718 skills · sorted by relevance
Operates native desktop apps through Cherry Studio Computer Use. It reads interface information, types, clicks, and captures windows, using fresh observations to choose actions and verify results within the permissions and capabilities available.
Guides agents in choosing Cherry Studio tools for research, document conversion, memory, notifications, and other tasks. It explains when to use app tools or local runtimes, with checks for availability, configuration, and approval.
Inspect an agent’s current model, processing limits, workspace, tools, and message routing details. Diagnose unavailable capabilities, adjust permitted runtime settings, or keep temporary session notes, with advance notice before changes that affect the model or limits.
Review a repository’s architecture using Ontoly Software Graph, a map of code relationships. Explain module boundaries, package structure, dependencies, and architectural risks, with graph evidence and a stated confidence level.
Evaluates task complexity and selects a small set of existing skills for work spanning multiple areas. Uses agent-memory-mcp to record and retrieve successful combinations, while keeping simple tasks within the agent’s ordinary capabilities.
Find autonomous AI agents, frameworks, and tools through AgentFolio. Compare their capabilities, intended users, integrations, and deployment options to shortlist existing products or gather examples and ideas before designing an agent of your own.
Compare AAS skills against a project's capabilities, then record the chosen combination as a validated stack manifest. Inspect the result, identify catalog gaps, and optionally export evidence documenting the selection process.
Let the host AI agent review Git changes while ocr selects files and resolves review rules. Receive findings grouped by severity, plus coverage details showing which files were reviewed or skipped and why.
Check Binance options for buying or selling crypto with government-issued currencies, such as yen or euros. Look up country-specific payment methods, limits, and reference prices, plus order and payment history when API credentials are available.
Set up and manage DeepTutor from the command line, a text interface for running commands. Run learning tasks, build searchable document collections, manage sessions and notebooks, diagnose installation issues, and launch the server or Web app.
Evaluate whether a fine-tuned model is ready for release by checking training data, general capability loss, comparisons with the base model, and staged production rollout. Produces an evidence-based promotion or rejection report with one prioritized remedy when rejected.
Create, edit, and inspect Word documents such as memos, reports, letters, and templates. The workflow preserves originals by default and checks the result by reopening the document and extracting representative text.
Create or update Claude skills that capture specialized knowledge and repeatable workflows. Guides the organization of instructions, scripts, references, and templates, then covers initialization, validation, and packaging into a distributable skill file.
Review PostgreSQL queries and data designs using execution plans, which show how queries run, and targeted index recommendations. Get guidance on JSONB, arrays, full-text search, analytical queries, extensions, and routine database maintenance.
Generate a PHP server for MCP, a protocol that lets AI applications access tools and data. Build a project with the official PHP SDK, including requested capabilities, configuration files, PHPUnit tests, and setup documentation.
Check an MCP server before release through a real client session. Compare available features with source code and documentation, test invalid requests and installation, and produce a verdict backed by reproducible commands and responses.
Create an agent user in Microsoft Entra ID so an AI agent can access services requiring a user identity. Covers validating the parent agent identity, creating the account, assigning a manager and licenses, and troubleshooting setup errors.
Create Markdown documents for time-limited technical investigations before implementation. Define the decision to resolve, research tasks, success criteria, and deadlines, then record evidence, recommendations, and follow-up actions in a consistent structure.
Find and evaluate a small, compatible set of AI Agent Skills for a multi-step goal. Check existing capabilities, compare candidates for fit and safety, identify overlaps, and prepare recommendations with installation subject to user approval.
Keep the CopilotKit Intelligence documentation landing page aligned with feature and guide changes. It coordinates feature cards, links, navigation, and related tests so readers can find current guides after additions, moves, renames, or removals.
Find installable agent skills for a specific task, check their sources and adoption, and present relevant options with explanations, links, and installation commands. Help install a selected skill when the user wants to proceed.
Examine AI product reliability, learning methods, and model limitations through frameworks drawn from Andrej Karpathy’s public statements. Assess the gap between demonstrations and real use, uneven capabilities, and where people should retain control.
Simulate man-in-the-middle attacks, where traffic is intercepted between communicating systems, in authorized environments. Use Bettercap, Ettercap, and mitmproxy to test encryption enforcement, certificate validation, and network detection, then document findings and recommendations.
Build threat actor profiles from public reports, social media, code repositories, and other intelligence sources. Correlates indicators, maps related infrastructure and attack techniques, and produces structured dossiers with confidence assessments about who may be responsible.