llm-agents plugins

tigerless-labs/autoharness

Hook

Runs when a session starts, running an inline shell check. From tigerless-labs/autoharness.

tigerless-labs/autoharness

Hook

Runs when the agent finishes a response, running an inline shell check. From tigerless-labs/autoharness.

tigerless-labs/autoharness

Hook

Runs before the agent uses a tool for Skill, Read, Write, Edit, MultiEdit and NotebookEdit tool calls, running an inline shell check (2 commands). From tigerless-labs/autoharness.

XiaoLuoLYG/GOD

Skill Claude CodeCodex

Produce emotion.json and intention.json from workspace context.

XiaoLuoLYG/GOD

Skill Claude CodeCodex

Persist important outcomes from this step to long-term storage with automatic forgetting curve.

XiaoLuoLYG/GOD

Skill Claude CodeCodex

Execute intentions through the environment.

Spark-To-Paper-Skills/paperjury

Plugin Claude Code

Pre-submission AI review and editing for CS-conference papers: direct-edit LaTeX or Markdown (Word via one-time extraction), run an adversarial multi-agent courtroom review with consensus-gated revisions, or run it unattended toward a goal.

Spark-To-Paper-Skills/paperjury

Skill Claude CodeCodex

A tool for reviewing and editing computer-science conference papers in LaTeX or Markdown, the document formats commonly used for research papers. It supports direct edits, structured pre-submission review, and an optional unattended mode for selected fixes.

TheGreenCedar/codex-autoresearch

Instructions file CodexOpenCode

Instructions for TheGreenCedar/codex-autoresearch, covering agents.md, purpose and scope, canonical sources, stable product boundaries and source and package boundaries.

TheGreenCedar/codex-autoresearch

Skill Claude CodeCodex

Triage improvement work and run or resume accepted measured loops in a local project. Architecture, documentation, UX, product study, open research, taste, and one-shot fixes stay direct unless the user explicitly requests repeated measurement with a complete experiment contract.

A-EVO-Lab/a-evolve

Instructions file

Claude Code instructions for A-EVO-Lab/a-evolve, covering claude.md, project overview, repository structure, arc-agi-3 key concepts and game environment (arc-agi sdk).

A-EVO-Lab/a-evolve

Skill Claude CodeCodex

Optimize an AI agent's harness for MCP-Atlas benchmark. Use when analyzing execution traces, diagnosing failures, and proposing improved prompts, skills, or harness code.

A-EVO-Lab/a-evolve

Skill Claude CodeCodex

When to prefer GUI mouse clicks over keyboard shortcuts — especially for formatting, multi-step visual tasks, and cross-application workflows.

A-EVO-Lab/a-evolve

Skill Claude CodeCodex

Reading, writing, and converting common data formats (CSV, Excel, JSON, YAML) with correct handling of encoding, types, and edge cases.

VILA-Lab/FigMirror

Agent Claude Code

Reviewer role in the FigMirror loop. Audits a draft figure against the L1 reference image, L2 aesthetic library, and optional 3D insert; outputs ONE strict JSON object (anchor.whatisright + qualityfloor + fidelity.verdict + focusthemes). Vision-only audit — must NOT read data.txt, drawer notes, or any path outside the…

VILA-Lab/FigMirror

Agent Claude Code

Drawer role in the FigMirror loop. Produces a self-contained matplotlib script + rendered PNG + iter notes that match a reference paper figure's STYLE (not its data). Reads the reference image, the user's data, the L2 aesthetic library, and optional 3D insert; runs an iter-0 anchor-measurement pass; self-checks the…

VILA-Lab/FigMirror

Agent Claude Code

Stage-0 image cropper for FigMirror. Cleans the user-supplied reference screenshot before Drawer/Reviewer style analysis by preserving the raw upload, cropping away captions/page text/screenshot margins/neighboring panels when safe, writing referenceclean.png plus a before/after crop check and report. Dispatched…

VILA-Lab/FigMirror

Command Claude Code

Implement tasks from an OpenSpec change (Experimental).

VILA-Lab/FigMirror

Command Claude Code

Archive a completed change in the experimental workflow.

VILA-Lab/FigMirror

Command Claude Code

Enter explore mode - think through ideas, investigate problems, clarify requirements.

VILA-Lab/FigMirror

Skill Claude CodeCodex

This FigMirror skill should be used when the user asks to "mirror this figure's style", "copy this figure's style", "make a chart that looks like this paper", "reproduce this figure with my data", "match this paper's aesthetic", "I want a NeurIPS-quality version of this", or any variant where they hand over a cropped…

VILA-Lab/FigMirror

Skill Claude CodeCodex

Implement tasks from an OpenSpec change. Use when the user wants to start implementing, continue implementation, or work through tasks.

VILA-Lab/FigMirror

Skill Claude CodeCodex

Enter explore mode - a thinking partner for exploring ideas, investigating problems, and clarifying requirements. Use when the user wants to think through something before or during a change.

gaotiexinqu/OneResearchClaw

Agent Cursor

Score, diagnose, and gate a research report draft for grounded-review. Prefer a model different from the writer when available.