374 skills · sorted by relevance
Inspect OmniRoute connection restrictions, usage quotas, and retry delays from the command line. Reset stuck providers and adjust failure thresholds, cooldowns, and recovery timing to manage how connections respond to errors.
Coordinate child agents on tasks that must happen in a particular order. Define dependencies, pass results through handoff files, verify the outcome, and recover individual failed tasks while reusing work that has already finished.
Monitor a GitHub pull request for review feedback, automated check failures, and merge readiness. Diagnose failures, fix problems caused by the branch, and retry likely temporary failures while continuing to watch for updates.
Manage n8n automation workflows from the command line. Create, update, and activate workflows, inspect or retry executions, and manage credentials, variables, and tags through n8n's public API with structured JSON output.
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.
Inspect local AI coding session logs with agenttrace to identify cost spikes, delays, failed tools, and retry loops. Produce readable reports, compare attempts, and configure automated checks for unusual or unhealthy runs.
Move slow Python operations into background jobs so requests can return promptly. Use task queues and workers, the processes that execute queued work, with retry rules, duplicate handling, time limits, and persistent job status.
Build workflows that extract structured data from LLM responses, check field types and values with Pydantic, and retry failed extractions. Includes examples for nested data, classification, and receiving results as they are generated.
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.
Write integration tests for core error processors by simulating API failures with a mock model. Check retry attempts, changes to conversation messages, and streamed responses, with guidance on test setup and diagnosing empty output.
Investigate stalled, retrying, or failed Symphony runs by connecting Linear issue identifiers with Codex sessions. Trace log events in time order, identify the failing stage, and collect evidence for the probable cause.
Reproduce chat errors, retries, parallel tool calls, and app creation in a running desktop application. Check how messages and cards appear, including interrupted replies, grouped steps, and error details.
Retry commands that fail with network errors through proxychains4, a tool that routes connections through a proxy. The skill also guides proxy configuration and troubleshooting when downloads, package installations, or Git operations cannot connect.
Recover failed Stripe subscription payments through a charge retry and three timed reminder emails. Track each subscription’s progress in a ledger, stop reminders after payment, and hand unresolved cases to a person after the final notice.
Diagnose iii invocation failures using error codes across Node, Python, Rust, and browser workers. Distinguish permission denials, timeouts, and handler failures, then choose appropriate exception handling and decide whether retrying is suitable.
Run batches of machine learning experiments on remote GPUs over SSH, varying settings and random seeds. The skill schedules jobs, tracks progress, retries GPU memory failures, and cleans up leftover sessions before starting subsequent batches.
Handle network requests blocked by an OpenShell sandbox by checking its current access rules and proposing the smallest necessary change. Wait for approval and confirmation that the policy has reloaded before retrying the request.
Build workflows that extract structured data from LLM responses, check field types and values with Pydantic, and retry failed extractions. Includes examples for nested data, classification, and receiving results as they are generated.
Split independent research or data-entry tasks among parallel workers. Provides a workflow for tracking completion in a table, testing one task first, and using a Python playbook to retry unfinished work and resume interrupted runs.
Build dashboard panels in plain TypeScript with titles, counts, loading states, and retry controls. Includes patterns for escaping external text before HTML insertion to address XSS, where untrusted content can run scripts in a page.
Build dashboard panels with patterns for handling failed API requests. TypeScript examples cover retries, cached data, temporary pauses after repeated failures, loading and error displays, and saving panel size and expansion state in the browser.
Create dashboard panels in plain TypeScript using the browser’s page-building API. Follow a shared base class to add titles, counts, loading indicators, error messages, manual retry buttons, and periodically refreshed content.
Build dashboard panels in vanilla TypeScript with shared loading and error displays, saved panel state, and request handling. Examples show retries with increasing delays and CircuitBreaker integration to pause repeated failures and reuse cached results.
Resume Python tasks after execute_code_sandbox errors or timeouts by saving the attempted code as a script and running it through run_shell. The workflow includes dependency checks, execution timeouts, and verification of generated files such as Excel reports.