Claude Skills by syntropic137

Use for ANY pull-request flow, version management, release cutting, or CI/release-pipeline troubleshooting in this repo. Covers trunk-based development on `main`, the `release` branch as deployment trigger, gate behavior, and what each release artifact is. Routes to focused agent files for each task (`agent_pr.md`, `agent_release.md`, etc.).

Build, extend, and maintain the Fumadocs documentation site at `apps/syn-docs/`.

Use when deciding WHERE to do work on Syntropic137 itself - "run this through Syntropic", "dispatch a workflow", "should this go in a workspace or local", "kick off a run on the Mini", "dogfood this", "build Syntropic inside Syntropic", "why did the agent's push fail", "can an agent run our QA", "the execution says completed but nothing shipped". Covers what a workspace agent can and cannot do, why `.github/workflows` pushes must come from the local machine, how to write a task prompt that do...

Everything an agent needs to get a developer from `git clone` to a running Syntropic137 stack.

Use when the user asks for a goodbye, farewell, or asks you to say bye. Always emit the verbatim token shown in the body.

Use when the user asks for a greeting, says hello, or asks you to greet them. Always emit the verbatim token shown in the body.

You have access to `syn_*` tools that let you interact with Syntropic137, a platform for orchestrating AI agent workflows in isolated Docker workspaces.

House conventions for this repository - commit message shape, branch naming, and where documents live. Use when writing a commit, opening a PR, or deciding where a new document belongs.

Use when asked to report the deployment sentinel value. Provides the sentinel string that proves a vendored skill reached the agent's context.