В каталоге 185 369 навыков в 14 категориях.
humanizeracademic は、学術・医療領域の英語文を「正確さを維持したまま」自然で読みやすい文体に整えるためのスキル。
Humanizer 中文学术版——当用户要求润色论文、去除AI味、降低AIGC检测率,或说"帮我改改这段""这段读起来像AI写的"时触发。
Remove signs of AI-generated writing from text. Use when editing or reviewing text to make it sound more natural and hum...
Edit-Pass für bestehenden deutschen Text: Register/Rhythmus messen, belegtreu redigieren, Naturalness prüfen, KI-Schreib...
Write or rewrite English into ASD-STE100 Simplified Technical English and strip AI artifacts (decorative emojis, Markdow...
Detects and corrects Korean AI writing patterns to transform text into natural human writing. Based on scientific lingui...
Lint and humanize robotic or stiff prose using a deterministic local Node.js analyzer. Eight lexical packs (EN, ID, ES,...
Remove AI writing patterns and add human voice to any text. Use when the user says "humanize this", "make it sound human...
Скилл для очеловечивания русскоязычного текста. Убирает признаки AI-генерации, делает текст живым. Используй ВСЕГДА, ког...
Редактор русского текста - убирает признаки AI-генерации, канцелярит и воду, сохраняя факты и добавляя голос. 38 паттерн...
Rewrite text so it reads like a real person wrote it, not an AI. Auto-detects Russian vs English and applies the matchin...
Use when: нужно очеловечить (humanize) сгенерированный ИИ текст на русском. Убирает 25 машинных паттернов, делает язык ж...
Use when a user asks to edit Russian prose that sounds formulaic or machine-generated while preserving its meaning and a...
Biên tập văn bản tiếng Việt máy móc, sáo rỗng hoặc đều giọng để câu chữ tự nhiên, rõ và đúng ngữ cảnh. Dùng khi người dù...
Rewrite AI-sounding text so it reads naturally without changing what it says. Use when editing or reviewing prose for in...
检测并去除中文文本中的 AI 生成痕迹,使其更像人类自然书写。 覆盖内容模式(夸大意义、宣传语言、模糊归因)、语言模式(AI 高频词、三段式、同义词循环)、 风格模式(破折号滥用、粗体堆砌、表情符号)三大类 24 种 AI 写作特征的识别与...
去除文本中的 AI 生成痕迹。适用于编辑或审阅文本,使其听起来更自然、更像人类书写。 基于维基百科的"AI 写作特征"综合指南。检测并修复以下模式:夸大的象征意义、 宣传性语言、以 -ing 结尾的肤浅分析、模糊的归因、破折号过度使用、三段...
Use when the user wants final-stage Chinese prose humanization after facts, structure, terminology, and evidence are alr...
编辑中文文章、评论和文档中的空话、重复及模板化表达,让文字更自然,同时保留事实、确定程度和作者声音。适用于润色已有文本,不用于判断作者身份或保证通过 AI 检测器。
检测并去除文本中特定的 AI 生成痕迹,使其更像人类自然书写。 当用户明确提及 AI 写作特征、机器生成感、ChatGPT 风格或需要去除 AI 痕迹时使用。 专注于修复:过度强调意义、宣传性语言、-ing 形式肤浅分析、模糊归因、破折号滥...
识别并移除 AI 生成文本的痕迹,使其更加自然和人性化。适用于编辑或审查文本时使用。基于维基百科全面的"AI 写作迹象"指南。可检测并修复以下模式: 过度夸大的象征意义、促销性语言、肤浅的 -ing 分析、模糊的归因、破折号过度使用、三段式...
编辑中文文本,去掉套话、机械重复、夸张修辞和纠错过程残留,同时保留事实、作者语气与必要限定。适用于润色讲稿、技术说明、报告和一般文章。
Use when removing AI writing痕迹 from Chinese text to make it sound more natural and human-written.
中文降 AI —— 去除中文文本中的 AI 生成痕迹,使其更自然、有人味。适用于编辑或审阅中文文本(公文、月报、论文、 宣传稿、汇报材料等)去除"AI腔"。基于维基百科"AI 写作特征"指南翻译扩充,并针对中文政务/学术 文稿补充专项规则。...
