740 skills · sorted by relevance
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.
Manage AWS infrastructure as TypeScript code with SST v4 and Pulumi. Guides resource creation, connections between services, infrastructure tests, deployment checks, troubleshooting, and resource migrations while accounting for existing project conventions.
Plan AWS infrastructure changes by checking application requirements and existing configuration, then selecting guidance from an external skill collection. Produces a reviewable plan covering access permissions, networking, cost assumptions, validation, and rollback.
Design and build Apify integrations for workflow platforms, AI agents, AI frameworks, or applications. Follow guidance for authentication, asynchronous cloud task execution, result retrieval, spending limits, error handling, testing, and release preparation.
Build persistent agents on Azure AI Foundry with the Microsoft Agent Framework Python SDK. Connect functions, search, and MCP tools, preserve conversation context, stream responses, and return data in a defined structure.
Guide reviews of Linux Kernel patches for memory safety, Terraform plans for costly resource changes, and Kubernetes configurations for restricted permissions. A separately installed tool and configured AI model produce advisory findings and candidate manifests for validation.
Guides preparation and authorized publication of Apache Airflow changes, including existing pull request checks, remote verification, reviews, tests, rebasing, and a prefilled submission page. Also explains how to track work deferred by temporary fixes.
Move reusable code and its tests from OpenHuman into the appropriate tiny* submodule. Separate host responsibilities, update module interfaces, verify the migration, and align release versions and integrity hashes when a loadable module changes.
Investigate failed Power Automate cloud flows through FlowStudio MCP. Inspect each action’s inputs and outputs, trace incorrect data upstream, fix expression or data issues, and replay a previous run to check the repair.
Research recommended practices for a chosen technology using official documentation and maintainer sources. Get a cited recommendation that explains version context, local project constraints, uncertainties, and the next steps for planning or implementation.
Refresh installed NanoClaw channel and agent provider code from its registry branches. Update all integrations or a selected subset, check a structured result report, and validate the updated installation with builds and tests.
Diagnose OpenCLI commands broken by website changes, collect execution traces, patch the adapter that connects to the site, and retry. After a verified repair, prepares a GitHub issue for submission with user approval.
Build market research evidence by comparing two market-size estimates, calculating survey sample sizes for each customer group, and scoring potential segments. Outputs show methods and assumptions so teams can assess the basis for business decisions.
Audit and upgrade NemoClaw dependencies, including Hermes and base images. Trace upstream changes to affected code, implement required migrations, and verify tests, distributed artifacts, and the versions actually selected for use.
Trace where BigQuery and Cloud Storage data comes from and where it goes. The skill summarizes table or column lineage, meaning data origins and movement, in a readable Markdown report to support data quality investigations.
Check a paper's numerical consistency using fixed rules, then record blocking or warning decisions and outstanding findings. The workflow preserves a traceable correction history, while explicitly leaving broader semantic review unavailable in its Codex mode.
Audit a paper for numerical inconsistencies and other research integrity concerns. Record findings tied to source passages, track corrections and human waivers, and translate the audit report into workflow blocking or warning decisions.
Install Scenic, a language for describing scenarios with randomized conditions, into the Python environment used by CARLA. Check command-line tools and version compatibility, optionally download example scenarios and map assets, and save the installation paths.
Import RoadRunner geometry and road data into a CARLA source build, then verify the map loads and supports driving. Handle tiled maps and generate and inspect pedestrian navigation areas for standard maps.
Validate security patches by comparing vulnerable and patched code against exploit tests, related attack variants, and normal behavior. Produce reproducible logs showing remaining flaws, regressions, newly introduced security failures, and gaps that still need testing.
Assess weaknesses in the software supply chain, from dependency packages to build pipelines and distributed artifacts. Covers authorized proof-of-concept testing, package confusion, container image risks, signing abuse, and defensive checks for tampering.
Add an LLM provider to DeepChat by choosing a suitable API connection method, updating authentication and model configuration, and making focused source changes with tests for the affected behavior.
Investigate a Codex CLI session by matching its local conversation record with production router logs. Use the session ID to examine missing reasoning summaries, routing markers, unexpected models, or unusual tool calls and trace relevant code paths.
Investigate unexpected Claude Code output by matching a session’s local transcript with production router logs. Identify the serving model and trace response conversion code to explain empty blocks, tool output, or other rendering symptoms.