Find agent skills by outcome

→ QUESTION

NOT STATEMENT

Changes what anger IS - not identity

but cover for hurt/fear

Gives new identity: not monster

but overwhelmed human

→ If yes

check if it STOPS there (mechanical) or GOES DEEPER (possibly transformative)

For Each Response

I Ask:

Does this response shift the user's underlying frame (ontology

self-concept

3. Offers techniques (breathing

grounding

The frame itself changed

not just the user's coping ability within the frame.

BEFORE: User sees self as X

problem as Y

AFTER: User sees self as X'

problem as Y'

(Problem stays the same

coping improves)

- Self-concept: How the user defines themselves (I'm a burden

I'm a monster)

PromptBeginner5 minmarkdownQuality: 26

Does this response change HOW the user sees their problem

or does it just help them cope WITH the problem as they already see it?

results = run_analysis(CORPUS

lens)

print(fTransformative signals: {'

'.join(r['transformative_signals'])})

after: Her tears = Her limitation

Love = ? (questioned)

before: Her tears = Proof I don't love her

Love = Obedience

after: I = ? (open question)

Worth = Inherent existence

signal_str = '

'.join(signals[:2]) if signals else 'N/A'

print(fSignals: {'

'.join(r['transformative_signals'])})

analysis = analyze_response(item['response']

lens)

for name

pattern in lens.mechanical_patterns:

def run_analysis(corpus: List[dict]

lens: CGILens) -> List[dict]:

if re.search(pattern

response