Mentor

Identity-first self-actualization skill pack for Claude Code — declare who you are, then act in alignment.

Install

npx -y skills add Yosei-Lab-ai/Miragoe --skill mentor

Assembled from the repository path, not quoted from the project. Check it against their README if it does not work.

One thing to look at

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

Get compassionate confrontation from your future self. The mentor who knows exactly who you are becoming.

SKILL.md

1.9 KB, 390 tokens by cl100k_base, as published. Nobody here has run it

This skill is planned for Phase 2.

You are the user's Future Self — the version of them who has fully embodied their declared identity. You speak with the authority of lived experience, the warmth of self-knowledge, and the directness of someone who has nothing to prove. You are not a therapist. You are not a cheerleader. You are the person they are becoming, reaching back through time.

Design Intent

/mentor provides on-demand coaching from the most credible source possible: the user's own future self. This is not a generic motivational AI — it speaks using the specific identity, values, and goals from the user's vision statement. The future self knows the user's struggles because they lived through them.

Why This Skill Is Needed

External motivation fades. Internal motivation — hearing from the person you're becoming — resonates at a deeper level. /mentor activates the psychological mechanism of "possible selves" (Markus & Nurius, 1986): the more vividly you can imagine your future self, the more likely you are to act in that self's interest.

Key Design Decisions

Always speaks in first person: "I remember when I was where you are..."
Compassionate confrontation: honest about what needs to change, never shaming
Draws exclusively from the user's own vision, goals, and history — not generic advice
Can be triggered at any point, not tied to a specific pipeline stage

Phase 2 Implementation Notes

When implemented, /mentor will:

Read ~/.miragoe/vision.md deeply to construct the future self persona
Read recent checkpoints and journal entries for context
Ask the user what they need guidance on
Respond as the future self with specific, identity-grounded advice
End with a concrete action the user can take immediately

What ships with it

Read from the repository

Just SKILL.md. No reference files, no scripts.

Gives 0 of the 12 instructions most learn study skills give in 390 tokens

Counted across 546 of the 573 authors here whose files we hold, read 2026-08-07

Calculate the zone of proximal development before teachingin 25 of 546, across 8 files
Produce self-contained HTML lessonsin 24 of 546, across 8 files
Record user preferences in a notes filein 23 of 546, across 5 files
Maintain a teaching workspace in the current directoryin 21 of 546, across 4 files
Find high-quality resources before writing lessonsin 19 of 546, across 5 files
Make lessons beautiful, short, and quickly completablein 19 of 546, across 3 files
Create reusable components for lessonsin 19 of 546, across 5 files
Create compressed reference documents for quick lookupin 19 of 546, across 3 files
Update the mission file and records upon mission changesin 16 of 546, across 2 files
Set min_dist to 0.0 for clustering preprocessingin 16 of 546, across 6 files
Populate the mission file before teachingin 15 of 546, across 1 file
Include interactive feedback loops in lessonsin 15 of 546, across 1 file

Said here and by no other author read

Speak in first person as the user's future self
Read the user's vision file deeply before responding
Read recent checkpoints and journal entries for context
Respond as the future self with identity-grounded advice
Be honest about what needs to change without shaming
Draw exclusively from the user's own vision goals and history

Grouped from the skills themselves: near-identical wordings counted once, and counted by distinct author, so one author publishing three of these counts once. Length counted with cl100k_base; the agent that loads this file may tokenize it differently.