Automate Humanloop tasks via Rube MCP (Composio). Always search tools first for current schemas.
Hume integration. Manage data, records, and automate workflows. Use when the user wants to interact with Hume data.
Hume AI Octave TTS and EVI speech-to-speech configs: synthesize speech and manage EVI configs. Trigger phrases: hume, hu...
Humi integration. Manage data, records, and automate workflows. Use when the user wants to interact with Humi data.
Prevent overconfidence, acknowledge limitations, be honest about uncertainties
Structured reasoning framework for AI agents — turns plans, hypotheses, observations, evaluations, decisions, and reflec...
Complete HUMMBL Base120 mental models framework with all 120 models across 6 transformations (Perspective, Inversion, Co...
Hummingbot trading bot framework - automated trading strategies, market making, arbitrage, connectors for crypto exchang...
Discover, bet on, track, and settle Hunch prediction markets in natural language. Trigger when a user wants to bet, take...
Produces the first hundred days as a bandwidth-budgeted, sequenced plan with the reporting cadence installed in week one...
Create irresistible offers using the Value Equation, bonus stacking, risk-reversing guarantees, and ethical scarcity. Us...
Write Hungarian that sounds human. Not formal, not robotic, not AI-generated.
Maps the `hunkdiff/extension` authoring surface for Hunk, the terminal diff viewer — hiding or reordering reviewed files...
Prepares, publishes, verifies, and curates Hunk releases. Use for release metadata, benchmarks, tags, publishing, releas...
Interacts with live Hunk diff review sessions via CLI. Inspects review focus, navigates files, hunks, and exact lines, r...
Hypothesis-driven threat hunting with MITRE ATT&CK mapping
Expert guidance for proactive threat hunting. Use this when the user asks to "hunt" for threads, IOCs, or specific TTPs.
Finds root cause before applying fixes for errors, crashes, regressions, failing tests, broken behavior, and screenshot-...
Finds root cause before any fix. Use when something errors, crashes, regresses, or used to work. Not for code review or...
- Enumerate a username across hundreds of platforms with sherlock, maigret and WhatsMyName, then correlate and confirm w...
Enumerate a username across hundreds of platforms with sherlock, maigret and WhatsMyName, then correlate and confirm whi...
Active Directory attack hunting - enumeration to domain dominance. Spray-safe (lockout gate), AS-REP/Kerberoast, ACL + A...
API attack hunting (REST / GraphQL / gRPC) - BOLA/IDOR, BFLA, mass assignment, excessive data exposure, auth/JWT, intros...
Hunt for a specific APT/threat actor in your environment. Use when you have a threat actor name or GTI collection ID and...
Hunt ASP.NET-specific surface — ViewState deserialization (signed-only vs encrypted), machineKey recovery, dual-parser M...
9 distinct paths. ATO is a destination class, not a single bug — each path below is a primitive that becomes Critical on...
Hunt account takeover taxonomy — 9 distinct paths to ATO, plus chains. Paths: (1) password reset flaws (host header inje...
Hunt account takeover taxonomy
Auth bypass and ATO hunting - legacy protocol matrix (XMLRPC, SharePoint /_vti_bin/, EWS, Citrix, etc.), JWT manipulatio...
Hunting skill for auth bypass vulnerabilities. Built from 12 public bug bounty reports across SAML XSW / parser-differen...
Business-logic flaw hunting - workflow/state bypass, price/quantity tampering, negative/overflow values, coupon/refund a...
Hunt Missing/Weak Rate Limiting — login brute force, OTP/2FA brute force (10^6), credential stuffing, username/email enu...
Drive Burp Suite over its MCP server as an AI triage + attack layer - review proxy history for signals, replay via Repea...
Hunting skill for business logic vulnerabilities. Built from 12 public bug bounty reports. Covers coupon-race-stacking (...
Web cache poisoning + cache deception hunting - unkeyed input poisoning, cache-key analysis, path-confusion deception, h...
Hunting skill for cache poison vulnerabilities. Built from 10 public bug bounty reports including X-Forwarded-Host poiso...
