Top Agent Skills

Launch community-powered growth campaigns across social platforms: amplify posts with authentic engagement (replies, likes, reposts) and discover relevant conversations to join.

Manage Bankr spaces: post, pin, vote, sync with Bankr projects, and handle fundraising and bounties via the bankr.space API.

Conducts exhaustive multi-source research on a topic, tagging each claim with source class and confidence, and includes a mandatory adversarial counterpoint and open-questions list.

Buy and sell NFTs on OpenSea's Seaport marketplace. Fulfill listings, accept offers, create new orders, cross-chain purchases, and sweep multiple listings.

Interact with GitHub repositories using the `gh` CLI to manage issues, pull requests, CI runs, and query the GitHub API.

Build, refactor, or review macOS menubar apps that use Tuist and SwiftUI, with a focus on Tuist-first workflows, strict architecture boundaries, and reliable local launch scripts.

Extracts full detail data from a single Goofish (闲鱼) second-hand item page, including title, price, seller info, description, images, tags, and want-count.

Navigate a Taobao or Tmall shop's catalog page to extract paginated product listings including itemId, title, and image URL.

Extract structured job listing data from Indeed search results, including job titles, companies, salaries, descriptions, benefits, and apply links.

Extracts structured product listings from Amazon, including titles, ASINs, prices, ratings, and specifications, using the BrowserAct API.

Extracts structured business data from Google Maps, including names, categories, contact info, ratings, and addresses, using the BrowserAct API.

Extract structured product details from Amazon using an ASIN, including title, price, ratings, brand, and description via the BrowserAct API.

Scrapes Instagram posts by hashtag, returning media items with captions, like/comment counts, media URLs and user info from the hashtag explore feed.

Searches X (Twitter) for tweets matching an advanced query and returns structured data including text, author profile, engagement metrics, media, hashtags, mentions, and pagination cursors.

Automatically discovers social media profiles for individuals or brands across platforms like Facebook, Twitter, Instagram, LinkedIn, and TikTok, returning profile URLs, follower counts, and bio snippets as a downloadable CSV.

Extract Xiaohongshu (RedNote) user profile information and published notes list by user ID, returning nickname, bio, follower/following counts, engagement totals, tags, and paginated notes with engagement stats.

Extracts clean Markdown content from any website URL using the BrowserAct Web Search Scraper API, with automatic retry and error handling.

Extracts posts from public Facebook pages or profiles, returning structured data with text, engagement metrics, reaction breakdowns, media thumbnails, and pagination support.

Extract GitHub repository details and contributor contact information using keywords, star counts, and update dates via the BrowserAct API.

Posts text, images, videos, and long-form Markdown articles to Weibo via a real Chrome browser, bypassing anti-bot detection.

Summarizes WeChat group chat highlights into a structured digest using the local wx-cli binary, with per-group history, user profiles, and privacy guardrails.

Downloads YouTube video transcripts/subtitles and cover images by URL or video ID, with support for multiple languages, translation, chapters, and speaker identification.

Run standard single-cell RNA-seq analysis pipelines: QC, normalization, dimensionality reduction, clustering, differential expression, and visualization using Scanpy.

Create, read, manipulate, and store annotated data matrices using the AnnData Python package, designed for single-cell genomics and general-purpose annotated data workflows.

Create, analyze, and visualize complex networks and graphs in Python with NetworkX, including graph algorithms, community detection, synthetic network generation, and multiple I/O formats.

Process and analyze physiological signals including ECG, EEG, EDA, RSP, PPG, EMG, and EOG using Python.

Build and evaluate machine learning models using scikit-learn for classification, regression, clustering, dimensionality reduction, and preprocessing.

Write competitive research proposals for NSF, NIH, DOE, DARPA, and Taiwan NSTC with agency-specific formatting, review criteria, budget preparation, and compliance guidance.

Design experiments and studies before data collection — choosing a design, randomizing, blocking, and laying out treatment combinations so results are interpretable.

Integrate with Benchling's Python SDK and REST API to manage registry entities, inventory, ELN entries, workflows, and Data Warehouse queries for life sciences R&D automation.

Create publication-quality scientific diagrams using AI generation with smart iterative refinement and quality review.

Automates enrichment of raw indicators of compromise with multi-source threat intelligence context using SOAR platforms, Python pipelines, or TIP playbooks to reduce analyst triage time and standardize enrichment outputs.

