CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

learning-path

Run the local Claude Code learning path, record evidence, and schedule evidence-based reviews.

Quality

78%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide
SecuritybySnyk

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./examples/skills/learning-path/SKILL.md
SKILL.md
Quality
Evals
Security

Claude Code learning path

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.

Start with the diagnostic

Run /self-assessment quick before choosing a track. It is a self-reporting aid, not a certification. Map its result deliberately:

Self-assessment resultLearning-path track
BeginnerBeginner
IntermediatePractitioner
AdvancedProduction

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:

TrackOutcomeModules
BeginnerSafe first daily workflow01 to 03
PractitionerReusable project workflows01 to 05
ProductionAutomation with verification controls01 to 07
MaintainerShared practice and governance01 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.

Commands

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.

Completion gate

Before completing a module:

  1. Read the linked guide page.
  2. Do the linked exercise in a real project.
  3. Record a concrete evidence note that another person can inspect, such as a command, changed file, test result, or review artifact.
  4. Use 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.

Reviews

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.

Safety boundary

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.

Validation boundary

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.

Repository

FlorianBruniaux/claude-code-ultimate-guide

Path

examples/skills/learning-path/SKILL.md

Last updated
First committed

Is this your skill?

If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.