Gptme Contrib

Wrap up the session safely: gate on uncommitted/unpushed work and missing journal, refuse to end if anything is unsaved, write the closing summary, then exit the harness when the session was light (stay alive for review when it was substantial). Invoke as /end (Claude Code, Codex) or /skill:end (gptme).

Use when creating or revising an agent's SOUL.md, splitting runtime voice out of broader identity docs, or tightening a vague persona file into a short, opinionated, voice-only artifact without changing the agent's core identity.

Analyze your gptme conversation history for insights like token usage, costs, model preferences, and usage patterns — inspired by Spotify Wrapped.

Query a Home Assistant instance for presence, sensor data, calendar events, and cameras

Structured output formatting for clarity and accessibility. Optimized for command-heavy workflows and neurodivergent accessibility (ADHD, dyslexia, autism). Adapted from ayghri/i-have-adhd.

Add foundational CS knowledge (7 classic books) and session-memory search to Claude Code or Claude Desktop via MCP. Lets Claude answer "how does X work?" by querying indexed books inline, and "what did we discuss about Y?" by searching past sessions. Use this skill when setting up or troubleshooting the rag-mcp-server.

Template for creating new skills in gptme-contrib. Use this as a starting point when creating your own skills.

Auto-discover and run the relevant test suite after making code edits. Use when you've edited source files and want to verify correctness without being told which tests to run. Do NOT use for purely exploratory sessions with no file edits, or when the user has already specified which test command to run.

Systematic code review workflows with bundled utilities for analyzing code quality, detecting patterns, and providing structured feedback. Use this skill when reviewing pull requests or conducting code audits.

Guide to creating gptme plugins with tools, hooks, and commands — covers ToolSpec, lifecycle hooks, custom /commands, testing, and pyproject.toml setup.

Workflow for publishing HTML artifacts (demos, visualizations, interactive content) to the web. Enables agents to share work products publicly via GitHub Pages or similar hosting.

Generate an offline, single-file HTML presentation from structured slide JSON. Use when turning notes, research, demos, or technical explanations into an agent-generated slide deck.

Template and guide for restructuring large documentation files into token-efficient directory structures. Reduces context bloat by 40-60% while maintaining accessibility.

Conduct a structured interview about a new project and generate a ready-to-use CLAUDE.md/AGENTS.md starter so the agent knows your conventions from session one.