642 skills (repositories by diegosouzapw) · sorted by popularity
Prepare a selected batch of pull requests, or proposed code changes, by reviewing overlaps, diagnosing conflicts, and preserving contributor credit. Check the exact version and required authorization before each merge, then report completed work and remaining holds.
Run or inspect local Release-Green checks for a specific code revision or combined pull request candidate. Report blocking failures, diagnostic differences, and missing evidence, compare against the base revision, and identify remaining CI checks.
Manage OmniRoute API keys and provider authentication from the command line. Register, rotate, or revoke keys, inspect usage and expiration, set spending and model restrictions, and start or check OAuth sign-in connections.
Configure prompt compression, which shortens text sent to AI models, through the OmniRoute command line. Adjust RTK filters, Caveman rules, and combined compression modes, then preview the results using real prompts.
Read and update application settings through APIs, including system prompts, reasoning limits, IP filters, and login requirements. Also manage proxy and cache settings, with guidance on how reasoning settings affect requests sent to AI providers.
Start, stop, and restart the OmniRoute server from the command line. Configure its port, background operation, automatic recovery, and system tray integration, or open the dashboard to manage the running server.
Check and control OmniRoute’s MCP server, which connects agents to tools. Inspect tool permission scopes, enable or restart the server, and invoke tools with JSON arguments from the command line.
Manage OmniRoute context settings from the command line, including token budgets and RTK filters for processing context. Switch saved server connections, import or export configurations, and inspect or expire conversation sessions.
Browse and search OmniRoute's AI model catalog from the command line. Filter by provider or capability, check model aliases, validate compatible models before adding them, and maintain manually registered model details.
Create, list, switch, and delete model routing combinations from the command line. Request suggestions using task descriptions, cost limits, and response time limits, with an option to explain recommendations or activate a suggested setup.
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.
Send prompts to LLMs from a terminal, display answers as they arrive, or hold an ongoing conversation. Use files or standard input for prompts, choose models, and set system instructions through OmniRoute.
Manage command-line tools connected to OmniRoute through its API. Inspect tool status, read or change settings, manage Codex profiles and backups, and invoke tool plugins for automation tasks.
Check OmniRoute server health, component status, and live metrics from the command line. Filter alerts or watch a refreshing dashboard to see provider status and circuit breakers, which interrupt requests when failures occur.
Manage OmniRoute API keys by creating, listing, rotating, and revoking them. Set access permissions, allowed models, spending limits, and expiration dates for each key to control access to proxy and management endpoints.
Review OmniRoute audit logs and request history from the command line. Filter records by actor, action, or time, manage access rules, and export logs or compare operational data for compliance reviews.
Manage cached LLM responses, which are saved answers available for reuse. Inspect statistics and stored entries, clear cached data, and configure expiration policies and similarity thresholds that govern when answers can be reused.
Find available AI models across configured providers and browse a catalog that includes provider-specific variants. Inspect individual models and create or update aliases, alternative names used to refer to models.
Manage AI provider connections from the terminal. List configured services, test connections individually or together, rotate credentials, and inspect usage metrics. Validate local configuration without contacting providers when checking its structure.
Find agent skills on GitHub, score their relevance using rule-based checks, scan for malware and embedded secrets, and import them into supported agent directories, including Hermes, Claude Code, Gemini CLI, and OpenCode.
Synchronize OmniRoute configuration, provider connections, and settings with cloud storage. Manage authentication for the cloud worker, a remote service, along with its credentials and remote backup destinations.
Keep coding changes small by questioning unnecessary work and reusing existing code, standard libraries, and native platform features. Apply this approach to implementation, bug fixes, reviews, and dependency choices while preserving validation, security, and accessibility.
Inspect AI costs, token usage—the units used to measure model input and output—and call logs from the OmniRoute command line. Filter records, review spending by connection, and export usage reports for further review.
Connect AI agents to OmniRoute through MCP, a protocol for accessing tools. Use tools for request routing, memory, cache, providers, and audits, with three connection methods and permission scopes that control which operations are available.