发现 Skills

Perform final verification on development branches; choose from four merge strategies.

Spectral similarity and compound identification for metabolomics. Use for comparing mass spectra, computing similarity scores (cosine, modified cosine), and identifying unknown compounds from spectral libraries. Best for metabolite identification, spectral matching, library searching. For full LC-MS/MS proteomics pipelines use pyopenms.

Query the Precision Medicine Knowledge Graph (PrimeKG) for multiscale biological data including genes, drugs, diseases, phenotypes, and more.

Model interpretability and explainability using SHAP (SHapley Additive exPlanations). Use this skill when explaining machine learning model predictions, computing feature importance, generating SHAP plots (waterfall, beeswarm, bar, scatter, force, heatmap), debugging models, analyzing model bias or fairness, comparing models, or implementing explainable AI. Works with tree-based models (XGBoost, LightGBM, Random Forest), deep learning (TensorFlow, PyTorch), linear models, and any black-box model.

description: Build quick IRR/MOIC sensitivity tables for PE deal evaluation. Models returns across entry multiple, leverage, exit multiple, growth, and hold period scenarios. Use when sizing up a d...

Generate professional company tear sheets using S&P Capital IQ data via the Kensho LLM-ready API MCP server. Use this skill whenever the user asks for a tear sheet, company one-pager, company profile, fact sheet, company snapshot, or company overview document — especially when they mention a specific company name or ticker. Also trigger when users ask for equity research summaries, M&A company profiles, corporate development target profiles, sales/BD meeting prep documents, or any concise single-company financial summary. This skill supports four audience types: equity research, investment banking/M&A, corporate development, and sales/business development. If the user doesn't specify an audience, ask. Works for both public and private companies.

Conductor workflow patterns for multi-phase orchestration including planning, implementation, review cycles, pause points, and handoffs. Use for lifecycle management, delegation, and state tracking.

AI image generation for paid ad creatives. Reads campaign-brief.md and brand-profile.json to produce platform-sized ad images using Gemini (default) or a configured provider. Requires GOOGLE_API_KEY or ADS_IMAGE_PROVIDER + matching key. Triggers on: "generate ads", "create images", "make ad creatives", "generate visuals", "create ad images", "generate campaign images", "make the images", "generate from brief".

Use when the user asks about user management or profile updates.

Use when you have a written implementation plan to execute in a separate session with review checkpoints

Use when designing IAM policies, troubleshooting access denied errors, implementing SCPs, permission boundaries, cross-account roles, or using IAM Access Analyzer. Covers AWS SCS-C02, SAP-C02, and DVA-C02 identity domains.

Use when building RAG pipelines - document ingestion, chunking, embedding, vector search, retrieval, reranking, and generation with context

Monitor Certificate Transparency (CT) logs using crt.sh and Certstream to detect phishing domains, spoofed certificates, and unauthorized certificate issuances targeting your organization.

Analyze network traffic produced by malware during sandbox execution or live incident response using Wireshark, Zeek, and Suricata to identify C2 protocols, data exfiltration channels, payload downloads, and lateral movement patterns. Applicable to malware network analysis, C2 traffic decoding, malicious PCAP analysis, or network-based malware detection tasks.

Identify ransomware network indicators through analysis of Zeek conn.log and NetFlow, including C2 beaconing patterns, connections to TOR exit nodes, data exfiltration traffic, and encrypted key exchanges.

Analyze the threat landscape using MISP (Malware Information Sharing Platform) by querying event statistics, attribute distributions, threat actor galaxy clusters, and tag trends. Use PyMISP to pull event data, calculate IOC type distributions, identify top threat actors and malware families, and generate a threat landscape report that includes temporal trends.

Collect and synthesize open-source intelligence (OSINT) about threat actors, malicious infrastructure, and attack activity using publicly available data sources, passive reconnaissance tools, and dark web monitoring. Suitable for investigating external threat actor infrastructure, performing pre-engagement reconnaissance for authorized red-team assessments, or enriching CTI reports with public adversary context. Applicable to requests involving Maltego, Shodan, OSINT Framework, SpiderFoot, or infrastructure reconnaissance.

Implement API threat protection using Google Apigee policies, including JSON/XML threat protection, OAuth 2.0 enforcement, SpikeArrest, and Advanced API Security to defend against OWASP Top 10 attacks.

Deploy CyberArk privileged access management to discover, vault, rotate, and monitor privileged credentials across enterprise infrastructure. Covers vault architecture, session isolation, credential rotation policies, and integration with NIST SP 800-53 access control requirements.

Design and implement Privileged Access Workstations (PAW), including device hardening, Just-In-Time (JIT) access, and integration with CyberArk or BeyondTrust to secure administrative operations.

During authorized reconnaissance, enumerate DNS records, attempt zone transfers (Zone Transfer), brute-force enumerate subdomains, and map DNS infrastructure to identify attack surface, misconfigurations, and information leakage in the target domain.

Perform a comprehensive security assessment of IoT devices and their ecosystems by testing hardware interfaces, firmware, network communications, cloud APIs, and companion mobile applications. Testers use techniques such as firmware extraction and analysis, hardware debugging via UART and JTAG, network protocol analysis, and runtime exploitation to identify vulnerabilities across IoT layers. Suitable for IoT security testing, embedded device assessments, firmware security analysis, or smart device penetration testing request scenarios.

Use ProjectDiscovery's Subfinder passive reconnaissance tool to enumerate subdomains of a target domain, mapping the attack surface during security assessments.

Conduct industry-specific threat landscape assessments by analyzing threat actor targeting patterns, common attack vectors, and industry-specific vulnerabilities to provide decision support for organizational risk management.