Loading...
Loading...
Found 6 Skills
Use whenever researching a technical question — a library, tool, API, error, version, or "what's the best way to X" — or whenever you're about to answer from memory. Forces multiple real searches over primary sources (official docs, source code, high-vote Stack Overflow, maintainer blogs) instead of one search plus training-data filler, and rejects SEO content-farm slop. Trigger on "research X", "look into", "what's the best library for", "how does X work", "is this still true", "find out".
Guides privacy research engineering for safeguards—PII and sensitive-data detection research, redaction and de-identification evals, memorization and extraction risk studies, privacy benchmarks and labeled corpora, logging/retention minimization for safety pipelines, and research memos on privacy–utility trade-offs for guardrail systems. Use when measuring PII detector quality, designing privacy eval suites for moderation stacks, studying training-data leakage or prompt logging risk, or recommending privacy mitigations for safeguard models—not for SOC 2/GDPR evidence automation (compliance-engineer), legal DPIA or AI policy (ai-risk-governance), harm/toxicity classifier R&D (ml-research-engineer-safeguards), production inference gateways (ml-infrastructure-engineer-safeguards), or general non-privacy research (ai-researcher).
Write Thai-language prose (technical documentation, marketing copy, explainers, blog posts) that reads like a real Thai writer — not generic AI output. Counters training-data skew toward over-formal, over-polite, calqued Thai. Use this skill whenever the user asks for Thai writing, asks to translate English content into Thai, or asks to edit/rewrite existing Thai prose, even if they don't explicitly say "good prose." Also use when the user is in a Thai-language conversation and asks for any non-trivial prose output (a paragraph, section, blog post, landing page, doc page, README in Thai, email, announcement). The default Thai output without this skill is mechanically polite, connective-spammed, and calque-shaped — this skill fixes that.
Track fitness with Garmin Connect - view activities, health metrics, and training data from Garmin devices
Guidelines for creating high-quality datasets for LLM post-training (SFT/DPO/RLHF). Use when preparing data for fine-tuning, evaluating data quality, or designing data collection strategies.
Extract MQL5 articles and documentation. TRIGGERS - MQL5 articles, MetaTrader docs, mql5.com resources.