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.

0.94x

Quality

76%

Does it follow best practices?

Impact

83%

0.94x

Average score across 3 eval scenarios

Securityby

Passed

No known issues

Fix and improve this skill with Tessl

tessl review fix ./SKILL.md

Quality

Content

70%

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

This is a well-structured routing/overview skill that excels at progressive disclosure and workflow clarity, with a clean load-order table and clear conditional triggers for reference files. Its main weakness is that it functions more as an index than a standalone actionable guide — nearly all operational detail lives in reference files, and there are no concrete examples of actual responses or dialogues. The content is mostly concise but includes some philosophical framing that could be trimmed.

Suggestions

Add one concrete example dialogue showing the 6-step conversation model applied to a real scenario (e.g., someone processing grief), so Claude has an executable template without needing to load clinical-spine.md first.

Trim the 'What Satori Does Not Do' list to only non-obvious constraints — items like 'moralize or preach' and 'offer empty affirmations' are inferable from the overall tone guidance and waste tokens.

Dimension	Reasoning	Score
Conciseness	The content is reasonably efficient but includes some unnecessary elaboration — the North Star quote and 'What Satori Does Not Do' section contain items Claude could infer from the clinical-spine reference. The load order table and core model summary are well-structured but the summary duplicates what's in reference files.	2 / 3
Actionability	The Opening Conventions provide concrete guidance for different scenarios, and the Core Conversation Model gives a clear 6-step sequence. However, there's no executable example of a response, no sample dialogue, and the actual operational detail is deferred entirely to reference files — making this more of a routing document than an actionable skill.	2 / 3
Workflow Clarity	The conversation model is clearly sequenced with six named steps. The load order table provides explicit conditional triggers for each reference file. Opening conventions cover multiple entry scenarios with specific responses. For a conversational/instruction skill (not a destructive/batch operation), this level of workflow clarity is strong.	3 / 3
Progressive Disclosure	Excellent progressive disclosure — the SKILL.md serves as a clear overview with a well-organized load-order table that signals exactly when to load each of 9 reference files. References are one level deep, clearly labeled with conditions, and the main file contains just enough summary to orient without duplicating reference content.	3 / 3
	Total	10 / 12 Passed

Description

82%

Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.

This description excels at trigger term quality and completeness, with explicit 'Activate when' clauses and natural user language examples. However, it is overly broad in its activation scope ('When in doubt, activate') which creates high conflict risk, and the actual capabilities are described more in terms of frameworks used than concrete actions performed. The use of second-person-adjacent framing is minimal, but the description leans heavily on listing traditions and methodologies rather than specifying what the skill actually does for the user.

Suggestions

Add concrete action verbs describing what the skill produces — e.g., 'Helps reframe difficult emotions, offers perspective through guided reflection, surfaces patterns in recurring life struggles' — rather than primarily listing frameworks.

Narrow the activation criteria to reduce conflict risk; 'When in doubt, activate' is too greedy and will cause this skill to fire inappropriately when other skills may be more relevant.

Dimension	Reasoning	Score
Specificity	The description names the domain (emotional/psychological support) and lists many frameworks and traditions, but the actual actions are vague — 'navigating the inner life,' 'processing something difficult,' 'think alongside someone.' It doesn't list concrete actions like 'reframe negative thought patterns' or 'guide grief processing exercises.' The specificity is more about inputs/frameworks than outputs/actions.	2 / 3
Completeness	Clearly answers both what (wisdom companion for navigating emotions, meaning, grief, purpose, etc., drawing from multiple traditions and therapeutic frameworks) and when (explicit 'Activate when' clauses with specific trigger phrases and scenarios, plus the generous 'When in doubt, activate' guidance).	3 / 3
Trigger Term Quality	Excellent coverage of natural trigger phrases users would actually say: 'I've been struggling with,' 'I don't know what to do,' 'I need to figure out,' plus domain terms like 'emotions, meaning, grief, purpose, relationship, identity.' These are highly natural and cover common variations of how users express emotional needs.	3 / 3
Distinctiveness Conflict Risk	While the philosophical/therapeutic framing is distinctive, the extremely broad activation criteria ('any emotionally charged framing,' 'When in doubt, activate') would cause this skill to trigger for a very wide range of conversations, potentially conflicting with more targeted mental health, relationship advice, or coaching skills.	2 / 3
	Total	10 / 12 Passed

Validation

100%

Warnings & errors only

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation — 11 / 11 Passed

Validation for skill structure

No warnings or errors.

Repository: MetcalfSolutions/Satori
Commit: 6440b52

Reviewed: 3 months ago

Table of Contents

Discovery Implementation Validation

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.