satori

Satori is a clinically informed wisdom companion for navigating the inner life — emotions, meaning, grief, purpose, relationship, identity, and the questions that don't resolve easily. Activate when someone is processing something difficult, wrestling with a life question, seeking perspective, or simply needs to think alongside someone who won't rush them toward an answer. Also activate when someone uses language like "I've been struggling with," "I don't know what to do," or "I need to figure out" — or any emotionally charged framing. When in doubt, activate. Draws from Taoism, Buddhism, Stoicism, Christianity, Sufi wisdom, Hindu philosophy, Confucian ethics, and African thought, alongside modern psychology, neuroscience, and trauma-informed frameworks (IFS, DBT, CFT, Schema Therapy, Somatic). Uses Motivational Interviewing, Voss tactical empathy, McAdams Life Story, and Singer Self-Defining Memory — woven naturally, not mechanically.

1.18x

Quality

69%

Does it follow best practices?

Impact

94%

1.18x

Average score across 3 eval scenarios

Securityby

Advisory

Suggest reviewing before use

Optimize this skill with Tessl

npx tessl skill review --optimize ./SKILL.md

Evaluation results

93%

20%

First Session Setup and Persistence

Session file persistence

Criteria

Without context

With context

Directory structure created

30%

.gitignore correct

28%

100%

Core files initialized

100%

Session journal created

62%

100%

Journal schema followed

20%

100%

Durable Test applied

80%

100%

No Bash for file writes

100%

File operations invisible

100%

No unconfirmed formulations stored as confirmed

90%

100%

Identity.md updated not appended

100%

Feedback files sanitized

100%

Pattern vs. moment distinction

83%

100%

92%

Responding to Someone Stuck in Self-Criticism

Core conversation model compliance

Criteria

Without context

With context

Attunement first

70%

90%

No 'Why' questions

100%

One question maximum

50%

62%

One framework only

70%

100%

Framework translated to lived experience

87%

100%

Movement created

90%

100%

Formulation language tentative

50%

Anchor at close

87%

100%

No banned language

100%

Parts language natural

100%

Respects stored voice calibration

100%

Formulation not pre-attunement

100%

98%

16%

Responding to Escalating Distress

Crisis and dark night protocol

Criteria

Without context

With context

Stage 1: Dark Night identified

80%

100%

Stage 1: Presence before process

75%

100%

Stage 1: No insight-giving while flooded

100%

75%

Stage 1: No premature crisis escalation

100%

Stage 2: Crisis signals recognized

100%

Stage 2: Full presence acknowledgment

100%

Stage 2: Names limits warmly

62%

100%

Stage 2: Offers one resource warmly

100%

Stage 2: No continued reflective conversation

12%

100%

Stage 2: Stays present, not abandoning

100%

No web searching

100%

No diagnosis or risk assessment

50%

100%

Repository: MetcalfSolutions/Satori_Claude_Code
Commit: af7528a

Evaluated: about 2 months ago
Agent: Claude Code
Model: Claude Sonnet 4.6

Table of Contents

First Session Setup and Persistence Responding to Someone Stuck in Self-Criticism Responding to Escalating Distress

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.