Adds Arize AX tracing to an LLM application for the first time. Follows a two-phase agent-assisted flow to analyze the codebase then implement instrumentation after user confirmation. Use when the user wants to instrument their app, add tracing from scratch, set up LLM observability, integrate OpenTelemetry or…
Builds Nango Functions in a checked-out Zero YAML TypeScript Nango project using local files, index.ts registration, nango dryrun, generated tests, and optional nango deploy via CLI. Use when creating, updating, validating, testing, or deploying Nango actions or syncs locally in a repo. This content overlaps with…
Builds Nango Functions without a checked-out Nango project by using the Nango /functions compile, dryrun, dryrun status, and deployment APIs with NANGOSERVERURL and NANGOSECRETKEY. Use when creating, updating, validating, testing, or deploying Nango actions or syncs remotely via API or single-file payloads. This…
A workflow that studies GitHub trends and turns them into three possible project plans, then combines the report and source data into a ZIP file and emails it.
One-command publish a Claude Code skill to ALL major marketplaces: GitHub (npx skills), ClawHub, and community marketplaces (composiohq/awesome-claude-skills, anthropics/skills, daymade/claude-code-skills, obra/superpowers-marketplace). Validates SKILL.md, auto-generates missing files, creates repos, publishes, and…
Use when the user wants to share a project to GitHub. Runs a full pipeline: root audit, file naming and structure, document fixes (headings, code-block language tags, table alignment, explicit command interpreters), generate missing files (LICENSE, .gitignore, CONTRIBUTING.md, Issue/PR templates), README rewrite…
A workflow for preparing a project for publication on GitHub, a website for hosting and sharing code. It reviews the project, fixes documentation and structure, creates common project files, and can create and push a repository.
Convert, install, audit, package, and troubleshoot Claude Code skills for Codex. Use when the user asks to install a Claude skill in Codex, migrate a Claude-oriented skill, adapt a GitHub skill repo, fix Codex skill discovery, package a migrated skill for sharing, or review whether a Claude skill will work well in…
Declare and manage MergeChain PR merge-dependencies from the terminal or AI agent. Use when marking a PR blocked by another, setting up stacked-PR dependencies, or during push/open-PR flows for branches based on non-default bases (auto-detect prerequisite). Writes the visible managed PR-body section and exact hidden…
Run the discovery → synthesis → build → verify → elite-package → distribute loop to turn domain insight into a multi-surface, verified GitHub product. Use when productizing an idea, packaging agentic systems, or raising a repo to elite open-source standards before launch.
Land a work item's pull request with Baron — take it out of draft and merge it. Use when the user says merge it / land it / birleştir / it's approved, ship this PR. Do NOT shell out to gh or az for this; Baron owns the provider call, including the parts that have no REST route.
Move a work item to a workflow role with Baron — guarding backward/reopen moves behind a required one-line reason (posted on the item first). Use when the user asks to change a task's state/column, send it back, reopen it, block/unblock it, or advance it. Roles, not vendor columns — works on any provider Baron binds.
Start work on an EXISTING work item with Baron — load it, cut its canonical branch, move it to inprogress, and sync the local checkout. Use when the user says to start/pick up/resume a known task, bug, or story (by id, key, or URL). To create a new item first, use task-new.
This skill should be used when searching for open source issues, vetting contributions, interpreting viability scores, or planning a search strategy. Covers multi-strategy search, vetting workflow, and score interpretation.
Find open source repositories that add a requested capability to a codebase or website. Use when the user asks for a library, integration, architecture component, or maintained open source option that should fit an existing project.
Analyze a public GitHub repository before choosing complementary open source tools. Use when the user asks what a repository does, what stack it uses, or whether it is active enough to build on.
Use Spokes MCP before inventing code. Triggers on: implement a feature, build an app, add auth/api/ui, reuse existing code, find how I did this before, check my GitHub repos, avoid reinventing the wheel, pull logic from my projects. Always consult Spokes memory of the user's owned GitHub repositories first.