agentrigs
+ submit rig
~ / rigs / bojieli / ai-agent-book

bojieli/ai-agent-book

《深入理解 AI Agent：设计原理与工程实践》（李博杰 著）开源主仓库：全书正文、编译版 PDF 与按章配套代码

↗ GitHub ★ 52.5k apache-2.0 updated 9d ago project Claude Code
share on X
ARCHETYPE
Skill Collector
Ten-plus skills loaded on demand. A procedural-knowledge library.
CONTEXT TAX · EVERY TURN
~1.3k tokens
Featherweight · median rig: 2.3k · breakdown
GUARDRAILS
0/5
No committed guardrails · details

Copy this rig

# review before running: this installs third-party code
$ npx degit bojieli/ai-agent-book/skills ./rig-ai-agent-book/skills

MCP servers are added to Claude Code at local scope; env vars are shown as YOUR_… placeholders — we never store values. Files are fetched with degit into a separate folder so you can review before merging.

$ npx degit bojieli/ai-agent-book/chapter10/multi-role-transfer/skills/coding .claude/skills/coding
$ npx degit bojieli/ai-agent-book/chapter10/multi-role-transfer/skills/data_analysis .claude/skills/data_analysis
$ npx degit bojieli/ai-agent-book/chapter10/multi-role-transfer/skills/research .claude/skills/research
$ npx degit bojieli/ai-agent-book/chapter10/multi-role-transfer/skills/triage .claude/skills/triage
$ npx degit bojieli/ai-agent-book/chapter10/multi-role-transfer/skills/writing .claude/skills/writing
$ npx degit bojieli/ai-agent-book/chapter2/agent-skills-ppt/skills/pptx .claude/skills/pptx
$ npx degit bojieli/ai-agent-book/skills/agent-evaluation .claude/skills/agent-evaluation
$ npx degit bojieli/ai-agent-book/skills/agent-evolution .claude/skills/agent-evolution
$ npx degit bojieli/ai-agent-book/skills/agent-state-bar .claude/skills/agent-state-bar
$ npx degit bojieli/ai-agent-book/skills/async-event-agent .claude/skills/async-event-agent
$ npx degit bojieli/ai-agent-book/skills/bad-case-to-dpo .claude/skills/bad-case-to-dpo
$ npx degit bojieli/ai-agent-book/skills/coding-agent-harness .claude/skills/coding-agent-harness
$ npx degit bojieli/ai-agent-book/skills/computer-use .claude/skills/computer-use
$ npx degit bojieli/ai-agent-book/skills/context-compression .claude/skills/context-compression
$ npx degit bojieli/ai-agent-book/skills/context-engineering .claude/skills/context-engineering
$ npx degit bojieli/ai-agent-book/skills/error-recovery .claude/skills/error-recovery
$ npx degit bojieli/ai-agent-book/skills/eval-dataset-design .claude/skills/eval-dataset-design
$ npx degit bojieli/ai-agent-book/skills/knowledge-org .claude/skills/knowledge-org
$ npx degit bojieli/ai-agent-book/skills/kv-cache-design .claude/skills/kv-cache-design
$ npx degit bojieli/ai-agent-book/skills/loop-engineering .claude/skills/loop-engineering
$ npx degit bojieli/ai-agent-book/skills/mcp-skill-hub .claude/skills/mcp-skill-hub
$ npx degit bojieli/ai-agent-book/skills/memory-system .claude/skills/memory-system
$ npx degit bojieli/ai-agent-book/skills/multi-agent-design .claude/skills/multi-agent-design
$ npx degit bojieli/ai-agent-book/skills/post-training-strategy .claude/skills/post-training-strategy
$ npx degit bojieli/ai-agent-book/skills/rag-pipeline .claude/skills/rag-pipeline
$ npx degit bojieli/ai-agent-book/skills/reward-design .claude/skills/reward-design
$ npx degit bojieli/ai-agent-book/skills/tool-design .claude/skills/tool-design
$ npx degit bojieli/ai-agent-book/skills/tool-discovery .claude/skills/tool-discovery

This rig commits no guardrails. Here is the community baseline instead — the deny/ask rules most often found across all 7,204 rigs:

{
  "permissions": {
    "deny": [
      "Read(./.env)",
      "Read(**/.env)",
      "Read(~/.ssh/**)",
      "Bash(rm -rf *)",
      "Read(**/*.pem)",
      "Bash(rm -rf /)",
      "Bash(git push --force:*)",
      "Bash(sudo *)",
      "Read(.env)",
      "Bash(rm -rf /*)",
      "Read(./.env.*)",
      "Read(~/.aws/**)",
      "Bash(git push --force*)",
      "Bash(rm -rf:*)",
      "Read(**/*.key)",
      "Read(**/.env.*)",
      "Bash(sudo:*)",
      "Bash(git reset --hard*)",
      "Bash(git reset --hard:*)",
      "Read(.env.*)"
    ],
    "ask": [
      "Bash(git push:*)",
      "Bash(git push *)",
      "Bash(git commit:*)",
      "Bash(rm *)",
      "Bash(rm:*)",
      "Bash(git rebase *)",
      "Bash(wget *)",
      "Bash(npm publish:*)",
      "Bash(git commit *)",
      "Bash(gh pr merge *)"
    ]
  }
}

Skills (28)

codingdata_analysisresearchtriagewritingpptxagent-evaluationagent-evolutionagent-state-barasync-event-agentbad-case-to-dpocoding-agent-harnesscomputer-usecontext-compressioncontext-engineeringerror-recoveryeval-dataset-designknowledge-orgkv-cache-designloop-engineeringmcp-skill-hubmemory-systemmulti-agent-designpost-training-strategyrag-pipelinereward-designtool-designtool-discovery

Similar rigs

byronxlg/skillfold
Declarative skill manager for Claude Code and Codex. Declare skills in YAML, pin exact revisions in a lockfile, install them reproducibly into .claude/skills.
★ 15 project Claude CodeCodex 12 skills 1d ago
Skill Collector 2.2k tok ·
ana52070/claude-code-setup
—
★ 1 setup Claude Code 17 skills 3mo ago
Skill Collector 1.2k tok ·
muratcankoylan/Agent-Skills-for-Context-Engineering
A comprehensive collection of Agent Skills for context engineering, multi-agent architectures, and production agent systems. Use when building, optimizing, or debugging agent systems that require effective context management.
★ 18.1k project Claude CodeCodex 18 skills 8d ago
Skill Collector 3.8k tok ·
designgrappler/agent-os
Agent OS is a management layer for complex, multi-agent AI projects. Instead of letting agents get lost in endless conversational loops, it enforces a disciplined workflow: upfront planning, shared context, scoped work tracks, and strict qu
★ 1 project Claude Code 19 skills 28d ago
Skill Collector 1.2k tok ·
copied ✓