1. GET the form/endpoint that shows a CAPTCHA to understand its field name (usually g-recaptcha-response, captcha, captc...
Hunt CAPTCHA Bypass — 6 distinct patterns: (1) CAPTCHA field simply omitted from the request (server-side validation abs...
Hunt CI/CD pipeline vulnerabilities — GitHub Actions workflow injection (pull_request_target + untrusted input), Jenkins...
CI/CD pipeline attack hunting (GitHub Actions focus) - pwn requests (pull_request_target), script injection, self-hosted...
Hunt CI/CD pipeline vulnerabilities — GitHub Actions workflow injection (pull_request_target Pwnrequest + ${{ }}-into-sh...
Clickjacking (UI Redressing) lets an attacker load a target page inside a transparent iframe on a malicious site. The vi...
Hunt Clickjacking — missing X-Frame-Options / CSP frame-ancestors lets an attacker embed the target page in an invisible...
Cloud attack hunting for AWS / Azure / GCP - credential discovery, metadata SSRF, IAM privesc, service enumeration, pers...
Hunt cloud / infrastructure misconfigurations. AWS: public S3 buckets (s3:GetObject anonymous), permissive bucket polici...
Shared discipline for every hunt-* skill: scope and authorization gating, the two-account rule, the confirmation gate th...
Hunt CORS Misconfiguration — origin-reflection with credentials, null-origin trust, subdomain-regex bypass (unanchored v...
Hunt CORS Misconfiguration — wildcard with credentials, null origin, regex with subdomain trust, pre-flight bypass, post...
Hunt for credential access techniques like LSASS dumping or browser credential theft. Use when searching for evidence of...
Hunting skill for csrf vulnerabilities. Built from 10 public bug bounty reports. Use when hunting csrf on any target.
Hunting skill for csrf vulnerabilities. Built from 15 public bug bounty reports including modern variants — SameSite=Lax...
Skill-set loader for /hunt orchestrator. Fingerprints the target, picks the right platform attack skills, and loads the...
DOM-based attacks execute in the victim's browser — the server often never sees the payload, so WAFs and server-side inp...
Hunt client-side DOM vulnerabilities
Hunt client-side DOM vulnerabilities — DOM Clobbering (overwrite JS globals via HTML injection), PostMessage hijacking (...
Hunt mishandling of exceptional conditions — feed an endpoint malformed/unexpected input (wrong type, broken JSON, overs...
Hunt FastAPI-specific vulnerabilities: dependency injection gaps, Pydantic coercion, and OpenAPI mining.
OAuth and SAML attack hunting - redirect_uri bypass, state CSRF, SAML XSW (XSW1-XSW8), signature stripping, comment inje...
Generic GraphQL bugs (IDOR, mass assignment, introspection, batching abuse — see hunt-graphql)
Hunt fintech-specific GraphQL vulnerabilities: money-movement mutations (transfers, redemptions, withdrawals, card top-u...
Hunt Forgot Password / Account Recovery Authentication Flaws — 5 distinct patterns: (1) username enumeration via differe...
Hunting skill for graphql vulnerabilities. Built from 3 public bug bounty reports. Use when hunting graphql on any targe...
Hunting skill for graphql vulnerabilities. Built from 12 public bug bounty reports across IDOR via node() / GID, mutatio...
Hunt gRPC vulnerabilities — server reflection enabled (enumerate all services/methods), missing authentication / metadat...
Hunt gRPC vulnerabilities — server reflection enabled (enumerate all services/methods), missing authentication on intern...
Show available THRUNT threat hunting commands and artifact layout
Hunt Host Header Injection — password reset poisoning → ATO, web cache poisoning via unkeyed Host/X-Forwarded-Host, rout...
Hunt Host Header Injection — password reset poisoning → ATO, cache poisoning via unkeyed host, X-Forwarded-Host injectio...
Hunt HTML Injection — user-supplied input is rendered as raw HTML in the response without sanitisation, allowing an atta...
Lowest dup rate. $5K–$30K. PortSwigger research by James Kettle.
Hunt HTTP request smuggling (CL.TE, TE.CL, H2.CL, H2.TE). Cause: front-end proxy and back-end server disagree on where o...