Skill Claude Code
A workflow that turns daily recommendation ideas into research work. It reads a day's saved ideas, or creates ideas from scored items, then sends them to the appropriate idea or research pipeline.
Skill Claude CodeCodex
A chatbot-based workflow for reading daily research papers with iDeer, a paper-digest tool.
Skill Claude Code
A daily research digest that gathers items from sources such as arXiv, a research-paper archive, Hugging Face, GitHub, and Semantic Scholar, then summarizes and scores them.
Skill Claude CodeCodex
Integrate a benchmark or custom environment into SAfactory using fixed adapter templates and local contract tests, optionally run Docker/RJob evaluation, or prepare GRPO/RL training. Use for SAfactory onboarding and runtime workflows.
Skill Claude Code
Drive the a3s-box microVM sandbox CLI - a Docker-like runtime that runs OCI/container images in hardware-isolated microVMs (libkrun). Use when the user wants to run, build, exec into, snapshot, or tear down containers with a3s-box, sandbox untrusted or agent-generated code, spin up throwaway isolated environments, or…
Skill Claude CodeCodex
Query read-only trajectory and evaluation records from WT Serving through the trajectoryanalysis domain JSON CLI when an agent needs WT data; excludes Delivery, Landing, production, writes, and failure analysis.
Skill Claude CodeCodex
Analyze finance data through the finance domain tool set (relational, workspace files, SEC filings, XBRL facts, market prices, web sources) when an agent needs finance data; excludes any source outside the exposed tools, writes beyond the declared output contract, and unbounded dumps of raw data.
Skill Claude CodeCodex
SentrySkills is a workspace-local self-guard framework for AI agents.
Skill Claude CodeCodex
Extension layer for SentrySkills. It separates online extra-rule detection from post-model-stage knowledge management.
Skill Claude CodeCodex
Execute privacy and sensitive leakage guarding before output. As long as context contains sensitive information, must trigger this skill even if user only requests explanation/summary. Default to downgrade expression for tool conclusions not multi-source verified.
Skill Claude CodeCodex
Establish security boundaries before execution. Trigger this skill whenever involving command execution, file writing, sensitive data reading, external tool result adoption, or potential unauthorized requests; first output risk assessment and allowed/forbidden action lists.
Skill Claude CodeCodex
Monitor high-risk actions and behavior drift during execution. Trigger this skill when task enters command execution, tool calls, file writing, or batch modification; continuously produce event logs, alerts, and disposition recommendations.
Skill Claude CodeCodex
Run SentrySkills before every task using a rule-first frontend and a risk-gated model backend. The skill/framework decides sync vs async after rule gating.
At most 3 mods per repository are shown here, and a mod shipped inside a plugin is left to that plugin's page — the rest are on their repository pages: