2.4K skills · sorted by relevance
Automate Api2pdf operations through Rube MCP, a connection for agent tools. The skill guides tool discovery, connection checks, and execution using current input requirements, with support for bulk operations and retrieving results across multiple pages.
Automate Affinda operations through Rube MCP, a connection for agent tools. The skill discovers available actions and their required inputs, checks authentication, and provides workflows for execution, bulk operations, and retrieving paginated results.
Automate Ably operations through Rube MCP and Composio. The skill discovers tools for your task, checks current input requirements, verifies an active connection, and guides execution of single operations or batches.
Review JavaScript module usage and convert CommonJS code to ES modules using import/export. Inspect source code and browser execution, explain how unused code can be removed during builds, and describe how to verify changes.
Review frequent JavaScript events and apply debounce, which waits until activity stops, or throttle, which limits execution frequency. Identify handlers causing sluggish interfaces or excessive API calls, and define browser checks for the fixes.
Review JavaScript variable declarations, report every use of var with line numbers, and replace declarations with const or let according to reassignment. Explain variable scope and initialization behavior, and check affected browser execution paths.
Find console output left in production JavaScript and help remove it, disable it by environment, or replace it with a logging service. Reviews cover source code and browser execution paths, including how to verify the changes.
Review a reusable Agent Skill package before implementation. Validate its identity fields, separate instructions from external capabilities and execution timing, and receive a validation report with a minimal set of building blocks and reasons for each choice.
Use Strix to test web apps, APIs, and source code for exploitable security flaws. Choose local or cloud execution, set testing scope and budget, and review validated findings with reproducible examples and structured reports.
Inspect stored Muse records when regular product tools do not reveal enough detail. Use read-only database queries to investigate missing records, trace execution history, and check relationships or inconsistencies across different product areas.
Test agent features across local and remote execution environments using integration tests, which check components working together. Covers Docker and Wine setups, test helpers, and configuration-specific skips for the app-server and exec-server split.
Turn recurring GUI workflows into macros that agents can call from the command line with parameters. Define and inspect macros, simulate runs before making changes, and review structured results and execution history.
Design a process for AI agents to learn from execution records. Evaluate outcomes, actions, and quality, choose whether to update knowledge, instructions, code, or model parameters, and define independent validation, release checks, and rollback procedures.
Design tools that AI agents can choose and use correctly. Define clear descriptions, inputs, and outputs, manage large search results, and plan approval checks, isolated execution environments, and interfaces for collaboration between agents.
Design the operating layer around a coding agent so it can read and edit code, run checks, and correct errors. Define completion criteria, permission boundaries, feedback, and recovery methods, and assess which tasks suit autonomous execution.
Build quantum circuits with Qiskit, test them locally, and prepare them for IBM quantum hardware. The skill covers hardware-specific circuit conversion, sampling, expectation values, and analysis of measurement results, uncertainty, and resource usage.
Build and operate bioinformatics workflows on Latch using Python, Nextflow, or Snakemake. Configure computing resources and input forms, move data, connect Registry records, and register, debug, launch, and monitor analysis runs.
Build and operate genomics workloads on DNAnexus using its command-line tools and Python SDK. The skill covers data transfers, app configuration checks, workflow imports, execution monitoring, and explicit cost controls for reproducible analysis workflows.
Rank possible gene regulatory relationships from bulk or single-cell expression data using GRNBoost2 or GENIE3. The skill guides input preparation, compatible execution, method comparison, and stability checks to help prioritize candidates for further biological investigation.
Create and manage persistent Azure AI agents from Java. Covers conversation threads that retain messages, agent execution, status checks, response retrieval, and cleanup, using preview SDK examples with guidance on authentication and cloud resource handling.
Develop AxonX plugins and manage quantitative finance research through the command line or MCP, an agent connection interface. Track data preparation, training, prediction, and historical strategy tests using execution status, logs, artifacts, and dependencies.
Design AI agents that break down goals, plan actions, use tools, and correct their own mistakes. The guidance focuses on reliable execution, clear operating boundaries, and managing conversation context as tasks grow longer.
Store and retrieve execution output, model responses, reports, and operation receipts in YYLO Ledger. Choose storage and retention settings, attach provenance describing the source, and verify immutable evidence using record identifiers and content digests.
Document the tools an AI agent may call, including input rules, caller permissions, execution limits, and retry conditions. Produce a tool register and verification plan for reviewing registrations or MCP routing designs.