Follow a structured Claude Code curriculum with tracks for different goals. Record concrete evidence from project exercises, unlock modules when prerequisites are complete, and check scheduled reviews while keeping progress data inside the current project.
中文简介正在准备中。当前显示英语简介。
Run the local Claude Code learning path, record evidence, and schedule evidence-based reviews.
安装前可以查看交给 AI 代理的指令内容。
Use this skill to follow a bounded, local progression through the existing seven-module guide. The engine selects only modules whose prerequisites are complete, saves nothing outside the current project's .claude/learning/ directory, requires a non-empty evidence note, and rejects corrupt state.
Run /self-assessment quick before choosing a track. It is a self-reporting aid, not a certification. Map its result deliberately:
| Self-assessment result | Learning-path track |
|---|---|
| Beginner | Beginner |
| Intermediate | Practitioner |
| Advanced | Production |
Maintainer is not a self-assessment result. Select it manually only when the goal is shared governance, such as maintaining team instructions, controls, or evidence practices.
Choose the lowest track that covers your immediate goal:
| Track | Outcome | Modules |
|---|---|---|
| Beginner | Safe first daily workflow | 01 to 03 |
| Practitioner | Reusable project workflows | 01 to 05 |
| Production | Automation with verification controls | 01 to 07 |
| Maintainer | Shared practice and governance | 01 to 07 |
The module definitions, guide references, exercises, prerequisites, and review intervals are in assets/path.yaml. The source curriculum is the existing seven-module learning path.
Run commands from the repository or project being learned. CLAUDE_SKILL_DIR is the installed-skill directory provided by Claude Code. --root "$PWD" makes the learner's current project, rather than the installed skill, the only state target.
python3 "${CLAUDE_SKILL_DIR}/scripts/progress.py" --root "$PWD" init --track Beginner
python3 "${CLAUDE_SKILL_DIR}/scripts/progress.py" --root "$PWD" status
python3 "${CLAUDE_SKILL_DIR}/scripts/progress.py" --root "$PWD" next
python3 "${CLAUDE_SKILL_DIR}/scripts/progress.py" --root "$PWD" complete module-01 \
--evidence "Installed Claude Code, ran /help, and recorded the version."
python3 "${CLAUDE_SKILL_DIR}/scripts/progress.py" --root "$PWD" due
The state file is .claude/learning/claude-code-guide-progress.json. It belongs to the learner's project, not this installed skill. init refuses to overwrite an existing state file. Keep the state local unless you deliberately decide to share the evidence.
Before completing a module:
next to retrieve the next unlocked module.An empty note, an unmet prerequisite, an unknown module, a module outside the selected track, or corrupt state is an error. The tool does not infer completion from a percentage, a command exit code, or an assertion by the learner.
Each completion schedules reviews exactly at 1, 3, 7, 14, 30, 60, and 90 days after the recorded completion date. due returns all scheduled reviews due on or before today. Revisit the linked exercise and update a separate proof artifact if the knowledge has changed.
All writes are local and atomic. A malformed state file fails closed and remains untouched for inspection or recovery. The prototype does not call a network service, install packages, assess competence automatically, or edit the guide.
The runtime validates path.yaml with Python's JSON parser because the file uses the JSON subset of YAML. The bundled quick_validate.py skill validator imports PyYAML before it parses SKILL.md frontmatter. If that import fails, this frontmatter validation is UNKNOWN, not a successful skill validation. The dependency-free runtime tests can still establish that this exact path definition loads.
还没有评价。欢迎分享你的使用感受。
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。
Evaluate Claude Code agents, skills, and commands with weighted quality criteria. Get scores, readiness grades, template comparisons, and practical improvement suggestions in Markdown or JSON reports to guide reviews before release.
中文简介正在准备中。当前显示英语简介。
Assess a codebase across seven areas, including exposed credentials, security, dependencies, structure, and tests. Receive category scores, findings tied to file locations, and a prioritized improvement plan with smaller tasks that can be completed quickly.
中文简介正在准备中。当前显示英语简介。
Measure code patterns such as casts to any or disabled lint rules, then run repeated, targeted edits. Keep changes that improve the chosen metric, revert unsuccessful changes, and track results for each improvement loop.
中文简介正在准备中。当前显示英语简介。
Generate several separate solutions, compare them against criteria fixed in advance, and verify the selected result through executable checks or an independent reviewer. Keep a proof log documenting candidates, evidence, failures, and remaining limits.
中文简介正在准备中。当前显示英语简介。
Monitor a live application after deployment and compare it with a saved baseline, a record of its earlier state. Check page responses, loading times, and new errors, flag persistent changes, and produce a per-page health report.
中文简介正在准备中。当前显示英语简介。
Rebuild project context after clearing a conversation or returning to work. Review recent Git history, uncommitted changes, and TODO markers to get a structured summary of project status and suggested next steps.
中文简介正在准备中。当前显示英语简介。