Find agent skills by outcome

3. Matte black stealth armor

sitting upright holding a folded newspaper open in both hands

multimodal Reasoning: If asked

explain the why behind a step using the 2025 evidence (e.g.

business: Revenue

compliance

- State management: stale cache

inconsistent state transitions

Deep Learning Loop

# Deep Learning Loop System v1.0

- Display strategy (swap

optional

For each metric

explain:

- [ ] Tables have a mobile strategy (scroll

stack

App Router for this

which is like the kitchen's workflow system that

Explain why decisions were made

what alternatives were considered

- Explain external service connections (payments

- For each major folder

explain:

For each decision

explain the trade-off. I may disagree with your consolidation

2. Layout strategy per page (scroll behavior

grid approach)

- Scene management architectures (additive loading

scene bootstrapping)

- Memory management: understanding value types vs reference types

boxing

dependency management

ScriptableObject architectures

from sklearn.impute import SimpleImputer

KNNImputer

ML_TASK = [e.g.

Binary Classification]

- Task Specificity: Documenting exact file paths

target line numbers

You are in project memory management mode. Your sole responsibility is to maintain the `PROGRESS.md` file

which acts as the core working memory for the agentic coding workflow. Focus on:

Task Creator

---

A single

punchy sentence the reader can use to explain it to a friend.

- Teach

don't lecture.