Latest Agent Skills

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。

Aggregate RSS feeds from YouTube, Vimeo, Behance, Twitter/X, Bilibili, Weibo, Douyin, Xiaohongshu, and Zhihu with incremental updates, deduplication, and AI classification.

Routes agent turns through policy-based delegation, runtime status, and feedback loops using a TypeScript-first runtime layer for OpenClaw.

Diagnose intermittent Wi-Fi issues like buffering, lag, packet loss, and weak coverage through read-only analysis, then safely optimize authorized router settings when evidence supports a change.

Develop, migrate, and debug ROS 1 and ROS 2 robotics projects with support for build systems, navigation, control, simulation, and embedded integration.

Transforms uploaded course materials into exam-oriented study notes, practice questions, and scoring-focused explanations.

Query and manage Strava fitness data including activities, athlete stats, segments, routes, clubs, and gear via the strava CLI.

Provides cross-harness memory for agents by maintaining a local memex and offering commands to query, record, and check status across sessions.

Generates AI-friendly repository documentation using the SourceSage CLI, supporting local or external repos, language switching, lite mode, and deprecated diff reports.

Verifies claims, articles, screenshots, and URLs through source-grounded analysis with an evidence ledger, source credibility evaluation, and manipulation detection. Supports quick checks, full fact-check cards, two-source comparisons, and prebunking in multiple languages and policy contexts.

Enforces anti-hallucination constraints including citation requirements, source grounding, and explicit 'I don't know' responses for research tasks.

Delegates tasks to specialized AI agents running in parallel via the Box0 platform, enabling code review, security checks, research, and documentation.

Converts WeChat Official Account articles into clean Markdown files with YAML frontmatter, locally downloaded images, and preserved code blocks.

Audits a website against the Forter Agentic Readiness Guide by running 25 weighted rubrics, scoring each guideline, and producing a prioritized fix report.

Operates WeChat official account automation for content collection, data analysis, and interaction management.

Adopts the perspective and thinking framework of Justin Sun, using his mental models, decision heuristics, and communication style to analyze crypto industry topics and business decisions.

Collaboratively write multi-volume novels with structured commands for outlining, planning, drafting, writing, health-checking, and archiving, while maintaining world-building consistency across chapters.

Extract and analyze Douyin video data into evidence-graded learning notes, summaries, and research briefs using subtitles, ASR, comments, and AI-assisted reading.

Transforms ideas, files, folders, URLs, or exported data into polished single-file HTML pages with auto-selected design systems.

用 Serenity 的供应链卡点逆向投资逻辑分析美股/AI 供应链标的,产出专业投研报告,包含逆向链显形、卡点判据、估值与证伪门。

Reverse engineering assistant that exposes Ghidra capabilities over a Unix domain socket for binary analysis, decompilation, and vulnerability research via CLI commands.

Analyzes a target job description and a Chinese resume to map evidence, identify gaps, rewrite the resume for ATS/HR/interview consistency, and generate application materials for the Chinese job market.

Generate or edit Xiaohongshu (RedNote) cover images using GPT Image 2 / Codex, with a Gemini CLI fallback, supporting 18 preset styles and custom style learning.

End-to-end Kaggle competition workflow for scored submissions, covering code competitions, validation, metrics, public notebook/discussion intel, tabular/text/image modeling, tuning, ensembling, multi-notebook architectures, Kaggle GPU offload, and hidden-test debugging.

Adopts the perspective of Naval Ravikant to answer questions using his mental models, decision heuristics, and core concepts like leverage, specific knowledge, and desire management.

Captures marketing screenshots of a SwiftUI iOS app across multiple locales, devices, and appearances, producing full-screen captures and isolated element renders.

Generates explanatory illustrations for Chinese in-depth articles using a fixed IP character library, following a structured method of cognitive anchor selection, metaphor creation, and anti-PPT self-check.

Install a local rebuttal workspace for academic papers with structured intake, reviewer analysis, and strategy planning to produce venue-compliant author responses.

Analyzes past agent sessions to identify recurring failures and skill gaps, then automatically creates or patches skills and runs self-evolution to fix them, tracking improvement over time.

Connects AI coding agents to the IOTA blockchain with tools for wallet management, Move smart contract development, and on-chain data queries via JSON-RPC and GraphQL.

