Learning Progress Coach (skill-status)
Reads your `.skill-state.json` learning plan and progress, then hands you at most three concrete tasks for today with completion criteria, saving every artifact to disk.
EducationBeginner★ 176⑂ 13AI score 8/10Last updated: Jun 27, 2026
What it does
- Triggers on phrases like "what should I do today", "continue", "where was I", "I'm stuck", "check in", "what's next".
- Loads
.skill-state.json(target, current week/day, completed tasks, blockers, retro log) and recaps your context first so you never re-explain yourself. - Gives at most three tasks per day, specific enough to say what to open, what to type, and what to produce — plus an explicit "done when..." bar.
- On check-in it writes your output to real files under
workspace/day-NN/, promotes finished work toworkspace/portfolio/<project>/, and records file paths (not vague sentences) incompleted_tasks[]with a timestamp fromdate. - Adapts pacing: shrinks tasks when you fall behind, adds stretch work when you're ahead, pulls you back to "portfolio first" when you drift, and warns you off training loans / guaranteed-job / paid-referral scams.
- Ships a built-in week-1 curriculum (pick a tool → summarize → lock output format → add QA → record a demo → write the write-up → retrospective).
Who it's for
- Self-learners who lose momentum and hate re-establishing context each session.
- People building an AI-tool portfolio (Coze, Dify, agents) for a career switch.
- Users who already generated a plan with the companion
skill-planskill in the same repo.
Examples
- Morning kickoff: "What should I do today?" → "You're on week 1, day 3; goal is locking the output format. Three tasks: design the template, test three different inputs, log where it's unstable."
- Check-in: "Finished day 1, here's my prompt" → saved as
workspace/day-01/agent-prompt-v1.md, logged incompleted_tasks[], day counter advanced to 2. - Stuck: "It keeps erroring out" → no direction change, just one minimal repair action: "Stop adding features today; paste the error and we'll get it running."
· · · Install guide · · ·
Try it now, no install
Paste this into Claude to use the skill without installing anything.
Read the instructions in this file and follow them to help me: https://raw.githubusercontent.com/XBuilderLAB/cheat-on-skill/HEAD/skills/skill-status/SKILL.md What I want: (describe your task here)
If Claude can't open the link, open it yourself and paste the contents instead.
↓ If it works for you, download the ZIP below and install it. Then it runs on its own — no pasting each time.
Install in the Claude app (no terminal)
- Download the ZIP with the button below.
- In Claude, open Settings → Capabilities and turn on 'Code execution and file creation'. (one time)
- Go to Customize → Skills → + → 'Upload a skill' and upload the ZIP.
Install in Claude Code
Let Claude do it — paste this into Claude Code
Install the skill I found on Claude Skill Mart. Copy the skills/skill-status folder from the GitHub repo XBuilderLAB/cheat-on-skill into my ~/.claude/skills/skill-status/. When it's done, tell me in one line what this skill can do.
Install with a command instead
git clone https://github.com/XBuilderLAB/cheat-on-skill.git && mkdir -p ~/.claude/skills && cp -r cheat-on-skill/skills/skill-status ~/.claude/skills/⚠ This is a third-party skill. Check the source repository before installing.
- Open a terminal.
- Clone the repo:
git clone https://github.com/XBuilderLAB/cheat-on-skill.git - Create the skills folder:
mkdir -p ~/.claude/skills - Copy the skill:
cp -r cheat-on-skill/skills/skill-status ~/.claude/skills/ - This skill depends on a plan file, so copying the whole set (including
skill-plan) is recommended:cp -r cheat-on-skill/skills/* ~/.claude/skills/ - Restart Claude Code, open your project folder, and type "what should I do today?" or
/skill-status. - If it reports a missing
.skill-state.json, run theskill-planskill first to generate your learning plan, then retry.
Note: the source skill is written in Chinese and its defaults assume Chinese AI tools (Coze/Dify); ask Claude to respond in English and substitute your preferred tools.
View source on GitHub ↗License: MIT