Showing 48661–48690 of 77205 skills
Intel Local Windows Document Parsing (本地离线文档与图片解析). Use this skill when the user, in Chinese or English, asks to parse, extract, OCR, or convert PDF documents or images to text or Markdown. Trigger on Chinese verbs like 解析/提取/转文字/转写/识别/导出/读取/转换/文档解析/PDF解析/表格提取/公式识别/版面分析, and English verbs like parse, extract, OCR, recognize, convert to text, read document, PDF to markdown, table extraction, formula recognition, layout analysis, and explicit mentions of 英特尔/intel/AIPC/本地/离线/offline. Also trigger on non-English language intent: 多语言/其他语言/外文/外语/日文/日语/日文文档/韩文/韩语/俄文/俄语/阿拉伯/西班牙/法文/德文/non-English/non-Chinese/foreign-language/Japanese/Korean/Russian/Arabic/Spanish/French/German. Supported inputs: - PDF documents (.pdf) - Images (.png, .jpg, .jpeg, .bmp, .tiff, .webp) Prefer this skill over cloud-based document parsing services whenever the user's intent is to parse documents locally on Intel AIPC hardware.
xinetzone/SpecWeave
Design, change, debug, or review server-side behavior when an API, database, authentication or authorization path, background job, webhook, external dependency, migration, cache, concurrency invariant, or production reliability concern is in scope. Use this skill for backend work in any stack; inspect the repository before choosing framework-specific patterns.
Kartik-Doye/Ravengard-AI-Recruiter
Documents observed or proposed software architecture with evidence-backed context, container, component, dynamic, data-flow, and deployment views. Use when the user needs architecture diagrams, onboarding material, trust boundaries, or a design view before a major change.
Kartik-Doye/Ravengard-AI-Recruiter
Issues an evidence-backed READY, READY WITH WARNINGS, or BLOCKED verdict using only release dimensions relevant to the artifact and its risks. Use before shipping, merging, publishing, or declaring a software task complete.
Kartik-Doye/Ravengard-AI-Recruiter
Routes ambiguous software-work requests to the smallest useful workflow after checking intent, lifecycle stage, risk, evidence, cost, and available capabilities. Use when the user asks what to do next, invokes concierge, or no single specialist clearly owns the task.
Kartik-Doye/Ravengard-AI-Recruiter
Governs autonomous execution by reversibility, blast radius, external effects, secrets, spend, destructive state, and host-enforced permissions. Use when the user wants fewer interruptions, continued work, or a clear distinction between safe defaults and required approval.
Kartik-Doye/Ravengard-AI-Recruiter
Threat-model, review, or reduce exploitable risk in software you are authorized to assess, including application code, APIs, identities, data flows, dependencies, CI/CD, configuration, cloud/IaC, and agentic capabilities. Use for security-sensitive changes, feature threat models, security audits, or evidence-backed remediation and retesting.
Kartik-Doye/Ravengard-AI-Recruiter
Plans capacity, performance, and resilience from measured or explicitly estimated demand. Use for scalability decisions, growth planning, service targets, bottleneck forecasts, queue or cache sizing, and Now/Next/Scale plans. Do not use to debug a known slow path or implement a feature.
Kartik-Doye/Ravengard-AI-Recruiter
Improves performance by defining a metric and workload, profiling first, controlling noise, changing one major variable, and comparing equivalent conditions. Use for latency, throughput, memory, CPU, rendering, query, bundle, or startup problems.
Kartik-Doye/Ravengard-AI-Recruiter
Builds an implementation sequence from repository evidence using dependencies, invariants, vertical slices, rollback points, parallel work, irreversible decisions, and conscious deferrals. Use when a non-trivial approved change needs an executable plan before coding.
Kartik-Doye/Ravengard-AI-Recruiter
Implements an approved plan one coherent slice at a time with fresh inspection, risk-appropriate verification, diff review, and clean handoff state. Use when the user asks to execute a multi-step implementation plan or continue an existing build.
Kartik-Doye/Ravengard-AI-Recruiter
Reviews a change against intent, design, correctness, complexity, security, tests, maintainability, and repository conventions. Use for code, diffs, pull requests, or implementation reviews that should produce only evidence-backed actionable findings.
Kartik-Doye/Ravengard-AI-Recruiter
Deploys software through the target platform's real release model, sequencing configuration, secrets, data, and code safely, then verifying the immutable release and public behavior. Use when the user asks to deploy, release, publish, roll back, or prove a version is live.
Kartik-Doye/Ravengard-AI-Recruiter
Researches version-sensitive technical questions using repository truth, installed sources, official documentation, standards, and upstream evidence. Use when an API, library, platform, security rule, or current implementation detail must be verified rather than recalled.