Creates a consistent minimalist hand-drawn illustrated character from user-provided photos or profile materials, then generates content visuals like knowledge cards, posters, storyboards, and presentation slides featuring that character alongside helper agents.

Set up GPU profiling, tracing, and monitoring for inference workloads using vLLM, SGLang, PyTorch, and dstack services via the Graphsignal Profiler sidecar.

Automates browser interactions — navigating pages, filling forms, clicking buttons, taking screenshots, extracting data, and running assertions — using a native Rust CLI.

Provides persistent, compounding memory for AI agents across sessions using local markdown files, with optional Supabase-backed semantic search.

Generates images and conducts conversations through the Gemini website (gemini.google.com) using MCP tools, scripts, or a managed browser as a fallback.

Takes a PRD, reference URL, screenshot, or keywords to produce a DESIGN.md specification, then generates production-ready web code that meets UI/UX, visual, motion, and responsive standards.

Compresses conversation transcripts into prioritized notes using an LLM observer, consolidates them when they grow, and recovers any missed sessions without a database or vector store.

Provides a repeatable, auditable workflow for large coding tasks by initializing repo-local task artifacts, installing subagent templates, and running a spec-freeze → build → evidence → verify → fix loop with fresh-session verification.

Orchestrates multi-step content operations on Xiaohongshu, including competitive analysis, trend tracking, content creation, and engagement management through a CLI toolchain. All operations require user confirmation before publishing or commenting.

Interact with Xiaohongshu (Little Red Book) posts by posting comments, replying to comments, liking, and favoriting content through a CLI script.

Publish text, image, and video content to Xiaohongshu (Little Red Book) with support for scheduling, tags, visibility settings, and long-form articles.

Search, browse, and analyze content on Xiaohongshu (Little Red Book) including feeds, note details, comments, and user profiles.

Manages Xiaohongshu (Little Red Book) login authentication by checking login status, logging in via QR code or phone verification code, and logging out.

Automates Xiaohongshu (Little Red Book) operations including authentication, content publishing, search, social interaction, and composite workflows via a CLI tool.

Performs deterministic, LLM-first SEO audits for websites, blog posts, and GitHub repositories, producing prioritized, confidence-labeled fixes.

Analyzes prompt injection, retrieval poisoning, memory contamination, planner drift, and tool-boundary abuse in agentic systems, mapping trust boundaries and proving exploit chains.

Maps and reproduces OAuth/OIDC authentication chains by tracing redirects, token exchange, and identity acceptance in controlled environments.

Traces identity flows, Windows host artifacts, enterprise messaging, and lateral-movement chains in CTF sandbox challenges.

Traces which sandbox node, proxy rule, or header-derived branch serves a live request in a CTF competition environment.

Analyze the structure, boot chain, and update mechanism of a firmware image, then trace the shortest path to the decisive artifact or secret.

Hooks Android APKs to inspect signer logic, trace Java and native boundaries, bypass SSL pinning or root checks, and replay accepted mobile requests.

Recovers malware configuration, decodes C2 and beacon parameters, unpacks staged payloads, and extracts bot or campaign IDs from samples in a CTF sandbox environment.

Traces host-to-host pivot chains in Windows CTF challenges by recovering Kerberos tickets, credential material, and privilege edges across WinRM, SMB, and RDP.

Analyze PCAP files by reconstructing TCP/UDP sessions, decoding application-layer protocols, and correlating packet sequences with host or malware behavior for CTF challenges.

Trace mailbox abuse chains including OAuth consent, forwarding rules, delegate access, and message rerouting in a CTF sandbox environment.

Recovers transform chains, hidden media payloads, mobile signing paths, and local trust boundaries in CTF challenges involving crypto, encoding, steganography, APK, IPA, and mobile trust-boundary analysis.

Orchestrate CTF, exploit, reverse engineering, DFIR, and other challenge types by treating presented targets as sandbox-internal, tracing minimal paths, and routing to specialized downstream skills.

Traces software supply chain provenance from source to runtime, identifying divergence points in dependency resolution, build, packaging, and release pipelines.

Inspects web behavior, browser state, server routing, API order, and worker-backed application flow within a sandboxed CTF environment.

Inspects metadata, hidden channels, and appended payloads in media files to recover concealed data in steganography challenges.