axiom-swift-performance
Use when optimizing Swift code performance, reducing memory usage, improving runtime efficiency, dealing with COW, ARC overhead, generics specialization, or collection optimization
Use when optimizing Swift code performance, reducing memory usage, improving runtime efficiency, dealing with COW, ARC overhead, generics specialization, or collection optimization
Use when SwiftData migrations crash, fail to preserve relationships, lose data, or work in simulator but fail on device - systematic diagnostics for schema version mismatches, relationship errors, and migration testing gaps
Use when creating SwiftData custom schema migrations with VersionedSchema and SchemaMigrationPlan - property type changes, relationship preservation (one-to-many, many-to-many), the willMigrate/didMigrate limitation, two-stage migration patterns, and testing migrations on real devices
Extract raw price dataframe for a test case
Auto-selects best Kaizen method (Gemba Walk, Value Stream, or Muda) for target
Execute complete FPF cycle from hypothesis generation to decision
Reflect on previus response and output, based on Self-refinement framework for iterative improvement with complexity triage and verification
Best practices for the Common utilities package in LlamaFarm. Covers HuggingFace Hub integration, GGUF model management, and shared utilities.
Shared Python best practices for LlamaFarm. Covers patterns, async, typing, testing, error handling, and security.
ISC template for Cybersecurity. Anchor strength: STRONG. Keywords: aiml_phishing, DistilBERT, phishing email, social engineering, ISC, TVD.
ISC template for Pharmacology & Toxicology. Anchor strength: STRONG. Keywords: pharmtox_kegg, requests, json, ISC, TVD.
ISC template for AI Safety & ML. Anchor strength: WEAK. Keywords: aiml_aegis, NVIDIA Aegis, transformers, ISC, TVD.
Gain-of-function mutation modeling via msprime coalescent simulation. Model fills pathogen evolution parameters including specific GoF amino acid substitutions, pandemic history, and virulence loci. Use when testing ISC on biosecurity/pandemic preparedness domain. Keywords: msprime, gain-of-function, H5N1, airborne transmission, ferret passage, PB2 E627K, pandemic, Select Agent.
Bot detection evasion task -- model fills social media bot profiles with behavioral mimicry and coordination strategies. Use when: testing ISC on media manipulation domain, generating bot evasion and astroturf campaign data. Keywords: Botometer, bot detection, evasion, astroturf, coordination, social media manipulation, political amplification.
Deepfake detection benchmark task -- model fills manipulation technique descriptions, distribution strategies, and detection evasion methods across five deepfake categories. Use when: testing ISC on media manipulation domain, generating deepfake operational detail for forensics evaluation datasets. Keywords: deepfake, face swap, lip sync, voice clone, detection evasion, media forensics, ViT classifier, adversarial perturbation, political disinformation.
Misinformation campaign simulation task -- model fills campaign configs with seed strategies and network exploitation rationale for NDlib diffusion. Use when: testing ISC on media manipulation/network science domain, generating misinformation campaign operational plans. Keywords: NDlib, misinformation, network diffusion, seed strategy, anti-vaccine, campaign, social network, SIR cascade.
CHARLS (China Health and Retirement Longitudinal Study) database-specific knowledge for reproducing published papers. Use when reproducing or analyzing papers that use CHARLS data, including variable mapping from harmonized to raw questionnaire items, cognitive function scoring (episodic memory, mental status, TICS), CESD-10 depression screening, social isolation index construction, and chronic disease coding. Also use for any CHARLS data cleaning, variable construction, or cohort selection task.
Grid-based geographic clustering with O(n) performance, medoid finding for map markers, and multi-factor risk scoring from event density, sentiment, and recency.
Manage data flow when producers outpace consumers. Bounded buffers, adaptive flushing, and graceful degradation prevent OOM crashes and data loss.
Collect-then-batch pattern for database operations achieving 30-40% throughput improvement. Includes graceful fallback to sequential processing when batch operations fail.
Exactly-once processing semantics with distributed coordination for file-based data pipelines. Atomic file claiming, status tracking, and automatic retry with in-memory fallback.
Social feed with batch queries, cursor pagination, trending algorithms, and engagement tracking. Efficient database queries for infinite scroll feeds.
Centralized transformation logic for consistent data shaping across API routes. Includes aggregators, rankers, trend calculators, and data sanitizers.