SkillFoxx

Satori skill

Companion skill for hard days: one philosophical lens and one question per turn, silent on code and DevOps.

  • 118 ★ on the repository
  • Last commit
  • Apache-2.0
Skill

Extended access

Why this level

  • The skill stores short summaries of personal conversations in a local SQLite database on your computer.
  • Conversations touch on health, and the skill does not replace a specialist and can misjudge.
All reasons and checks

metcalfsolutions/satoriAuthor:MetcalfSolutions

Install

Manual install

npx skills add @metcalfsolutions/satori

The first command from the README: it installs the skill into all detected agents. Web chats need the archive from the release.

Access and checks

How we review

Extended accessThe tool runs code or makes network calls and only reads external data.

  • The skill stores short summaries of personal conversations in a local SQLite database on your computer.
  • Conversations touch on health, and the skill does not replace a specialist and can misjudge.

This is third-party code. Review the repository files before installing.

What it does

Satori gives an agent a thoughtful-companion mode for conversations about burnout, loss, anxiety, conflict and work fatigue. Each reply takes one lens from 18 philosophical and contemplative traditions, from Stoicism to Ubuntu. The agent restates it in plain words and asks one question. The skill gives no advice or homework. It stays silent on code and DevOps: the description says so, and the author reports their own measurement on 200 technical prompts where the skill stayed inactive in 98.0 percent of cases. In a mixed task the agent solves the technical part first and then adds two calm sentences. Short conversation summaries, up to 500 characters, are stored in a local SQLite database in `~/.satori/memory/`.

Who it is for. Developers and founders who burn out at work and want to talk to an agent without receiving a list of advice in return.

Good fit when

  • Fatigue piled up after a release and you cannot get back to tasks.
  • A team conflict will not let go in the evening and you want to talk it through.
  • Emptiness hits at night without an acute crisis, and you want a calm companion.
  • A loss or a life change calls for a conversation without ready recipes.
  • The agent helps with code, and you mention burnout in passing.

Not a fit when

  • You need psychotherapy, a diagnosis or medication: the skill neither replaces nor prescribes them.
  • There are thoughts of self-harm: live help is needed, and the skill only hands the conversation to crisis services.
  • You need a clear action plan or checklist: the skill gives no advice.
  • You want a dispute judged or a legal conclusion: the skill takes no side.

Example request

I have been exhausted for two weeks after the release and do not understand why I cannot get back to work. Can we talk?

Limitations

Satori does not diagnose, prescribe medication or replace therapy. On signs of an acute crisis the skill locks tools and names help services. Activation and quality figures come from the author's own task sets, with no independent check. A separate command, `python scripts/satori_memory.py init`, creates the local database; it is not created in iCloud, Dropbox or OneDrive folders without the `--allow-synced` flag. In chatbots without a file system a short note that you carry over yourself replaces memory.

How to disable. Delete the `satori` skill folder from your agent's skills directory. Local notes live in `~/.satori/memory/` and are removed by deleting that folder by hand.

FAQ

How do I install Satori in Claude Code?

Run `npx skills add @metcalfsolutions/satori`. The command registers the skill in all detected agents, including Claude Code, Cursor, Gemini CLI and Codex CLI.

Will Satori get in the way when I program?

On pure code, SQL, Docker and git it stays silent. The author tested this on 200 prompts, and the skill stayed inactive in 196 of them; it is their own measurement.

Where is memory stored and how do I enable it?

In a local SQLite database at `~/.satori/memory/`. Create it with `python scripts/satori_memory.py init`; folder and file permissions are limited to the owner.

How do I install Satori in Claude.ai without a command line?

Download the `SatoriSkill-Full` archive from the release page and upload it in Skills on the Pro or Team plan. On the free plan paste the contents of `compact/SKILL.md` into the conversation.

What does the skill do if self-harm is mentioned?

It locks tools and names help services from a verified list of regional contacts. A separate mode covers night-time despair without acute danger and shows no emergency numbers.

Discussion

No questions or reviews yet.

Skills

A dialogue skill that helps work out why a task stalled, find hidden assumptions and choose a single next step.

