浏览和安装 Killer-Skills 目录中的数千个 AI Agent 技能。支持 Claude Code、Windsurf、Cursor 等。
本地化技能摘要： An operating system for autonomous research — from literature to manuscript inside a governed, checkpointed loop. It covers ai-agents, autonomous-research, checkpointing workflows. This AI agent skill supports Claude Code, Cursor, and Windsurf workflows.
Memory Checkpoint is an AI agent skill that streamlines biomedical literature research by providing a professional MCP server with 40 tools, multi-source search, and full-text access, benefiting developers and researchers.
Create a safe checkpoint git commit on the current branch (avoid competition data, runs, artifacts, secrets).
Review checkpoint specs and tests to identify tests that encode ambiguous interpretations rather than explicit requirements. Use when asked to check checkpoint_N.md against test_checkpoint_N.py, when auditing tests for ambiguity, or when reviewing snapshot eval failures for interpretive issues.
Run after completing significant work — implementing a feature, fixing a bug, refactoring, or any substantial code changes. Proactively ensure code quality before reporting work as done.
Use when running multi-step or long-running agent jobs in aios that require checkpointing, retries, evidence capture, and safe human handoff.
Use when you have a written implementation plan to execute in a separate session with review checkpoints
Run StyLua formatting and Luacheck linting on Lua files
Plan code refactors by defining goals/non-goals, mapping dependencies, sequencing phases, and specifying verification and rollback checkpoints; triggers: refactor plan/restructure/rename/move modules.
Debug preprocessing pipeline failures. Guides through reading checkpoint files, checking step artifacts, interpreting QC metrics, examining visualization PNGs, and identifying which step failed and why. Use when a preprocessing run produces unexpected results, crashes, or generates poor-quality outputs.
To diagnose active, stuck, or failed Kilroy Attractor runs, inspect run artifacts (`manifest.json`, `live.json`, `checkpoint.json`, `final.json`, `progress.ndjson`), resolve run IDs/log roots, identify model/provider routing, and isolate failure causes. Includes CXDB operations for launching/probing CXDB, opening the CXDB UI, and querying run context turns. This skill is useful when investigating run status, debugging retries/failures, explaining model usage, or inspecting CXDB-backed event history.