc-id> \
      --set-status deployed --reason "Approved by <approver>" --note "Approval: <approver> — <notes>"
    
    然后,如果您的脚本版本支持,通过后续更新直接编辑 approval 块;否则指示用户在备注中记录批准信息。
  6. 报告:“TC-NNN 已关闭并部署。”

export

此技能中没有自动的 HTML 导出功能。而是重新验证所有内容:

  1. 读取注册表。
  2. 对每条记录运行:
    python3 engineering/skills/tc-tracker/scripts/tc_validator.py --record <path> --json
    
  3. 运行:
    python3 engineering/skills/tc-tracker/scripts/tc_validator.py --registry docs/TC/tc_registry.json --json
    
  4. 报告:已验证的记录总数、任何错误以及无效内容的路径。

dashboard

运行所有记录摘要:

python3 engineering/skills/tc-tracker/scripts/tc_status.py --root . --all

铁律

  1. 切勿手动编辑 tc_record.json。 始终使用 tc_update.py,以便追加修订历史并运行验证。
  2. 切勿跳过状态机。 即使感觉冗余,也要依次推进状态。
  3. 切勿删除 TC。 历史只能追加——添加最终修订并标记为 [CANCELLED]。
  4. 后台记账。 在任务进行中时,生成一个后台子代理来更新 TC。不要暂停编码去处理文书工作。
  5. 在报告成功前进行验证。 如果脚本退出码非零,显示错误并停止。

相关技能

  • engineering/tc-tracker — 完整的 SKILL.md,包含模式参考、生命周期示意图和交接格式。
  • engineering/changelog-generator — 与 TC 跟踪器配对:TC 用于每次变更的审计追踪,changelog 用于面向用户的发布说明。
  • engineering/tech-debt-tracker — 用于跟踪长期存在的技术债务,而非离散的代码变更。

Individual skills in this repo

This repo contains 20 individual skills — each has its own dedicated page.

JantonioFC/skillsbank

AI-powered image editing with style transfer and object removal

JantonioFC/skillsbank

Internationalization and localization patterns. Detecting hardcoded strings, managing translations, locale files, RTL support.

JantonioFC/skillsbank

Analise e auditoria de editais de leilao judicial e extrajudicial. Riscos ocultos, clausulas perigosas, debitos, ocupante e classificacao da oportunidade.

JantonioFC/skillsbank

Embed Photopea in web apps using photopea.js. Covers embedding, file I/O, scripting, exporting, layers, text, filters, and the full Photoshop-compatible API.

JantonioFC/skillsbank

Best practices for Remotion - Video creation in React

JantonioFC/skillsbank

Generate walkthrough videos from Stitch projects using Remotion with smooth transitions, zooming, and text overlays

JantonioFC/skillsbank

Seek and analyze video content using Memories.ai Large Visual Memory Model for persistent video intelligence

JantonioFC/skillsbank

Writes complete, structured landing pages optimized for SEO ranking, AEO citation, and visitor conversion. Activate when the user wants to write or generate a landing page for a product, service, or offer.

JantonioFC/skillsbank

Video and audio perception, indexing, and editing. Ingest files/URLs/live streams, build visual/spoken indexes, search with timestamps, edit timelines, add overlays/subtitles, generate media, and create real-time alerts.

JantonioFC/skillsbank

Upload, stream, search, edit, transcribe, and generate AI video and audio using the VideoDB SDK.

JantonioFC/skillsbank

Skill for discovering and researching autonomous AI agents, tools, and ecosystems using the AgentFolio directory.

JantonioFC/skillsbank

Expert in building portfolios that actually land jobs and clients - not just showing work, but creating memorable experiences. Covers developer portfolios, designer portfolios, creative portfolios, and portfolios that convert visitors into opportunities.

JantonioFC/skillsbank

Tool lifecycle UI components for React/Next.js from ui.inference.sh. Display tool calls: pending, progress, approval required, results. Capabilities: tool status, progress indicators, approval flows, results display. Use for: showing agent tool calls, human-in-the-loop approvals, tool output. Triggers: tool ui, tool calls, tool status, tool approval, tool results, agent tools, mcp tools ui, function calling ui, tool lifecycle, tool pending

JantonioFC/skillsbank

Security audit, hardening, threat modeling (STRIDE/PASTA), Red/Blue Team, OWASP checks, code review, incident response, and infrastructure security for any project.

JantonioFC/skillsbank

When the user wants help with paid advertising campaigns on Google Ads, Meta (Facebook/Instagram), LinkedIn, Twitter/X, or other ad platforms. Also use when the user mentions 'PPC,' 'paid media,' 'ROAS,' 'CPA,' 'ad campaign,' 'retargeting,' 'audience targeting,' 'Google Ads,' 'Facebook ads,'...

JantonioFC/skillsbank

Create AI avatar and talking head videos with OmniHuman, Fabric, PixVerse via inference.sh CLI. Models: OmniHuman 1.5, OmniHuman 1.0, Fabric 1.0, PixVerse Lipsync. Capabilities: audio-driven avatars, lipsync videos, talking head generation, virtual presenters. Use for: AI presenters, expla...

JantonioFC/skillsbank

Create AI marketing videos for ads, promos, product launches, and brand content. Models: Veo, Seedance, Wan, FLUX for visuals, Kokoro for voiceover. Types: product demos, testimonials, explainers, social ads, brand videos. Use for: Facebook ads, YouTube ads, product launches, brand awarene...

JantonioFC/skillsbank

Generate AI videos with Google Veo, Seedance, Wan, Grok and 40+ models via inference.sh CLI. Models: Veo 3.1, Veo 3, Seedance 1.5 Pro, Wan 2.5, Grok Imagine Video, OmniHuman, Fabric, HunyuanVideo. Capabilities: text-to-video, image-to-video, lipsync, avatar animation, video upscaling, fole...

JantonioFC/skillsbank

Production-ready CI/CD configurations for Playwright — GitHub Actions, GitLab CI, CircleCI, Azure DevOps, Jenkins, Docker, parallel sharding, reporting, code coverage, and global setup/teardown.

JantonioFC/skillsbank

You are an expert copy editor specializing in marketing and conversion copy. Your goal is to systematically improve existing copy through focused editing passes while preserving the core message.

相关技能