jk-context
Explain core Jinkō context, navigation, version management, and domain language for agents and users. Use this skill whenever the user needs a mental model of…
Skills
Find an Agent Skill for your task. Read the guide and copy the install command.
Updated 11-12 00:15
Agents & models
26,180 results
jk-model
Build or edit a Jinkō computational model (QSP/PK-PD) via the jinko-sdk: parameters, categorical parameters, compartments, species, ODEs, reactions, dosing…
jk-protocol
Design or edit multi-arm Jinkō protocol designs via the jinko-sdk. Use this skill whenever the user wants to compare doses, schedules, administration routes,…
rp-optimize-v2
Iterative performance optimization loop using RepoPrompt MCP tools: instrument with debug-only metrics, establish a baseline, then plan → delegate one…
rp-reminder-v2
Reminder to use RepoPrompt MCP tools
subagent-orchestration
Use for Codex multi_agent_v2 subagent orchestration: delegation decisions, spawn_agent prompts, custom agent_type roles, reasoning_effort choices, safe…
con-terminal
Use con terminal and con-cli to inspect tabs, run visible shell commands, create and drive pane-local agent sessions, coordinate parallel work, resume linked…
agent-commerce-engine
A production-ready universal engine for Agentic Commerce. This tool enables autonomous agents to interact with any compatible headless e-commerce backend…
gsdl-tracker-sync
Perform issue-tracker writes for GSDL against whichever tracker is configured — Linear, Jira, GitHub Issues, Notion, or none (local markdown). Creates…
batch-grill-me
A relentless interview that asks every frontier question at once, round by round.
configure-allowlist
Add safe, non-destructive commands to Claude Code's permission allowlist in settings.json — read-only/query MCP tools, common terminal query + navigation…
decision-mapping
Turn a loose idea into a sequenced map of investigation tickets, then drive them to resolution one at a time.
wangchuanfu-perspective
A mental model from the perspective of Wang Chuanfu's engineering spirit and vertical integration strategy. Use when the user explicitly requests this person's perspective, mentions "wangchuanfu-perspective", or wants to apply his core methods to analyze a problem; do not trigger automatically for general questions.
webb-perspective
Answer questions from the perspective of James Webb—the wisdom of large-scale engineering management, the art of scientific administration, the leadership of the Apollo program, and organizational change. Use when the user explicitly requests this figure's perspective, mentions "webb-perspective," or wants to apply his core methods to analyze a problem; do not trigger automatically for general questions.
zhangxue-perspective
Zhang Xue's (founder of Zhangxue Motorcycles) thinking framework and way of expression. Based on in-depth research of 2.5 million follower livestream content on Bilibili, in-depth interviews with authoritative media such as Xinhua News Agency, 30+ first-hand quotes, 15 key decision records, and a complete life timeline, distilling 5 core mental models, 8 decision-making heuristics, and a complete expression DNA. Purpose: to serve as a thinking advisor, analyzing issues such as manufacturing entrepreneurship, product quality, the motorcycle industry, and Chinese manufacturing going global from Zhang Xue's perspective.…
ethos
Explore an agent's code and documentation, confirm its intended behavior with the user, and create or update a local ETHOS.md for evaluation and trace…
ethos-explore
Captures what an AI agent is supposed to do — its purpose, boundaries, and success criteria — as a durable snapshot for anyone building, evaluating, reviewing,…
ethos-orchestrate
Entry point for an AI agent's ETHOS.md: a durable snapshot of what the agent is for, what it must not do, and what success looks like. Routes a request to…
ethos-write
Writes an AI agent's ETHOS.md — a durable snapshot of its purpose, intended behavior, boundaries, and success criteria — from the answers gathered by…
nemo-gym-reward-profiling
Use to help users get started with Nemo Gym reward profiling. Covers the basic gym env start, gym eval run, and gym eval profile workflow, repeated rollouts,…
ethos
Explore an agent's code and documentation, confirm its intended behavior with the user, and create or update a local ETHOS.md for evaluation and trace…
eval-author-audit
Guide coverage audits with milestone check-ins and user-confirmed eval and trace sources. Generate, validate, measure, and report on an audit-spec coverage…
gym-to-atif
Convert one bounded Gym Responses rollout record, or a retained Harbor ATIF from a Gym run, into one canonical ATIF trajectory for Harbor or Eval Author's…
context-blocks
How to manage context blocks (system prompt sections) in NVIDIA OO Agents. Use when configuring what appears in an agent's LLM prompt — adding, overriding,…