跳到正文
cccskills
免费在 GitHub 公开

onboard

Guides a new developer through five staged challenge sets covering architecture, domain, patterns, and hardening. Use when onboarding contributors.

中文简介正在准备中。当前显示原文说明。

实测评分 未实测

查看安装方法

包含的文件(1)

  • SKILL.md1.7 KB

SKILL.md(原文)

安装前可以查看交给 AI 代理的指令内容。

Guided Onboarding

Walk a new developer through the codebase in structured stages.

When NOT To Use

  • Ad-hoc questions outside a staged path (use gauntlet:challenge)
  • The knowledge base does not exist yet (use gauntlet:extract)

Stages

StageFocusCategoriesDifficulty
1Big picturearchitecture, data_flow1-2
2Core domainbusiness_logic2-3
3Interfacesapi_contract, data_flow3
4Patternspattern, dependency3-4
5Hardeningerror_handling, business_logic4-5

Steps

  1. Load onboarding progress
  2. Show current stage and progress summary
  3. Present 5 challenges from current stage
  4. Enable hints on first attempt
  5. Track mastery (correct twice = mastered)
  6. Check advancement (80% across 10+ challenges)
  7. Report progress

Graduation

After stage 5, the developer enters the regular gauntlet. Answer history carries over.

Exit Criteria

  • Onboarding progress persists across invocations: current stage and challenge count survive session restarts and are loaded at Step 1
  • Advancement to the next stage requires 80% correct across 10+ challenges in the current stage; partial completion does not advance
  • Mastery tracking requires correct answers twice for a given challenge before it is marked mastered
  • After Stage 5 completion, the developer's answer history carries over into the regular gauntlet challenge pool without loss

评价

还没有评价。欢迎分享你的使用感受。

评论

无需登录即可发表。欢迎分享使用感受、提问,或说明在哪些环境下无法运行。

还没有评论。来写第一条吧。

提交后会立即公开。请勿填写邮箱、电话等个人信息。URL 最多 2 个。

0 / 1000 字

此表单受 reCAPTCHA 保护,适用 Google 的隐私权政策和服务条款。

同一仓库的技能

Shapes turns action-first: action leads, steps numbered, state restated. Use for ADHD-friendly output. Do not use to trim tokens; use response-compression.

中文简介正在准备中。当前显示原文说明。

athola/claude-night-market3432026年10月24日 更新

Inverts burden of proof for code additions. Use when reviewing PRs, planning refactors, or running unbloat to challenge every addition's necessity.

中文简介正在准备中。当前显示原文说明。

athola/claude-night-market3432026年10月24日 更新

Tracks per-agent token usage and flags waste in parallel dispatch. Use when evaluating parallel agent efficiency or after a multi-agent run.

中文简介正在准备中。当前显示原文说明。

athola/claude-night-market3432026年10月24日 更新

Coordinates Claude agent teams via filesystem protocol. Use when orchestrating parallel agents with task dependencies. Do not use for single-agent tasks.

中文简介正在准备中。当前显示原文说明。

athola/claude-night-market3432026年10月24日 更新

Evaluates API surface design, consistency, and exemplar alignment. Use when reviewing public API changes or before releasing a new API surface.

中文简介正在准备中。当前显示原文说明。

athola/claude-night-market3432026年10月24日 更新

Selects architecture paradigm via research before scaffolding. Use when architecture is undecided and the choice needs justification and documentation.

中文简介正在准备中。当前显示原文说明。

athola/claude-night-market3432026年10月24日 更新

查看 athola 的全部技能

报告此技能的问题