Browse reusable Agent Skills, each with a clear purpose and practical guidance.
Spawn additional Gauss Agent instances as autonomous subprocesses for independent long-running tasks. Supports non-interactive one-shot mode (-q) and interactive PTY mode for multi-turn collaboration. Different from delegate_task — this runs a full separate gauss process.
Build, test, and debug Gauss Agent RL environments for Atropos training. Covers the GaussAgentBaseEnv interface, reward functions, agent loop integration, evaluation with tools, wandb logging, and the three CLI modes (serve/process/evaluate). Use when creating, reviewing, or fixing RL environments in the gauss-agent repo.
Built-in MCP (Model Context Protocol) client that connects to external MCP servers, discovers their tools, and registers them as native Gauss Agent tools. Supports stdio and HTTP transports with automatic reconnection, security filtering, and zero-config tool injection.
Remove refusal behaviors from open-weight LLMs using OBLITERATUS — mechanistic interpretability techniques (diff-in-means, SVD, whitened SVD, LEACE, SAE decomposition, etc.) to excise guardrails while preserving reasoning. 9 CLI methods, 28 analysis modules, 116 model presets across 5 compute tiers, tournament evaluation, and telemetry-driven recommendations. Use when a user wants to uncensor, abliterate, or remove refusal from an LLM.
Migrate a user's OpenClaw customization footprint into Gauss Agent. Imports Gauss-compatible memories, SOUL.md, command allowlists, user skills, and selected workspace assets from ~/.openclaw, then reports exactly what could not be migrated and why.
Design and create AI-agent infrastructure for codebases: AGENTS.md, documentation architecture (docs/), linters with actionable errors (scripts/lint-*), harness/ configs, and CI integration. Creates files directly — never writes business/application code.
Publish local Agent Skills to a HiMarket backend instance. Use when the user wants to upload, publish, deploy, or sync skills to HiMarket. Supports batch publishing all skills in a directory with automatic category selection, tag generation, and conflict avoidance.
Generates and syncs AI rule configuration files (.cursorrules, CLAUDE.md, copilot-instructions.md) across 20+ coding tools from a single source. Use when syncing AI rules, running rulesync commands, importing or generating rule files, or managing shared AI coding configurations.
Maintenance orchestrator for the brooks-lint plugin itself. Runs a sequential subagent pipeline — author → eval → QA → trigger-audit → release — to add or edit a skill, refresh the eval suite, keep the four manifests + README + CHANGELOG + AGENTS/GEMINI in sync, audit trigger boundaries, and cut releases. Drives the five agents in .claude/agents/ (skill-author, eval-curator, consistency-qa, trigger-boundary-auditor, release-manager). Triggers when the maintainer asks to work ON brooks-lint itself: "add a new skill", "edit the brooks-debt guide", "update the eval suite", "fix the trigger descriptions", "make this change and validate it", "release brooks-lint", "bump and publish", and follow-ups: "re-run", "re-validate", "update that skill", "redo the audit", "do the X part again". Do NOT trigger for: USING the brooks-lint analysis skills on some target codebase (that's brooks-review / brooks-audit / brooks-debt / brooks-test / brooks-health / brooks-sweep); generic questions about brooks-lint that don't ask to change it; or maintenance of a different plugin.
Create new skills for FastClaw agents. Use when the user asks to create a skill, turn a workflow into a skill, or build reusable automation. Also use when discussing skill format, structure, or best practices.