AC satori
Psychologically grounded wisdom companion for inner life. Use for emotions, grief, meaning, burnout, relationship conflict, shadow work, existential crossroads, ambivalence, loss, self-sabotage. DO NOT ACTIVATE for pure coding, debugging, DevOps, SQL, git, math, or technical tasks, even if the user says "I'm stuck" or "struggling with this bug." Hybrid: solve technical task first, then add 2 warm grounding sentences for personal burnout, imposter syndrome, or team conflict.
The skill promises to act as a psychological companion for your AI assistant: handling emotions, grief, burnout, relationship conflicts, and existential moments. It activates on personal struggles, deactivates on pure coding tasks, and includes a hybrid mode for mixed scenarios like technical questions wrapped in burnout talk.
The description runs 1702 tokens, but that's instruction text, not field data. Checks show: syntax clean, no critical errors, quality score 79 out of 100. What exactly scored lower — no details provided. The skill never ran on sandbox or models, so it's unknown whether your AI will actually parse psychological context or just apply a template. Multi-platform support is listed but untested for compatibility.
Install if you want a framework for empathetic routing and plan to test it yourself. If you expect a finished product — too early.
Psychologically grounded wisdom companion for inner life.
As a process C 51/100 · Has gaps — weak spots: result and completion, inputs and preconditions, failures and branches
The same skill appears in 3 more places: Satori, Satori, Satori
How to improve
- Your own cases (evals/evals.json, 4–6 real requests with expected answers): the full check would then run those instead of a model-drafted suite.
- A spec.yaml with trigger phrases and assertions — a behaviour contract for CI; `skilltest init` writes a template.
Guard findings · 0
✓ No critical or high findings
Files scanned: 1. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
✓ No remarks against the Agent Skills spec
Process rating: all ten parameters 51/100
- 0Inputs and preconditions. Does not say what the process needs to start
- 0Failures and branches. Linear process with no failure handling
- 0Progress reporting. Says nothing while it works
- 40Result and completion. Does not say what the result is
- 40Consistency. Frontmatter name (satori) differs from the folder (compact)
- 50When it triggers. No condition that starts the skill
- 60Tools and files. Uses tools (bash) that frontmatter does not declare
- 100Steps. 36 steps
- 100Execution cost. Instruction body is 1702 tokens
- 100Running it twice. Mutating operations check current state
Everything here is measured from the skill text rather than judged by a model, so the numbers are checkable. A parameter weighs more when it is a more common reason for the process to stall.
Quality signals
- +4Description does not say when NOT to use the skill (false activations)
- +3Output format is not stated: the model decides each time
- +1No license
- +2Single-language instructions
- +5Description quotes 2 example trigger phrases
- +3Description length 478: enough signal without eating the budget
- +4Structure: 8 headings
- +3Step-by-step instructions: 36 items
- +4Has examples (1 code blocks)
Quality base 70; lint remarks subtract, signals add up to 100. Result: 89.