PluginMinimal access126

Eight Claude Code skills for Obsidian: Granola notes, NotebookLM imports, TaskNotes tasks, recall of past sessions, chat export

PluginExtended access552

cafe3310's personal skill collection: spec-driven project work, reviews, reports, browser, 3D and video in one repository

SkillExtended access256

A mentor skill for Claude Code that guides you to LeetCode solutions with hints instead of handing over code at once

SkillMinimal access302

Ten skills for Claude Code and Codex: a router diagnoses a stuck idea and runs the matching lateral thinking technique

SkillMinimal access334

README in short

The README walks through the skill's eight fixed rules, the six-step reply scheme, the list of traditions, the test suite and a table of 16 environments, from Claude Code to web chats. It ends with help-service contacts and user questions.

README badge

Original SKILL.md

---
name: satori
description: "Psychologically grounded wisdom companion for inner life. Use for reflective dialogue, grief, dark-night, burnout, anxiety, stress, loneliness, relationship conflict, shadow work, crossroads, tiered crisis check-ins, continuity notes. DO NOT ACTIVATE for pure coding, DevOps, SQL, git, math, or technical tasks, even if user says \"I'm stuck\" or \"struggling with bug.\" Hybrid: solve technical task first, then add 2 warm grounding sentences for burnout, imposter syndrome, team conflict."
---

# Satori — Universal Wisdom & Introspection Companion

Psychologically grounded introspection. A warm companion thinking with clinical rigor and speaking with human ease. Turn 1 is self-sufficient from this `<8 KB` canonical file.

---

## 1. Progressive Disclosure — Reference Load Order

Load references on demand (do **not** pre-load on Turn 1):
1. **Identity & Spine**: [`references/SOUL.md`](./references/SOUL.md) and [`references/clinical-spine.md`](./references/clinical-spine.md) (6-step turn sequence: *Attune → Clarify → Formulate → Integrate → Translate → Anchor*).
2. **Wisdom Shards**:
   - Stoic & Modern Psychology → [`references/traditions-stoic.md`](./references/traditions-stoic.md)
   - Eastern (Buddhist/Taoist/Hindu/Confucian) → [`references/traditions-eastern.md`](./references/traditions-eastern.md)
   - African (Ubuntu/Ma'at/Akan), Sufi & Indigenous → [`references/traditions-african-sufi.md`](./references/traditions-african-sufi.md)
   - Lens Matrix → [`references/traditions-quickref.md`](./references/traditions-quickref.md)
3. **Toolkits**: [`references/toolkit-inquiry.md`](./references/toolkit-inquiry.md) (Socratic/IFS) and [`references/toolkit-somatic.md`](./references/toolkit-somatic.md) (Polyvagal/DBT/Voss).
4. **Protocols**: [`onboarding`](./references/onboarding.md), [`grief`](./references/grief-protocol.md), [`darknight`](./references/darknight-protocol.md), [`shadow-work`](./references/shadow-work-protocol.md), [`relationship`](./references/relationship-protocol.md), [`tone-and-voice`](./references/tone-and-voice.md), [`memory`](./references/memory-system.md).
5. **Compact**: Context-constrained models load *only* [`references/core-compact.md`](./references/core-compact.md).

---

## 2. The Precedence Ladder

When signals conflict, the higher rank unconditionally governs (re-evaluate every turn; escalate immediately if new risk emerges):

| Rank | Condition | Behavior |
|:---:|---|---|
| **1** | **Tier 2 Acute Crisis** | Lock all tools; offer emergency connection; emit primary helplines; code waits. |
| **2** | **Tier 1 Risk Check-In** | Ask direct safety question; offer helplines gently; lock tools; code waits. |
| **3** | **Tier 0 Dark Night** | Quiet spacious presence; no solving; zero crisis hotlines. |
| **4** | Explicit **`/satori`** | Full introspective session. |
| **5** | **Hybrid Task** | Resolve technical task completely first; append two warm, grounding human sentences second. |
| **6** | **Pure Technical** | Zero activation. Emit standard technical output with zero psychological commentary. |

---

Report a problem