AI agent and LLM system engineering reference covering single-agent dev (ReAct, tool calling, plan-execute), multi-agent coordination (swarm, role decomposition, file locking), LLM security (prompt…
$ npx skills add telagod/code-abyss --skill building-agent-systems -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install telagod/code-abyss building-agent-systems --agent claude-codeProject scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).
$ git clone --depth 1 https://github.com/telagod/code-abyss.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/building-agent-systems .claude/skills/building-agent-systems && rm -rf skills-srcUse ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.
Claude Code skills documentation · loads skills from .claude/skills/
Install the "building-agent-systems" agent skill from https://github.com/telagod/code-abyss/tree/main/skills/building-agent-systems into .claude/skills/building-agent-systems/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "building-agent-systems", then confirm the skill loads.Claude Code copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$skill-installer install https://github.com/telagod/code-abyss/tree/main/skills/building-agent-systemsType this inside Codex. $skill-installer <name> installs a curated skill from openai/skills. The installer writes to $CODEX_HOME/skills (default ~/.codex/skills). Restart Codex if the skill does not show up.
$ npx skills add telagod/code-abyss --skill building-agent-systems -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install telagod/code-abyss building-agent-systems --agent codexProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/telagod/code-abyss.git skills-src && mkdir -p .agents/skills && cp -r skills-src/skills/building-agent-systems .agents/skills/building-agent-systems && rm -rf skills-srcUse ~/.agents/skills/ instead of .agents/skills for a personal install.
Codex skills documentation · loads skills from .agents/skills/
Install the "building-agent-systems" agent skill from https://github.com/telagod/code-abyss/tree/main/skills/building-agent-systems into .agents/skills/building-agent-systems/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "building-agent-systems", then confirm the skill loads.Codex copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add telagod/code-abyss --skill building-agent-systems -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install telagod/code-abyss building-agent-systems --agent cursorProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/telagod/code-abyss.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/skills/building-agent-systems .cursor/skills/building-agent-systems && rm -rf skills-srcUse ~/.cursor/skills/ instead of .cursor/skills for a personal install.
Cursor skills documentation · loads skills from .cursor/skills/, .agents/skills/, .claude/skills/, .codex/skills/
Install the "building-agent-systems" agent skill from https://github.com/telagod/code-abyss/tree/main/skills/building-agent-systems into .cursor/skills/building-agent-systems/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "building-agent-systems", then confirm the skill loads.Cursor copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gemini skills install https://github.com/telagod/code-abyss.git --path skills/building-agent-systems--scope user (default) or --scope workspace; --path is the subfolder of the repo that holds the skill; --consent skips the security confirmation prompt.
$ npx skills add telagod/code-abyss --skill building-agent-systems -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install telagod/code-abyss building-agent-systems --agent gemini-cliProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/telagod/code-abyss.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/skills/building-agent-systems .gemini/skills/building-agent-systems && rm -rf skills-srcUse ~/.gemini/skills/ instead of .gemini/skills for a personal install, then run /skills reload.
Gemini CLI skills documentation · loads skills from .gemini/skills/, .agents/skills/
Install the "building-agent-systems" agent skill from https://github.com/telagod/code-abyss/tree/main/skills/building-agent-systems into .gemini/skills/building-agent-systems/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "building-agent-systems", then confirm the skill loads.Gemini CLI copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gh skill install telagod/code-abyss building-agent-systemsInstalls for Copilot at project scope by default; add --scope user for a personal install. Preview a skill first with gh skill preview. Needs GitHub CLI 2.90.0 or later (public preview).
$ npx skills add telagod/code-abyss --skill building-agent-systems -a github-copilotProject install goes to .agents/skills/; add -g for ~/.copilot/skills/.
$ git clone --depth 1 https://github.com/telagod/code-abyss.git skills-src && mkdir -p .github/skills && cp -r skills-src/skills/building-agent-systems .github/skills/building-agent-systems && rm -rf skills-srcUse ~/.copilot/skills/ instead of .github/skills for a personal install. Commit .github/skills so cloud agent and code review can use it.
GitHub Copilot skills documentation · loads skills from .github/skills/, .claude/skills/, .agents/skills/
Install the "building-agent-systems" agent skill from https://github.com/telagod/code-abyss/tree/main/skills/building-agent-systems into .github/skills/building-agent-systems/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "building-agent-systems", then confirm the skill loads.GitHub Copilot copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add telagod/code-abyss --skill building-agent-systems -a opencodeOpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.
$ gh skill install telagod/code-abyss building-agent-systems --agent opencodeProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/telagod/code-abyss.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/skills/building-agent-systems .opencode/skills/building-agent-systems && rm -rf skills-srcUse ~/.config/opencode/skills/ instead of .opencode/skills for a personal install.
