All Skills

Generate a conventional commit message by analyzing staged git changes. Use when the user wants to create, write, or generate a git commit message from their current staged diff.

Create a `git` commit.

This skill should be used when the user asks to "build background agent", "create hosted coding agent", "set up sandboxed execution", "implement multiplayer agent", or mentions background agents, sandboxed VMs, agent infrastructure, Modal sandboxes, self-spawning agents, or remote coding environments.

This skill should be used when the user asks to "design agent tools", "create tool descriptions", "reduce tool complexity", "implement MCP tools", or mentions tool consolidation, architectural reduction, tool naming conventions, or agent-tool interfaces.

This skill should be used when the user asks to "offload context to files", "implement dynamic context discovery", "use filesystem for agent memory", "reduce context window bloat", or mentions file-based context management, tool output persistence, agent scratch pads, or just-in-time context loading.

This skill should be used when the user asks to "compress context", "summarize conversation history", "implement compaction", "reduce token usage", or mentions context compression, structured summarization, tokens-per-task optimization, or long-running agent sessions exceeding context limits.

This skill should be used when the user asks to "evaluate agent performance", "build test framework", "measure agent quality", "create evaluation rubrics", or mentions LLM-as-judge, multi-dimensional evaluation, agent testing, or quality gates for agent pipelines.

This skill should be used when the user asks to "start an LLM project", "design batch pipeline", "evaluate task-model fit", "structure agent project", or mentions pipeline architecture, agent-assisted development, cost estimation, or choosing between LLM and traditional approaches.

This skill should be used when the user asks to "diagnose context problems", "fix lost-in-middle issues", "debug agent failures", "understand context poisoning", or mentions context degradation, attention patterns, context clash, context confusion, or agent performance degradation. Provides patterns for recognizing and mitigating context failures.

This skill should be used when the user asks to "understand context", "explain context windows", "design agent architecture", "debug context issues", "optimize context usage", or discusses context components, attention mechanics, progressive disclosure, or context budgeting. Provides foundational understanding of context engineering for AI agent systems.

Resolve all active PR comments (conversation + code review).

polish

write-tests

Open a PR

roast-my-code

Triage the following pull request from an external contributor.

Address review feedback and fix failing e2e tests for a pull request.

Store team knowledge, project conventions, and learnings from tasks. Use to remember what works and recall context before new tasks. Connects to a self-hosted Hindsight server. (user)

Store user preferences, learnings from tasks, and procedure outcomes. Use to remember what works and recall context before new tasks. (user)

Store team knowledge, project conventions, and learnings from tasks. Use to remember what works and recall context before new tasks. Connects to Hindsight Cloud. (user)

Complete Hindsight documentation for AI agents. Use this to learn about Hindsight architecture, APIs, configuration, and best practices.

<!--

Orchestrate OpenAI Codex CLI for parallel task execution. As orchestrator, analyze tasks, inject context, manage sessions, and coordinate parallel instances. Use when delegating coding tasks to Codex or running multi-agent workflows. (user)

Research libraries, APIs, and patterns using searchGitHub and Exa tools. Finds real-world implementations and saves structured reports to docs/research/. Use when investigating technologies, debugging issues, or comparing options.