发现 Skills

Rowan is a cloud-native molecular modeling and medicinal-chemistry workflow platform with a Python API. Use it for pKa and macropKa prediction, conformer and tautomer ensemble generation, docking and analogue docking, protein–ligand cofolding, MSA generation, molecular dynamics, permeability and descriptor workflows, and related small-molecule or protein modeling tasks. It is ideal for programmatic batch screening, multi-step chemistry pipelines, and workflows that would otherwise require maintaining local HPC/GPU infrastructure.

description: Create professional investment proposals for prospective clients. Covers the firm's approach, proposed allocation, expected outcomes, and fee structure. Use when pitching new clients o...

GL Reconciler — fund accounting tool responsible for reconciling the general ledger with sub-ledgers. It compares general ledger balances with sub-ledger details (custodians / counterparties / asset types), identifies variances, traces root causes, and issues approval-level exception reports.

Ahead of the rest. Makes your agent limitless. Tell your agent what you want. Watch it deliver.

Resource-oriented REST/OpenAPI contract design for URI/method semantics, idempotency, pagination, and HTTP status behavior. Trigger when REST contract diffs are detected in paths, methods, schemas, or status semantics, or when request-response transport choice is still unresolved before implementation. Do not use for GraphQL schema authoring, error-taxonomy-only changes, version lifecycle governance, or consumer-provider contract test implementation.

C4 architecture modeling workflow for context, container, and component views that make boundaries and responsibilities explicit. Use when teams need a shared structural model before major implementation or refactoring; do not use as a substitute for decision records.

MLOps model serving workflow for serving topology, latency SLOs, and safe rollout controls. Use when deploying ML models to production serving paths with explicit reliability and rollback requirements; do not use for model-architecture research decisions.

Security workflow for authentication architecture, credential lifecycle, and session/token assurance. Use when login, identity proofing, MFA, or session security decisions are required; do not use for authorization policy design or non-security quality tuning.

Use this skill whenever the user wants to create, build, draft, or design a new AI agent skill from scratch, or when the user wants to improve, refine, test, validate, or iterate on an existing skill, or when the user wants to package a skill for distribution. Triggers include: 'create a skill', 'build a new skill', 'make a skill for X', 'write a SKILL.md', 'improve this skill', 'test my skill', 'validate my skill', 'package this skill', 'skill template', 'forge a skill', or any request involving skill authoring, validation, and iteration. Always use when the user describes a task they want to turn into a reusable skill. This skill orchestrates both its own tooling and the built-in skill-creator when available. Do NOT use for simply using/invoking an existing skill, installing skills, or for MCP server setup.

Create production-ready public repos with complete documentation, automated setup, bundled dependencies, and user-friendly installation.

Proofread, rewrite, and review Japanese documents according to document type, estimated readers, and intended use. Do not add facts that are not present in the input. Arrange repository documents, specification documents, READMEs, operational manuals, and article drafts into natural, verifiable Japanese.

Use when the user asks about higgsfield.ai - generating images, generating videos, animating an image, Soul ID characters, Cinema Studio 3.5, Seedance, Kling, Veo, Minimax Hailuo, Wan, Nano Banana, Soul 2.0, Soul Cinema, Flux, Seedream, UGC Factory, Lipsync Studio, Marketing Studio, or saving credits / avoiding credit spend on the Creator plan.

Writes idiomatic, performant, and maintainable Nix code. Covers best practices, anti-patterns to avoid (like `with`), module system design, and performance optimization.

Use when securing AI agent systems — defending against prompt injection, sandboxing tool execution, preventing indirect attacks through retrieved data, designing minimal-permission tool architectures, and security testing agents.

Use when defining how an AI product stands out — defensibility assessment, outcome-based messaging, feature vs product decision, competitive moat design, and positioning for a specific niche.

Use bottom-up and top-down role mining techniques to discover optimal RBAC roles from existing user-permission assignments, reducing role explosion and enforcing the least-privilege principle.

Detect DCSync attacks where attackers abuse Active Directory replication permissions to extract password hashes by monitoring non–domain-controller accounts requesting directory replication via DsGetNCChanges.

Detects and analyzes fileless malware that runs entirely in memory. This class of malware leverages PowerShell, WMI, .NET reflection, registry-stored payloads, and living-off-the-land binaries (LOLBins), and does not write traditional executables to disk. Suitable for fileless threat detection, memory malware investigations, LOLBin abuse analysis, and WMI persistence checks.

Identify and exploit OAuth 2.0 and OpenID Connect misconfigurations during security assessments, including redirect URI manipulation, token leakage, and authorization code theft.

Exploit the Zerologon vulnerability (CVE-2020-1472) in the Netlogon Remote Protocol to compromise a domain controller by resetting the machine account password to an empty value.

Deploy privileged access management for database systems (including Oracle, SQL Server, PostgreSQL, and MySQL). Covers session agent configuration, credential vaulting, query auditing, dynamic credential generation, and least-privilege database roles.

Following the PTES methodology, perform comprehensive external network penetration testing of internet-facing infrastructure across reconnaissance, scanning, exploitation, and reporting phases to identify exploitable vulnerabilities.

Perform a comprehensive security assessment of a Google Cloud Platform environment using Forseti Security, Security Command Center, and the gcloud CLI to audit IAM policies, firewall rules, and storage permissions, and to check compliance against the CIS GCP Foundations Benchmark.

Security assessment of SCADA Human-Machine Interface (HMI) systems to identify vulnerabilities in web-based HMIs, thin-client configurations, authentication mechanisms, and communication channels between HMI and PLC, in accordance with IEC 62443 and NIST SP 800-82 guidelines.