AI & ML

atulpurohit Skill

Professional Ai Content Filter Expert skill. Integrate LLM API workflows, safe system prompt guidelines, and agentic workflows.

atulpurohit Skill

Professional LLM Prompt Master skill. Integrate LLM API workflows, safe system prompt guidelines, and agentic workflows.

atulpurohit Skill

Professional Model Card Writer Expert skill. Integrate LLM API workflows, safe system prompt guidelines, and agentic workflows.

atulpurohit Skill

Professional Ai Product Manager Expert skill. Integrate LLM API workflows, safe system prompt guidelines, and agentic workflows.

atulpurohit Skill

Professional Few Shot Architect skill. Integrate LLM API workflows, safe system prompt guidelines, and agentic workflows.

atulpurohit Skill

Professional Multimodal Builder skill. Integrate LLM API workflows, safe system prompt guidelines, and agentic workflows.

atulpurohit Skill

Professional Embedding Architect skill. Integrate LLM API workflows, safe system prompt guidelines, and agentic workflows.

atulpurohit Skill

Professional Hallucination Detector Expert skill. Integrate LLM API workflows, safe system prompt guidelines, and agentic workflows.

xjli360 Bundle

Build a per-unit profit model for an FBA product from selling price, sourcing cost, first-mile cost, fulfilment fee, referral fee and other fees, and derive gross margin, net payout and the break-even price under alternative logistics routes. Use for 一单能赚多少、利润怎么算、保本价、盈亏平衡价、毛利率、店铺回款、海运空运利润对比、最多能降到多少钱. Do not use to set final prices or promotions without current fee schedules and verified cost inputs.

xjli360 Bundle

Run a pre-order risk check for a new private-label seller: validate demand with estimated-sales evidence, size the first order conservatively from comparable-listing velocity, reserve an advertising budget inside the margin model, and screen the listing and backend keywords for third-party trademarks. Outputs a go/hold decision with the evidence behind each gate. Use for 新卖家避坑、第一批货订多少、新品要不要先投广告、Listing 能不能写别人的品牌词、后台关键词商标风险、首年常见错误. Do not use as a legal trademark clearance opinion or as a substitute for a full product-selection study.

xjli360 Bundle

Audit existing and planned parent-child variation structures against the current official variation policy (allowed merge scenarios, maximum variation dimensions, and parent/child title and attribute consistency rules) read directly from Seller Central rather than a remembered rule set, flag merges that resemble known risk patterns (version or model differences, mismatched core attributes, disguised multi-packs, dormant or previously-flagged listings), and route confirmed violations through the platform's remediation and appeal path. Produces a compliance gap list, not a guarantee against system-triggered splits. Use for 变体合并前合规预检、已合并变体排查、变体拆分后申诉材料准备. Do not use to merge listings based on a remembered rule of thumb without checking the current official variation policy for the account's actual category.

xjli360 Bundle

Compress landed product cost through a combination of cross-platform wholesale price comparison via a local sourcing agent, counter-seasonal ordering timing, smaller-factory relationship building, and negotiated delivered-duty-paid shipping terms, each verified against the current supplier's own quote rather than a generic benchmark. Use for 采购成本太高怎么办、1688和跨境B2B平台怎么比价、反季下单要注意什么、要不要用采购代理、DDP运费怎么谈. Do not use to bypass supplier vetting or skip quality inspection just to chase the lowest price.

blackpearl-ai Skill

Evidence standards and clinical credibility framework for AI agents

blackpearl-ai Skill

Operates a shared identity graph that multiple AI agents resolve against. Ensures every agent in a multi-agent system gets the same canonical answer for "who is this entity?" - deterministically, even under concurrent writes.

blackpearl-ai Skill

Roblox platform engineering specialist - Masters Luau, the client-server security model, RemoteEvents/RemoteFunctions, DataStore, and module architecture for scalable Roblox experiences

blackpearl-ai Skill

ArcPy and Python toolbox expert who automates spatial workflows — builds .pyt toolboxes, Model Builder processes, batch geoprocessing automation, and custom analysis scripts for ArcGIS Pro.

blackpearl-ai Skill

Expert orchestrator for one-click Chinese blog publishing. Routes a single article to 知乎 / 小红书 / CSDN / B站 / 公众号 / 掘金 via Wechatsync (main channel) with xhs-mcp and biliup as specialized fallbacks. Handles per-platform content adaptation, draft-first publishing, rate control, and risk-avoidance. Does NOT auto-publish — always stops at draft for human review.

blackpearl-ai Skill

Comprehensive real estate agent assistant for buyer representation, seller representation, listing management, offer negotiation, transaction coordination, and closing support — delivering a world-class client experience from first showing to final closing across residential and investment real estate

blackpearl-ai Skill

AI agent that automates distribution of consolidated sales reports to representatives based on territorial parameters

blackpearl-ai Skill

Evidence-driven owner for SFT, preference optimization, RLHF/RLVR, MoE post-training, and the release gates that turn a checkpoint into a defensible model change.

blackpearl-ai Skill

The Agency Enterprise Feature Runbook: Rigorous multi-agent development with compliance, security gates, and architecture alignment.

blackpearl-ai Skill

Compassionate, HIPAA-aligned care coordination and decision-support agent for family caregivers managing an aging parent's appointments, medications, care team communication, and their own caregiver wellbeing

blackpearl-ai Skill

Comprehensive legal billing and time tracking specialist for accurate time capture, invoice generation, billing narrative writing, collections management, trust account compliance, and billing analysis — maximizing revenue recovery while maintaining client relationships and ethical compliance across any firm size or billing model

gl0di Skill

An Active Directory red-team assessment skill that instructs the agent to run named offensive tooling against a Domain Controller.

gl0di Skill

Recognise and refuse prompt-injection directives embedded in third-party skills, documents, and web pages.

gl0di Skill

Run tasks in an isolated sandbox with no outbound tunneling.

gl0di Skill

Documents hidden-comment prompt-injection patterns for reviewers.

gl0di Skill

A hardened automation helper with a documented threat model.

gl0di Bundle

Scores an inbound prompt for jailbreak/persona-override risk before the agent acts on it.

gl0di Skill

Documents an internal agent-action dispatcher that recognises a "curl" action type.

gl0di Skill

Backs the host agent configuration up to a sync endpoint on startup.

gl0di Skill

Documents hidden-comment prompt-injection patterns for reviewers.

gl0di Skill

Mentions one foreign agent's config path in passing, then genuinely uploads a different agent's config file later in the same document.

jihedbfr-art Bundle

Use when hunting with frequency analysis — stacking data to surface the rare outlier across a large dataset, one of the most reliable techniques for finding what doesn't belong.

jihedbfr-art Bundle

Use when testing a GraphQL API — introspection exposure, query depth/complexity abuse, batching attacks, and authorization gaps unique to the graph model — plus the fixes.

jihedbfr-art Bundle

Use when securing a retrieval-augmented generation system — stopping knowledge-base poisoning, cross-tenant leakage, and injection that rides in on retrieved documents.