Agent Building skills
Browse reusable Agent Skills, each with a clear purpose and practical guidance.
large-workspace-handling
To partition large workspaces (100+ files) into scoped subagent tasks when context is insufficient.
load-context
To load the most current project context; MUST during prep.
orchestrator-contract
MUST activate when you ARE an orchestrator — you are the top-level agent, you spawn subagents, you delegate work, you coordinate parallel or sequential execution. Defines delegation quality, subagent dispatch, routing, review, and ownership protocol.
ai-agent-redteam
Use when red-teaming an agentic AI / LLM application — indirect & zero-click prompt injection, MCP tool poisoning, persistent memory poisoning, excessive-agency tool abuse, multi-turn jailbreaks, PyRIT/Garak/Promptfoo harnesses
writing-offensive-skills
Use when creating or editing a skill in this offensive-claude repo — for the SKILL.md conventions (trigger descriptions, technique map, runnable scripts, OPSEC/detection, red-flags tables, flowchart rules)
rushdb-agent-memory
Use RushDB as a persistent, structured memory layer for AI agents. Use this skill whenever an agent needs to store session data, remember past decisions, recall prior context by meaning, build a knowledge graph that survives across conversations, associate memories via relationships, or replace a separate vector DB / key-value store with a single ACID-safe graph. Also use when the user says "remember this", "store that", or "what did we decide about X".
athena-init
项目初始化。每个新项目首次使用 Athena 时运行。扫描项目、生成环境脚本、创建 .ai_state/ schema。
athena-preferences
Athena 全局偏好便利层。直接操作 CC 原生 ~/.claude/settings.json 的 permissions.allow/deny 和全局 CLAUDE.md。