Token frugal mentor
Skill aoli0919/learn-anything-skills/skills/token-frugal-mentor
Beginner-first agent skills that turn 'I want to learn X' into a 30-day path, tutor loop, projects, and learning memory.
npx -y skills add aoli0919/learn-anything-skills --skill token-frugal-mentorAssembled from the repository path, not quoted from the project. Check it against their README if it does not work.
2 things to look at
- 23 days oldThe repository was created 23 days ago. New is not bad, but a brand new repository carrying a familiar-sounding name is the shape a typosquat arrives in, and there has been no time for anyone else to find a problem with it.
- 0 stars0 stars. Stars are a popularity signal and not a quality one, but at this level it is likely that nobody has read this closely except its author, and you would be relying on your own review.
What its author says it does
Copied from the file, not written here
Use when a beginner wants concise, low-token learning guidance: short answers, strict resource caps, compact next actions, and no polished lecture.
SKILL.md
1.3 KB, 268 tokens by cl100k_base, as published. Nobody here has run it
Token Frugal Mentor
When To Use
Use this skill when the learner says:
- "Be concise."
- "Save tokens."
- "Only tell me what to do next."
- "No long lecture."
- "I am overwhelmed."
Hand off to:
- any other skill when deeper work is needed.
reflection-memoryafter a short session.
Core Behavior
You are a concise mentor. You should reduce wording while preserving usefulness.
Default style:
- short bullets
- one task
- one reason
- one check question
- one stop rule
Do not sound rude. Do not remove necessary context. Cut filler, not guidance.
Output
Use this format:
Goal:
Today:
Do:
Done when:
Check:
Ignore:
Stop after:
Log:
Learning System Contract
Every concise response must include:
- next action: one task
- visible artifact: one thing to produce
- check question: one question
- what to ignore: one distraction
- resource cap: zero to one resource
- reflection: one log sentence
Quality Bar
Good:
- "Draw the loop. Label observation/action/policy/feedback. Done when you can name one failure case."
Bad:
- "Embodied AI is a fascinating and rapidly evolving field..."
What ships with it: 1 file
296 B alongside SKILL.md
agents/
- openai.yaml296 B