Loading...
Loading...
Found 35 Skills
Multi search engine integration with 17 engines (8 CN + 9 Global). Supports advanced search operators, time filters, site search, privacy engines, and WolframAlpha knowledge queries. No API keys required.
Guides research engineering and science on LLM tokens—hypotheses about context use, tokenization, compression, and inference efficiency; rigorous benchmarks (tokens per task, quality–cost Pareto); ablation design; instrumentation and reproducible logs; and research memos that inform product decisions. Use when designing token-efficiency experiments, measuring context utilization, comparing compression or routing methods, analyzing tokenizer effects, or writing technical reports on token/cost trade-offs—not for phased cost roadmaps and owners (ai-token-improvement-plan-engineer), production context pipeline implementation (ai-context-engineer), single-prompt edits (prompt-engineer), general non-token AI research (ai-researcher), or shipping features (ai-engineer).
An uncompromising Academic Research Engineer. Operates with absolute scientific rigor, objective criticism, and zero flair. Focuses on theoretical correctness, formal verification, and optimal implementation across any required technology.
Guides ML/research engineering for safeguards—safety classifier development, harm benchmarks and eval suites, labeled dataset design, fine-tuning and ablations, calibration and slice analysis, attack-surface research memos, and promotion criteria for new moderation models. Use when building or evaluating guardrail models, designing safety benchmarks, measuring precision/recall on policy categories, comparing mitigation techniques, or writing research reports on classifier improvements—not for production inference gateways (ml-infrastructure-engineer-safeguards), PII/leakage privacy research (privacy-research-engineer-safeguards), red-team attack campaigns (ai-redteam), AI governance policy (ai-risk-governance), general non-safety research (ai-researcher), or token-efficiency studies (research-engineer-scientist-tokens).
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).
Guides users to integrate text-search-engine SDK for Chinese/English fuzzy search with Pinyin support. Invoke when user wants to add fuzzy search, pinyin search, or text matching.
Adversarial robustness engineering for ML/AI—evasion, poisoning, extraction, membership-inference threat models; robust training, sanitization, detectors; ASR/certified evals; lab model attacks; data-pipeline integrity; production I/O guardrails (classical ML and LLM/multimodal). Use for adversarial examples, robustness suites, poison audits, deploy guardrails—not LLM app red team (ai-redteam), governance (ai-risk-governance), safety classifier R&D (ml-research-engineer-safeguards), safeguard serving (ml-infrastructure-engineer-safeguards), privacy research (privacy-research-engineer-safeguards), AppSec pentest (penetration-tester).
This skill should be used when the user asks for markup detection, detect manipulation, image tampering, deepfake detection, document integrity, hidden markup, metadata forensics, EXIF analysis, content authenticity, synthetic media, altered image, C2PA, or provenance verification across documents, images, and video. Guides workflow-level assessment of visual tampering indicators (splicing, cloning, inconsistent lighting or shadows, compression artifacts), metadata and provenance checks (EXIF, hashes, source chain), document revision and hidden markup (tracked changes, comments, invisible text), synthetic-media and deepfake red flags, watermarking and content-credentials concepts, and structured reporting with confidence levels and explicit limitations—not training detection models (ml-research-engineer-safeguards), cryptographic watermark design (cryptographer-specialist), full digital forensics lab attribution or legal conclusions, or blockchain-only tracing unless the user scopes on-chain context.
Convert YouTube videos into SEO-optimized blog posts. Extract video titles, descriptions, and content, then generate search-engine-friendly blog posts with embedded videos, cover images, and optimized metadata. Automatically generates English filenames and saves them to the configured Hexo blog posts directory.
Unified YouTube script creation for cardiology channels in Hinglish. Uses the COMPLETE research-engine pipeline (channel scraping, comment analysis, narrative monitoring, gap finding, view prediction) combined with RAG + PubMed for evidence. Data-driven topic selection, 15-30 min educational videos with 6-point voice check.
Guides quantitative research for markets and finance—research question framing, data sourcing and quality checks, descriptive and inferential statistics, time series and panel methods (high level), factor and signal research, backtest design and pitfalls (lookahead, survivorship), risk metrics (volatility, drawdown, Sharpe limitations), regime and stress analysis, and reproducible notebooks or reports with explicit limitations and uncertainty communication. Use when the user mentions "quantitative research", "quant researcher", "factor research", "signal backtest", "time series analysis", "panel regression", "alpha research", "Sharpe ratio analysis", "survivorship bias", "lookahead bias", "econometric analysis", or "risk factor model". Not for production ML pipelines (data-scientist, ml-research-engineer), equity narrative reports (equity-research skills), SOX accounting (financial-statements), legal investment advice, or trading execution systems (senior-software-engineer).
Guides AI ops leadership—LLM SRE, model/prompt releases, eval/incidents, cost/capacity, vendors, and cross-functional cadence. Use for AI platform ops, LLM SLAs, incidents, rollout governance, unit economics, red-team/eval gates, and team rituals—not memory (ai-memory-developer), context code (ai-context-engineer), security programs (cybersecurity), token roadmaps (ai-token-improvement-plan-engineer), solution architecture (applied-ai-architect-commercial-enterprise), skills portfolio (ai-skill-manager), or vertical AI product eng management (engineering-manager-vertical-ai-products). Prompt/eval team management and golden-set release policy: engineering-manager-agent-prompts-evals. Safeguard inference platform: ml-infrastructure-engineer-safeguards. Safeguard model research: ml-research-engineer-safeguards.