117건 · 관련도순
Use ast-grep (sg) to search, lint, and rewrite code across large codebases using AST pattern matching. A blazing-fast alternative to regex-based code transformations that understands syntax structure.
한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.
Rewrite recurring code patterns with syntax-aware matching so agents can run migration codemods more safely than plain regex search and replace.
한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.
Use when working on or testing imp-server and its HTTP APIs - OpenAI/Anthropic endpoints, /v1/chat/completions, /v1/messages, /v1/responses, SSE streaming, tool calling, json_schema/regex/GBNF constrained decoding, thinking/reasoning_content, cache_control/prefix cache, model loading and swapping, request priority, X-Request-Id, OTLP tracing / traceparent / Jaeger, /metrics, container env (IMP_SET), "server returns 404/garbage", API compliance. Do NOT use for CLI-only inference (imp-cli), kernel work (sm120-cuda-expert), or pure output-quality checks (check-degeneration).
한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.
Statically enforce a privacy/redaction boundary on an artifact tree before publication, the way an AST checker enforces a code contract. Builds a two-tier gate — a shape-based deny-list (regex over identifier shapes) plus a structure-aware tier that parses JSON/HTML/SVG/Markdown/code and asserts sensitive content cannot appear in meaningful positions — with a strict exit-code contract, label-only output that never echoes the patterns themselves, and false-positive narrowing instead of suppressions. Use when gating a public mirror, a disclosure draft, a wire-capture export, or any artifact that must pass a leak check before it ships, and when a plain line-grep is too coarse to trust.
한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.
fast-check patterns for JS/TS — 6 canonical property categories with worked examples targeting agent-studio utilities (path normalization, safe-json, glob-to-regex, routing logic)
한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.
Use when asked to run AST-based structural search, lint, or rewrite of code when regex is too fragile. Not for remote, credential, publish, deploy, or irreversible changes.
한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.
Remove telltale AI-writing patterns from README, docs, and user-facing text. Must be done line-by-line, manually. No regex. Use after agents write any user-visible prose.
한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.
Remove AI-writing tells from README, docs, and user-facing text. Must be done line-by-line, no regex. Use after agents write any user-visible prose.
한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.
Find and list functions in a binary by name, address, regex, or byte pattern. Use as the starting point for binary analysis, to locate specific functions, or to enumerate all functions matching criteria.
한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.
Outlines: structured JSON/regex/Pydantic LLM generation.
한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.
Controle saída de LLM com regex e gramáticas, garanta geração válida de JSON/XML/código, aplique formatos estruturados e construa fluxos de trabalho multi-etapas com Guidance - framework de geração restrita da Microsoft Research
한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.
Geração estruturada rápida e serving para LLMs com RadixAttention para cache de prefixos. Use para saídas JSON/regex, decodificação restrita, workflows com agentes que fazem chamadas de ferramentas, ou quando você precisa de 5× mais rápido que vLLM com compartilhamento de prefixos. Alimenta 300.000+ GPUs na xAI, AMD, NVIDIA e LinkedIn.
한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.
Detects prompt injection attacks targeting LLM-based applications using a multi-layered defense combining regex pattern matching for known attack signatures, heuristic scoring for structural anomalies, and transformer-based classification with DeBERTa models. The detector analyzes user inputs before they reach the LLM, flagging direct injections (system prompt overrides, role-play escapes, instruction hijacking) and indirect injections (encoded payloads, multi-language obfuscation, delimiter-based escapes). Based on the OWASP LLM Top 10 (LLM01:2025 Prompt Injection) and Simon Willison's prompt injection taxonomy. Activates for requests involving prompt injection detection, LLM input sanitization, AI security scanning, or prompt attack classification.
한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.
Parse Apache and Nginx access logs to detect SQL injection attempts, local file inclusion, directory traversal, web scanner fingerprints, and brute-force patterns. Uses regex-based pattern matching against OWASP attack signatures, GeoIP enrichment for source attribution, and statistical anomaly detection for request frequency and response size outliers.
한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.
Customize WP Rocket behavior from a third-party plugin / theme via filter hooks — exclude URIs / cookies / user agents / REST API namespaces from caching, configure CDN URL rewrites, extend lazy load handling, override capability requirements, hook into Action Scheduler integration. Critical guidance — rocket_cache_reject_uri takes URI patterns (regex-like), NOT full URLs; rocket_cache_reject_* filters all expect arrays. The rocket_buffer filter is the FULL HTML output filter — extremely powerful but dangerous; one fatal error in the callback breaks every cached page until WP Rocket is disabled. Use when extending WP Rocket's default rules, NOT for cache invalidation (see wp-rocket-cache-invalidation). Triggers on rocket_cache_reject_, rocket_cdn_, do_rocket_lazyload, rocket_buffer, rocket_capacity, "exclude from WP Rocket cache".
