Skills

All Skills

thresholds

Skills tagged with #thresholds

@coyvalyss1

context-monitor

Monitor conversation context and prevent MAX mode by warning at token thresholds and generating handoff summaries. Use when context approaches 100K/150K/180K tokens or when working with high-cost files.

coyvalyss1/model-matchmaker+2 more
19d ago
1440
@skydoves

choosing-derivedstateof

Use this skill to decide when Jetpack Compose derivedStateOf is the right tool and when it is pure overhead. Covers the "input frequency must exceed output frequency" rule, the mandatory remember { derivedStateOf { } } wrapper, the canonical pitfall of capturing non-state variables by initial value (and the remember(key) fix), and the snapshotFlow alternative for fire-and-forget side effects on derived values. Use when the developer mentions derivedStateOf, scroll-position-driven booleans, threshold checks, firstVisibleItemIndex, "show FAB on scroll", recomposition counts that don't drop after wrapping a value, or asks whether a computed string concatenation should use derivedStateOf.

skydoves/compose-performance-skills+16 more
9d ago
1760
@dcramer

agent-design-review

Designs, reviews, and iterates on LLM agents and agent-like workflows. Use when asked to "design an agent", "review this agent", "improve our system prompt", "optimize prompts for caching", "improve tool calling", "reduce hallucinated tool calls", "add structured outputs", "decide if this should be multi-agent", "reduce false positives", "tune agent thresholds", or "build evals for this agent". Covers architecture choice, cache-friendly prompt templates, tool and schema design, runtime loops, trust boundaries, and eval-driven iteration.

dcramer/peated+1 more
19d ago
900
@simonasrazm

sflo

Build products using the SFLO pipeline — a gated PM→Dev→QA process with configurable gates, threshold, and guardian safety. Use when user says SFLO or asks to install/download SFLO.

simonasrazm/simon-factory-lights-out
18d ago
210