2.4K skills · sorted by relevance
Turn a vague idea into a written specification through focused questions. The skill scores clarity across goals, constraints, and success criteria, explores hidden assumptions, and requires explicit approval before moving from planning to execution.
Turns vague development requests into reviewed plans through planning, architecture, and quality-review agents. It compares alternatives, defines testable acceptance criteria, and records decisions, stopping before implementation unless execution has been explicitly approved.
Launch an SGLang server, run a quick accuracy check, and capture an execution trace for performance inspection. Return the trace location and generated files, ready to open in Perfetto or Chrome tracing.
Review trading rules across China A-shares, Hong Kong stocks, US stocks, and crypto markets. Use comparison tables and checklists to identify execution limits, short-selling constraints, trading hours, fees, and tax considerations when designing historical trading simulations.
Detect attacks that misuse legitimate Windows tools by examining command arguments, parent and child processes, and network connections. Create Sysmon logging configurations and Sigma detection rules, analyze endpoint logs, and review application controls while accounting for legitimate usage.
Build detections for fileless attacks on Windows using process activity, script logs, and endpoint monitoring. Investigate suspicious PowerShell, code injected into running processes, WMI persistence, and registry-based execution with logging guidance and detection query examples.
Detect unexpected changes in running containers by comparing them with their original images and monitoring execution and file activity. Use Falco or Microsoft Defender for Containers to investigate changes and guide isolation, replacement, and preventive configuration.
Examine suspicious Word, Excel, and PowerPoint documents by extracting macros and untangling code designed to hide its purpose. Identify download addresses, execution triggers, and attack steps, then document findings and indicators for detecting related threats.
Use Phoenix to record execution traces, detailed records of an AI application's operations, and investigate problems. Evaluate answers on datasets, compare prompts and models, and set up monitoring through a self-hosted server.
Design collaborative AI teams with CrewAI by defining each agent’s role, goals, tasks, and expected results. Covers passing work between agents, manager-led coordination, memory settings, and execution planning for workflows such as research and writing.
Build and operate AutoGPT agents that carry out multi-step workflows. Covers a visual editor for connecting processing blocks, scheduled and webhook triggers, deployment, execution monitoring, and benchmarks for evaluating agent performance.
Investigate bugs using a graph of code relationships. Find relevant functions, trace calls and execution paths, check recent changes, and assess what a proposed fix could affect before reading and changing the implementation.
Explore an unfamiliar codebase using a graph of code relationships. Inspect its structure, find functions and classes, trace calls and imports, follow execution paths, and locate large functions for closer investigation.
Present clear choices when a task needs a human decision, then pause execution until the user replies. This reusable interaction pattern supports filing decisions, priority selection, and confirmation before destructive actions, with an option to decline.
Design agents for recurring internal work such as scheduled posts, data synchronization, and event responses. Define triggers, duplicate prevention, approval boundaries, required integrations, and a consistent seven-field execution record for every run.
Turn a Factory work item into a phased implementation plan grounded in current code and project history. Document scope, changes, tests, risks, and assumptions, then hand the plan to the execution stage.
Design systems where multiple AI agents share work, generate tool schemas that define tool inputs for Anthropic and OpenAI, and analyze execution logs. Outputs include role assignments, communication diagrams, and recommendations for addressing cost, latency, and failures.
Turn company strategy into operational plans through process design, OKRs—objectives paired with measurable results—and regular reviews. Produce bottleneck analyses, efficiency scorecards, meeting schedules, and readiness reports for teams preparing to grow.
Plan a Claude Managed Agent around one clear job, then route work through setup, launch preparation, evaluation, and scheduling. Produce execution plans and curl commands that users run with their own Anthropic API key.
Delegate research, coding, and testing from Claude Code to opencode workers. Run independent tasks in parallel with separate Git working directories, combine findings, track token use, and compare solo execution with coordinated workers.
Write JavaScript for n8n Code nodes to aggregate, filter, and transform workflow data. Guidance covers data access, output formats, execution modes, common errors, and performance choices when processing large numbers of records.
Design AI agents and chatbots in n8n, choosing suitable nodes and connecting models, tools, conversation memory, and structured JSON output. Includes guidance on document retrieval and human approval before tool execution.
Analyze saved NemoClaw CI timings to rank consistently slow command-line tests and compare base-image publication with reuse. Read-only analyzers report execution times, runner queues, and sample coverage as bounded JSON output.
Implement or modify GitButler’s but commands using its established structure. It covers typed arguments, input validation, execution, and human-readable, shell, or JSON output, while keeping operations usable from the terminal interface.