analyzer
01Agent
Analyze blind comparison results to understand WHY the winner won and generate improvement suggestions.
36 tagged linux, measured the same way as everything else here.
Browse within: audio 9ecs 9mac 9macos 9particles 9simulation 9
Agent
Analyze blind comparison results to understand WHY the winner won and generate improvement suggestions.
Agent
Compare two outputs WITHOUT knowing which skill produced them.
Agent
Evaluate expectations against an execution transcript and outputs.
Agent
Agent "AGENTS" from agent0ai/agent-zero, covering agent profiles dox, purpose, ownership, local contracts and work guidance.
Agent
generate a diary for user.
Agent
GitHub Agentic Workflows (gh-aw) - Create, debug, and upgrade AI-powered workflows with intelligent prompt routing.
Agent Claude Code
Reviews shell scripts for quality, security, and best practices.
Agent Claude Code
Tests installation scripts on fresh environments.
Agent Claude Code
Validates notification functionality across platforms (macOS, Windows, Linux, WSL).
Agent
GitHub Agentic Workflows (gh-aw) - Create, debug, and upgrade AI-powered workflows with intelligent prompt routing.
Agent
GitHub Agentic Workflows (gh-aw) - Create, debug, and upgrade AI-powered workflows with intelligent prompt routing.
Agent
GitHub Agentic Workflows (gh-aw) - Create, debug, and upgrade AI-powered workflows with intelligent prompt routing.
Agent
Analyze blind comparison results to understand WHY the winner won and generate improvement suggestions.
Agent
Compare two outputs WITHOUT knowing which skill produced them.
Agent
Evaluate expectations against an execution transcript and outputs.
Agent
An operator for carrying out explicitly requested tasks on a Windows computer through visible application actions. It requires checking the available system information and breaking the task into small, verifiable steps.
Agent Claude Code
C++/pyext implementation agent for the orkid engine. Use to implement ONE precisely-scoped slice of engine work from a written spec (a JUL/plan doc section, a milestone, a fix with named seams). Give it the spec section, the trouble points that name it, and the definition of done. It edits code and gets it…
Agent Claude Code
Procedural look-dev agent for orkid — authors DSL content (terrain graphs, hypermesh recipes, ptex3d materials, scatter, scene composition) to hit a NAMED visual target, thinking in industry technique (Houdini/World Machine/Blender geometry nodes/games VFX) and compiling it onto orkid primitives. Renders regular…
Agent Claude Code
Perceptual-quality analyst for orkid output artifacts — images, movies, meshes (OBJ), heightmaps. Use for open-ended quality work (why does this look wrong, review N renders, compare silhouettes across seeds, corpus sweeps, triage) AND for improving the vet instruments themselves. Instruments-first discipline; never…
Agent
Live OpenCode agent that uses Gemini for planning and review when the task genuinely needs it.
Agent Claude Code
Expert assistance for building MCP servers in Swift with the FastMCP library. Use proactively when authoring @Tool / @MCPResource / @MCPPrompt types, configuring the FastMCP builder, defining @Generable schemas, or debugging FastMCP server issues.
openSUSE/openSUSE-packaging-skill
Agent
Adversarial pre-commit / pre-SR review of the WHOLE change — spec diff, patches, sources/service moves, build outcome, and the .changes entry — against the actual diff and upstream reality. Use as the final gate before committing or filing a submit request — it plays a hostile Factory reviewer hunting for the decline…
openSUSE/openSUSE-packaging-skill
Agent
Block 3 of the openSUSE-packaging pipeline. Use to commit a green package, submit it to Factory (osc sr) or open the Gitea PR for a git-workflow package, then watch the submission and triage any decline or reviewer comment — looping fixes back to Block 2.
openSUSE/openSUSE-packaging-skill
Agent
Block 2 of the openSUSE-packaging pipeline. Use to actually update a single package (version bump or source-service refresh), rebase/drop its patches, clean the spec, and build it locally until green. Stops at a clean local build + green sourcevalidator — does not submit (unattended-mode commits go only to the…