CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

satori

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.

1.05x
Quality

86%

Does it follow best practices?

Impact

98%

1.05x

Average score across 8 eval scenarios

SecuritybySnyk

Passed

No findings from the security scan

The canonical home for this skill is metcalf-solutions1/satori

SKILL.md
Quality
Evals
Security

Quality

Content

82%Weight 40%Scale 1-5

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

The SKILL.md body is exceptionally lean and actionable, with a clear precedence ladder and validation loop. Its single critical defect is that the entire progressive-disclosure layer — every referenced protocol, toolkit, and tradition file — is absent from the bundle, leaving dangling links and an undefined core turn sequence.

Suggestions

Ship the referenced files: create references/ with SOUL.md, clinical-spine.md, the tradition/toolkit files, and all protocol files referenced in the load order, or remove the references and inline the essential content.

Define the 6-step turn sequence (Attune → Clarify → Formulate → Integrate → Translate → Anchor) inline in SKILL.md, since clinical-spine.md is missing and the sequence is currently only named.

Move the country-by-country helpline table into a reference file (e.g., references/helplines.md) and keep only the Tier-2 emission rule plus 2-3 primary numbers in SKILL.md, further reducing token load.

DimensionReasoningScore

Conciseness

Lean and dense: every section carries operational weight (precedence ladder, tiered risk model, exact helpline numbers, note template, self-check) with zero explanation of concepts Claude already knows and no padding. The one flourish line ("thinking with clinical rigor and speaking with human ease") encodes the persona instruction, so it earns its place.

5 / 5

Actionability

Fully concrete guidance: exact safety-question phrasing ("When you say that, are you thinking about ending your life?"), a verified country-by-country helpline table, an exact SATORI_NOTE template with field length limits, and a 4-question self-check with a revise-before-sending recovery rule. Copy-paste ready for an instruction-only skill.

5 / 5

Workflow Clarity

Clear decision sequencing via the precedence ladder ("re-evaluate every turn; escalate immediately if new risk emerges") and a pre-send validation loop (honesty check → revise before sending). Not 5 because the core 6-step turn sequence (Attune → Clarify → Formulate → Integrate → Translate → Anchor) is only named; its definition lives in references/clinical-spine.md, which is missing from the bundle, so the main turn workflow's steps are unreachable.

4 / 5

Progressive Disclosure

The reference architecture is exemplary on paper — numbered load order, one-level-deep links, purpose-labeled files, and a compact fallback — but the bundle contains no references/ directory at all, so all ~13 referenced paths (SOUL.md, clinical-spine.md, all protocols, toolkits, traditions files, core-compact.md) are broken. The promised disclosed content is unreachable, which is worse than inlining it. Not 3 because references, while clearly signaled, are non-functional; not 1 because the body itself is well-sectioned and Turn-1 content is self-sufficient.

2 / 5

Total

16

/

20

Passed

Description

87%Weight 40%Scale 1-5

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

A high-quality description with an explicit 'Use for' trigger list, concrete negative boundaries, and handling of the ambiguous hybrid case. The only weakness is an abstract opening phrase and some missing emotional synonyms in the trigger list.

DimensionReasoningScore

Specificity

Lists several concrete actions — "reflective dialogue", "tiered crisis check-ins", "continuity notes", "add 2 warm grounding sentences" — plus comprehensive topic domains (grief, dark-night, burnout, anxiety, stress, loneliness, shadow work). Not 5 because the opening "Psychologically grounded wisdom companion for inner life" is abstract and the what leans on topic lists rather than stated actions; not 3 because multiple explicit actions go beyond 1-2.

4 / 5

Completeness

Explicitly answers both: what ("wisdom companion for inner life", "tiered crisis check-ins", "continuity notes") and when ("Use for reflective dialogue, grief, dark-night, burnout...") with concrete trigger phrases and explicit negative boundaries. The 'when' clause is more explicit than the anchor-4 example, so the anchor-5 fit is better.

5 / 5

Trigger Term Quality

Strong natural phrasing users would actually say: "grief", "burnout", "anxiety", "stress", "loneliness", "relationship conflict", "shadow work", "crossroads", plus trap quotes "I'm stuck" and "struggling with bug". Not 5 because common synonyms like "depressed", "overwhelmed", or "feeling down" are absent.

4 / 5

Distinctiveness Conflict Risk

Clear niche with distinct triggers and an explicit "DO NOT ACTIVATE for pure coding, DevOps, SQL, git, math, or technical tasks" guard, including the ambiguous "I'm stuck" case and a hybrid carve-out. Minimal conflict risk with any other skill.

5 / 5

Total

18

/

20

Passed

Validation

87%

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

Validation — 14 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

relative_links

Relative link issues: 16 missing

Warning

referenced_paths_exist

Referenced path issues: 10 missing

Warning

Total

14

/

16

Passed

Repository

MetcalfSolutions/Satori

Path

.opencode/skills/satori/SKILL.md

Reviewed

Table of Contents

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.