한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.
Per-toolkit hardening audit loop for NV oOS Pro tools. Systematically scans each addons/pro/includes/tools/<toolkit> (and its plugins/nvoos-content-graph-pro mirror) for the recurring production failure classes — unguarded shell calls that fatal on exec-disabled hosts, calls to nonexistent client methods, string-assuming parsing of provider responses that may be arrays, provider enum/service mismatches, metric/source column drift that silently returns 0, secondary-table denominator gaps, the Chart.js fixed-height loop, misleading native-source errors, and silent import truncation that reports partial writes as success — then fixes, tests (Docker PHPUnit), and validates (phpcs both standards) before moving to the next toolkit. Use when asked to audit a toolkit, review the X tools for similar issues, do the same for the other toolkits, or continue the toolkit audit loop. The first case study (document-generation) found 3 fatal bugs + 1 broken regex; the food-beverage pass added classes 5–9.
한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.
Use WordPress' HTML API for safe server-side HTML inspection and mutation instead of regex, fragile string replacement, or DOMDocument. Covers WP_HTML_Tag_Processor, WP_HTML_Processor, set_attribute, remove_attribute, add_class, remove_class, set_modifiable_text, serialize_token, custom data attribute name mapping, and WP 6.9 behavior where attribute/text setters escape character references. Use when plugin code modifies rendered HTML, block output, shortcodes, content filters, widget markup, email fragments, or user-provided HTML.
한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.
Scans .NET code for ~50 performance anti-patterns across async, memory, strings, collections, LINQ, regex, serialization, and I/O with tiered severity classification. Use when analyzing .NET code for optimization opportunities, reviewing hot paths, or auditing allocation-heavy patterns.
한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.
Helps an AI assistant work with the Miraheze wiki farm — writing wiki requests that get approved, navigating ManageWiki, doing common how-to tasks (templates, skins, permissions, custom domains, backups), writing regex for MediaWiki search-and-replace, AND writing actual article and page content for Miraheze-hosted wikis. Miraheze does NOT ban generative AI; AI-written content is permitted (subject to per-wiki rules). MADE BY SQERSTERS
한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.
在授权渗透测试中挖掘 SQL/NoSQL 注入（SQLi、NoSQLi，含 WAF 绕过、盲注、堆叠查询、类型混淆注入）。当用户输入拼进 SQL/NoSQL 查询时使用——典型场景：id/搜索/排序/过滤参数、数组键当 SQL 片段、PHP 类型混淆、MongoDB `$where`/`$regex`、堆叠查询到 xp_cmdshell。适用目标类型 Web / REST API。触发场景包括用户说"测下 SQL 注入""这个参数能不能注入""盲注/时间注入试试""NoSQL/MongoDB 注入看一下"。输出：注入点 + 类型 + 证据的 finding（含 killed 记录）。
한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.
Use ast-grep (sg) for AST-aware code search and rewrite across 25 languages. Trigger for structural code matching or deterministic codemods: find every function/call/class/import shaped like X, rewrite console.log to logger.info, strip `as any`, migrate require() to import, find empty catch blocks or missing await, and scan/apply YAML rules. Prefer this over rg/grep when the target is syntax shape rather than text; use rg for string contents, comments, filenames, or regex-style byte searches.
한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.
Apply modern Swift language patterns and idioms for non-concurrency, non-SwiftUI code. Covers if/switch expressions (Swift 5.9+), typed throws (Swift 6+), result builders, property wrappers, opaque and existential types (some vs any), guard patterns, Never type, Regex builders (Swift 5.7+), Codable best practices (CodingKeys, custom decoding, nested containers), modern collection APIs (count(where:), contains(where:), replacing()), FormatStyle (.formatted() on dates, numbers, measurements), and string interpolation patterns. Use when writing core Swift code involving generics, protocols, enums, closures, or modern language features.
한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.
Searches and explores Burp Suite project files (.burp) from the command line. Use when searching response headers or bodies with regex patterns, extracting security audit findings, dumping proxy history or site map data, or analyzing HTTP traffic captured in a Burp project.
한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.
Implements data loss prevention policies using Microsoft Purview to protect sensitive information across Exchange Online, SharePoint, OneDrive, Teams, endpoint devices, and Power BI. The analyst configures sensitivity labels with encryption and content marking, creates DLP policies using built-in and custom sensitive information types with regex patterns, Dağıt:s endpoint DLP rules to control file operations on Windows and macOS devices, and monitors policy effectiveness through Activity Expl...
한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.