productivity▌

Skill by ara.so — Daily 2026 Skills collection.

sentry-code-review

Behavioral testing and reliability metrics for LLM agents, catching production failures benchmarks miss. \n \n Covers five core evaluation areas: agent testing, benchmark design, capability assessment, reliability metrics, and regression testing \n Emphasizes statistical test evaluation (multiple runs, result distribution analysis) and behavioral contract testing over single-run or string-matching approaches \n Includes adversarial testing patterns to actively probe agent failure modes and ident

Forge is a full-stack Rust framework. Everything compiles into a single binary backed by PostgreSQL. There is no separate API server, job runner, or cron scheduler -- one binary does it all.

Fetch external documentation, references, and context for a query. Decomposes into 2-5 facets and spawns parallel document-specialist Claude agents.

Use this skill when the user needs metadata definition or org metadata discovery: custom objects, fields, validation rules, record types, page layouts, permission sets, or schema inspection with sf CLI.

Simplify code while preserving behavior, public contracts, and side effects. Favor explicit code and local clarity over clever or compressed constructs.

Automated learning capture in CI pipelines that deduplicates failure patterns and proposes prevention rules. \n \n Inspects PR check results and CI failures to identify recurring patterns tracked by stable pattern_key , promoting only when recurrence thresholds are met (3+ occurrences across 2+ distinct runs within 30 days) \n Ingests learning candidates from simplify-and-harden-ci and emits machine-readable YAML output without interactive prompts, suitable for headless GitHub Actions workflows

Complete observability and tracing for LLM applications with prompt management, evaluation, and cost tracking. \n \n Automatic tracing of LLM calls, spans, and traces with user/session grouping; supports OpenAI SDK as drop-in replacement and integrates with LangChain via callback handlers \n Built-in prompt versioning, A/B testing, dataset management, and scoring for evaluation and quality monitoring \n Cost and performance tracking across traces with metadata tagging for production debugging an

Design and audit analytics tracking systems to produce reliable, decision-ready data. \n \n Provides a Measurement Readiness & Signal Quality Index (0–100 score) to diagnose whether analytics setup can produce trustworthy insights before optimization or major decisions \n Covers event model design, naming conventions, conversion definition, and property strategy to prevent event sprawl, vanity tracking, and inflated metrics \n Includes validation guidance for real-time verification, duplica