Agent skills for OpenAI Agents SDK

Set up a Replit project with .replit + replit.nix configuration, Secrets,

Monitor Replit deployments with health checks, uptime tracking, resource

Handle Replit resource limits: KV database caps, deployment quotas,

Handle Replit deployment events, build Replit Extensions, and set up

Automate Reply tasks via Rube MCP (Composio).

Automate Reply IO tasks via Rube MCP (Composio).

Clone and explore external GitHub repositories to understand how libraries, frameworks, or dependencies work.

Explore and analyze any repository (local path or remote GitHub/GitLab URL) by delegating to Claude Code CLI (`claude -p`) in…

Bootstrap a repository for agent-driven work: Beads issue tracking, AGENTS.md, CI guardrails, and a verification skill.

Run repo2ai on a repository path and load its full contents as context for the current conversation.

Audit how far a downstream repo has drifted from the upstream repomatic reference.

Prepare a release. Reconcile the changelog, code and docs to the net release state. Then commit, push, and babysit CI until the release PR…

Generate test report. Use when user says "test report", "results summary", "test status", "show results", "test dashboard", or "how did…

Use the moment you're forced into a workaround because the clean Spiderly-native path didn't exist — you looked for a lifecycle hook, an…

Use this skill when the user wants to "report a bug", "file an issue", "report an issue", "submit a bug report", or report any problem…

Narrow conversion skill. Invoke only when the user explicitly asks to convert an existing HTML analytics report into a native Google…

Analyze GitHub repositories for structure, documentation, dependencies, and contribution patterns.

Manages complex multi-language repository architectures through standardized task commands and automated version synchronization.

Use when repurposing a script or video concept across multiple platforms, adapting content from one format to another, creating platform…

HTTP request/response debugging and inspection tools

Assess every user request before answering or acting for reasonableness, ambiguity, hidden hazards, authorization, irreversible effects…