Results for “randomization”

Design and evaluate paid-ad experiments with hypotheses, randomization, sample-size calculations, guardrails, and decision rules for A/B and split tests.

Provides on-chain verifiable randomness for coin flips, dice rolls, raffles, shuffles, and game outcomes via the DARKSOL Random Oracle API on Base.

Randomly selects winners from lists, spreadsheets, or Google Sheets for giveaways, raffles, and contests with fair, transparent selection.

Identify cryptographic algorithms, key generation flaws, and potential decryption opportunities in ransomware samples using static and dynamic analysis.

Optimize a complete candidate context package by deduplicating, filtering, ordering, and allocating its token budget. Use when retrieved or assembled material is noisy or exceeds the useful context budget; use context-ranking for scoring chunks and context-compression for shrinking selected content.

Use before sensitive, clinical, identifying, or raw interview data is placed in front of an AI tool, when transcripts or student materials need de-identification, or when a data-minimization gate must run before any analysis or drafting.

Optimizes Qdrant query performance for large limits across multiple shards by using Poisson-distributed subsampling to reduce inter-shard data transfer.

Write effective fuzzing harnesses across languages to improve code coverage and find bugs in your system under test.

Generate personalized status briefings by pulling from configured data sources like GitHub, email, Teams, and Slack, then synthesizing updates in your own communication style.

Rewrites text to remove AI writing patterns and add a natural, human voice, based on Wikipedia's guide to signs of AI writing.

Improves AI skills for activation, clarity, and cross-model reliability through benchmarking, salience tuning, and regression triage.

Elite UX/UI & Advanced GSAP Motion Engineer. Enforces Python-driven true randomization for layout variance, strict AIDA page structure, wide editorial typography (bans 6-line wraps), gapless bento grids, strict GSAP ScrollTriggers (pinning, stacking, scrubbing), inline micro-images, and massive section spacing.

Picks random winners from lists, spreadsheets, or Google Sheets for giveaways, raffles, and contests. Ensures fair, unbiased selection with transparency.

Reviews parsers, deserialization, uploads, archives, YAML/JSON/XML/pickle, paths, templates, SSRF, and unsafe loaders.

Optimize Kubernetes cluster costs by right-sizing resources, configuring autoscalers, using spot instances, and monitoring spend.

Use to draw a defensible sample of support conversations for QA review, an audit or a manual analysis, so the results generalise to the population rather than to whatever was easy to pull. Trigger for "which tickets should we review", "how do we pick a sample", "is our QA sampling representative", stratified or risk-based sampling, review coverage design, or a finding based on a handful of hand-picked tickets.

Humanize text: strip AI-isms and add real voice.

Rewrite text to remove AI writing patterns and add a natural, human voice.

Humanize text: strip AI-isms and add real voice.

润色中文学术论文，识别并替换模板化、机械化的AI表达，使文本更自然、更符合人类学者的写作习惯。

`task-agent`/`review-agent`: use when image layers, build context, runtime user, secrets, health checks, shutdown, or provenance change; skip when container behavior is unaffected.

Designs and governs recursive self-improvement loops where an agent mines its own failures and proposes edits to its own harness, prompts, or workflow, covering acceptance gates, diversity preservation, and the optimization ladder.

Plan, execute, document, and retest authorized security assessments of AI agents and multi-agent workflows using safe adversarial cases, synthetic identities, canaries, and evidence-based findings. Use when defining red-team rules of engagement, assessing prompt injection or excessive agency, testing tool and identity boundaries, evaluating memory or cross-agent attacks, scoring a campaign, or verifying remediation in an approved environment.

Run autonomous optimization loops that iteratively improve artifacts against evaluators using hypothesis tree refinement, without overfitting.

Build and debug Retrieval-Augmented Generation pipelines — chunking, embedding, retrieval, reranking

Compresses long K-line (candlestick) data into a fixed-length sequence using OHLC aggregation rules and applies min-max normalization.

Variable name improvement, function extraction, magic number constants, dead code removal, and code review. For refactoring and PR review — does not change behavior. Don't use for bug/security (Judge), new tests (Radar), architecture (Atlas), or feature implementation (Builder).

Systematically fuzz web applications for hidden content and input validation vulnerabilities across directories, files, parameters, and authentication bypasses.

Designing and evaluating AI/ML systems: prompt engineering, RAG design, LLM application patterns, AI safety, evaluation frameworks, MLOps, cost optimization. Use for AI pipelines or eval harnesses.

Normalize SKILL.md artifacts into Scheduling-Structural-Logical (SSL) JSON representations using a conservative multi-pass extraction pipeline.

基于 anchor 论文、topic 关键词或当前 wiki 状态，产出一份排好序的候选论文 shortlist，供用户或上游 skill 决定是否进一步 `/ingest`。当用户问 "接下来该读什么"、"找和这篇相似的论文"、"推荐相关工作"、"这个方向周围有什么" 时触发；`/ingest --discover` 也会内部调用本 skill。本身不 ingest，只提出候选。

Prevents AI-introduced regressions with sandbox-mode API testing, automated bug-check workflows, and patterns that catch blind spots where the same model writes and reviews code.