Detect WMI event subscription persistence by analyzing Sysmon Event IDs 19, 20, and 21 for malicious EventFilter, EventConsumer, and FilterToConsumerBinding creation.

Maps intrusion activity to the Lockheed Martin Cyber Kill Chain framework to identify adversary phase completion, detection gaps, and defensive controls for post-incident analysis and prevention.

Analyzes malicious Linux ELF binaries including botnets, cryptominers, ransomware, and rootkits targeting servers, containers, and cloud infrastructure. Covers static analysis, dynamic tracing, and reverse engineering of x86_64 and ARM ELF samples.

Parses API Gateway access logs (AWS API Gateway, Kong, Nginx) to detect BOLA/IDOR attacks, rate limit bypass, credential scanning, and injection attempts using pandas for statistical analysis and anomaly detection.

Perform comprehensive forensic analysis of disk images using Autopsy to recover files, examine artifacts, and build investigation timelines.

Deploy Microsoft Sentinel as a cloud-native SIEM and SOAR platform for centralized security operations across AWS, Azure, and GCP.

Deploys and monitors ransomware canary files across critical directories using Python's watchdog library for real-time filesystem event detection, triggering alerts via email, Slack, or syslog when decoy files are accessed.

Detect and prevent API enumeration attacks including BOLA and IDOR exploitation by monitoring sequential identifier access patterns and authorization failures.

Detect DLL side-loading attacks where adversaries place malicious DLLs alongside legitimate applications to hijack execution flow for defense evasion.

Analyzes mobile applications for malicious behavior through static analysis, runtime monitoring, and network traffic inspection to identify malware indicators.

Detect Cobalt Strike beacon network activity using TLS certificate signatures, JA3/JA3S/JARM fingerprints, HTTP C2 profile matching, beacon jitter analysis, and named pipe detection via Zeek, Suricata, and Python PCAP analysis.

Audits HTTP security headers including CSP, HSTS, X-Frame-Options, and cookie attributes to identify missing or misconfigured browser-level protections.

Test LLM applications for system prompt leakage using manual payloads, garak, and Promptfoo to extract embedded secrets and routing logic.

Triages and enriches indicators of compromise (IPs, domains, file hashes, URLs, email artifacts) from phishing emails, security alerts, or threat feeds, assigning confidence scores and dispositions using VirusTotal, AbuseIPDB, MalwareBazaar, and MISP.

Guides the configuration of pfSense firewall rules, NAT policies, VPN tunnels, and traffic shaping to enforce network segmentation and protect network zones.

Detects cyber attacks targeting SCADA systems, including man-in-the-middle, command injection, HMI compromise, historian manipulation, and DoS, using OT-specific intrusion detection and protocol anomaly analysis.

Detect insider threat behavioral indicators including unusual data access, off-hours activity, mass file downloads, privilege abuse, and resignation-correlated data theft.

Detect insider threats by modeling normal user and entity behavior with Elasticsearch, computing anomaly scores, and correlating low-confidence indicators into high-confidence alerts.

Run MISP, curate threat feeds, and auto-generate detections for Wazuh, Sigma, and Suricata.

Detect and extract hidden data embedded in images, audio, and other media files using steganalysis tools to uncover covert communication channels.

Detect anomalous user activities including impossible travel, unusual access patterns, privilege abuse, and insider threats using SIEM-based behavioral baselines and statistical analysis.

Scan container images, IaC, and SBOMs for vulnerabilities and misconfigurations in CI/CD with Trivy.

Scan container images for vulnerabilities with Trivy and Grype, generate SBOMs, sign images with Cosign and Sigstore, configure registry access controls, and enforce security gates in CI/CD pipelines.

Triages security alerts in Splunk Enterprise Security by classifying severity, investigating notable events, correlating related telemetry, and making escalation or closure decisions using SPL queries and the Incident Review dashboard.

Perform static analysis of malicious PDF documents using peepdf, pdfid, and pdf-parser to extract embedded JavaScript, shellcode, and suspicious objects.

Ingests, normalizes, and enriches structured and unstructured threat intelligence feeds into STIX 2.1 format, evaluating feed quality and deduplicating indicators for distribution to SIEM, firewall, and EDR platforms.

Parses and analyzes the Windows Amcache.hve registry hive to extract evidence of program execution, application installation, and driver loading for digital forensics investigations.

Run Microsoft Entra ID tenant reconnaissance, token acquisition and manipulation, and federation backdoor testing with the AADInternals PowerShell toolkit to validate identity-attack resilience.