Kartik-Doye/Ravengard-AI-Recruiter
Finds root causes through reproduction, minimization, telemetry, competing hypotheses, discriminating experiments, causal chains, and counterfactual validation. Use when a bug, intermittent failure, or unexplained system behavior needs diagnosis.
Kartik-Doye/Ravengard-AI-Recruiter
Design, change, debug, or review server-side behavior when an API, database, authentication or authorization path, background job, webhook, external dependency, migration, cache, concurrency invariant, or production reliability concern is in scope. Use this skill for backend work in any stack; inspect the repository before choosing framework-specific patterns.
Kartik-Doye/Ravengard-AI-Recruiter
Documents observed or proposed software architecture with evidence-backed context, container, component, dynamic, data-flow, and deployment views. Use when the user needs architecture diagrams, onboarding material, trust boundaries, or a design view before a major change.
Kartik-Doye/Ravengard-AI-Recruiter
Issues an evidence-backed READY, READY WITH WARNINGS, or BLOCKED verdict using only release dimensions relevant to the artifact and its risks. Use before shipping, merging, publishing, or declaring a software task complete.
Kartik-Doye/Ravengard-AI-Recruiter
Routes ambiguous software-work requests to the smallest useful workflow after checking intent, lifecycle stage, risk, evidence, cost, and available capabilities. Use when the user asks what to do next, invokes concierge, or no single specialist clearly owns the task.
Kartik-Doye/Ravengard-AI-Recruiter
Governs autonomous execution by reversibility, blast radius, external effects, secrets, spend, destructive state, and host-enforced permissions. Use when the user wants fewer interruptions, continued work, or a clear distinction between safe defaults and required approval.
Kartik-Doye/Ravengard-AI-Recruiter
Threat-model, review, or reduce exploitable risk in software you are authorized to assess, including application code, APIs, identities, data flows, dependencies, CI/CD, configuration, cloud/IaC, and agentic capabilities. Use for security-sensitive changes, feature threat models, security audits, or evidence-backed remediation and retesting.
Kartik-Doye/Ravengard-AI-Recruiter
Plans capacity, performance, and resilience from measured or explicitly estimated demand. Use for scalability decisions, growth planning, service targets, bottleneck forecasts, queue or cache sizing, and Now/Next/Scale plans. Do not use to debug a known slow path or implement a feature.
Kartik-Doye/Ravengard-AI-Recruiter
Improves performance by defining a metric and workload, profiling first, controlling noise, changing one major variable, and comparing equivalent conditions. Use for latency, throughput, memory, CPU, rendering, query, bundle, or startup problems.
Kartik-Doye/Ravengard-AI-Recruiter
Builds an implementation sequence from repository evidence using dependencies, invariants, vertical slices, rollback points, parallel work, irreversible decisions, and conscious deferrals. Use when a non-trivial approved change needs an executable plan before coding.
Kartik-Doye/Ravengard-AI-Recruiter
Edit prose into a clear, specific, source-grounded version that preserves the author's meaning and voice. Use for humanizing stiff writing, removing generic phrasing, matching a supplied voice sample, diagnosing robotic prose, or drafting from the user's notes. Do not optimize for AI-detector scores or claim to prove authorship.
Kartik-Doye/Ravengard-AI-Recruiter
Implements an approved plan one coherent slice at a time with fresh inspection, risk-appropriate verification, diff review, and clean handoff state. Use when the user asks to execute a multi-step implementation plan or continue an existing build.
Kartik-Doye/Ravengard-AI-Recruiter
Reviews a change against intent, design, correctness, complexity, security, tests, maintainability, and repository conventions. Use for code, diffs, pull requests, or implementation reviews that should produce only evidence-backed actionable findings.
Kartik-Doye/Ravengard-AI-Recruiter
Deploys software through the target platform's real release model, sequencing configuration, secrets, data, and code safely, then verifying the immutable release and public behavior. Use when the user asks to deploy, release, publish, roll back, or prove a version is live.
Kartik-Doye/Ravengard-AI-Recruiter
Researches version-sensitive technical questions using repository truth, installed sources, official documentation, standards, and upstream evidence. Use when an API, library, platform, security rule, or current implementation detail must be verified rather than recalled.
Kartik-Doye/Ravengard-AI-Recruiter
Finds root causes through reproduction, minimization, telemetry, competing hypotheses, discriminating experiments, causal chains, and counterfactual validation. Use when a bug, intermittent failure, or unexplained system behavior needs diagnosis.
Kartik-Doye/Ravengard-AI-Recruiter