OpenCode skills documentation · loads skills from .opencode/skills/, .claude/skills/, .agents/skills/
Install the "building-agent-systems" agent skill from https://github.com/telagod/code-abyss/tree/main/skills/building-agent-systems into .opencode/skills/building-agent-systems/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "building-agent-systems", then confirm the skill loads.OpenCode copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
building-agent-systemsAI agent and LLM system engineering reference covering single-agent dev (ReAct, tool calling, plan-execute), multi-agent coordination (swarm, role decomposition, file locking), LLM security (prompt…
Building Agent Systems is an agent skill from telagod/code-abyss. AI agent and LLM system engineering reference covering single-agent dev (ReAct, tool calling, plan-execute), multi-agent coordination (swarm, role decomposition, file locking), LLM security (prompt injection, jailbreak defense, output filtering), RAG architecture (chunking, hybrid retrieval, rerank), and prompt engineering / evaluation (RAGAS, LLM-as-Judge). Use when building AI agents, designing RAG pipelines, orchestrating multi-agent workflows, hardening LLM apps, or writing prompts.
Its SKILL.md is about 690 tokens, which your agent loads only when the skill is triggered. The skill folder holds 7 other files, including reference files (for example `references/agent-dev.md`, `references/llm-security.md` and `references/multi-agent-coordination.md`).
It sits in AI & LLM Engineering, covering Building AI agents, Prompt injection and agent security and Retrieval-augmented generation. It works with React. The repository describes itself as: Give your AI coding agent a personality. Composable persona + style + skills for Claude Code, Codex, Gemini CLI & OpenClaw. Ships Tech Persona Card v1.0 spec. The licence is MIT.
5 steps, taken from the first numbered list in SKILL.md.
Read from SKILL.md and the folder at commit 2544577. It shows what the files ask for, not the result of running them.
Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.
From allowed-tools in the SKILL.md frontmatter.
No scripts in the folder and no shell commands in SKILL.md.
From the folder's file list and the shell code blocks in SKILL.md.
No URLs in SKILL.md.
From URLs in SKILL.md, links to its own repository left out.
Names no API keys, tokens, secrets or passwords.
From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.
Building Agent Systems loads about 691 tokens when it runs, and up to ~13k if it reads all its reference files. Until then it costs about 129 tokens; SKILL.md has 153 words of instructions outside code blocks.
Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.
The automated check found no risky patterns in SKILL.md.
Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.
The full file from telagod/code-abyss at commit 2544577, republished under its MIT licence (© telagod). 153 words, ~691 tokens.
.claude/skills/building-agent-systems/SKILL.md (or your agent's skills folder). This skill also uses 6 other files; get the full folder from GitHub.判断先于执行：决定「是否做 / 选什么 / 如何取舍」（栈、方案、架构、权衡）前，先读领域判断内核
skills/_kernel/ml/SKILL.md——它管 judgment，本秘典管 execution；冲突时以内核判断为准。
单 Agent 是器，多 Agent 是阵。先选规模，再选模式。
| 意图 | 加载 | 核心 |
|---|---|---|
| 单 Agent 开发（工具调用、ReAct） | agent-dev | ReAct / Plan-Execute / Reflection |
| 多 Agent 协同（>=3 文件 or >=2 并行） | multi-agent-coordination | 蚁群仿生、文件锁、依赖图 |
| 多 Agent 协议细节（消息素、收阵报告） | multi-agent-protocol | Codex 原生协议、角色定义 |
| LLM 安全（注入、越狱、输出过滤） | llm-security | OWASP LLM Top 10 视角 |
| RAG 系统（向量、检索、重排） | rag-system | Chunking / 混合检索 / Cohere rerank |
| Prompt + 评估 | prompt-and-eval | Few-shot / CoT / RAGAS / LLM-as-Judge |
单步任务（一文件、一查询） → 直接执行（不需要 Agent 框架）
多步任务（计划 + 工具） → 单 Agent (ReAct)
复杂任务（>5 步、需反思） → 单 Agent (Plan-Execute / Reflection)
独立并行任务（>=3 文件、>=2 流） → 多 Agent (TeamCreate)
跨域协作（角色明确） → 多 Agent (角色分工)犹豫时优先 TeamCreate — 串行降级容易，并行升级难。
Prompt 即代码须版控 | 输入输出皆验证 | 成本效果平衡 | 持续评估迭代 | 安全边界明确[unverified]| 信号 | 启用 TeamCreate |
|---|---|
| 涉及 ≥3 独立文件 | ✅ |
| 需 ≥2 并行流 | ✅ |
| 总步骤 >10 | ✅ |
| 用户明确要求 | ✅ |
| 单一探索任务 | ❌（用 explorer 或单 Agent） |
| 单文件改动 | ❌（用 worker 或直接执行） |
| 单步任务 | ❌（直接执行） |
详细生命周期、文件锁规则、依赖感知、过载保护、降级链：multi-agent-coordination.md
© telagod, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file
SKILL.md and 6 other files (references) in skills/building-agent-systems of telagod/code-abyss.
Open the folder on GitHubat commit 2544577
Building Agent Systems next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.
| Skill | Stars | Used in | Tokens | Auto-check | Licence | Repo updated |
|---|---|---|---|---|---|---|
| Building Agent Systems this skilltelagod/code-abyss | 243 | — | ~691 | Automated safety check: Pass | MIT | |
| Agent Harness DesignAnastasiyaW/codex-claude-code-config | 154 | — | ~764 | Automated safety check: Pass | MIT | |
| AI Engineerkid-sid/claude-spellbook | 189 | — | ~3.7k | Automated safety check: Pass | MIT | |
| Chatbotmajiayu000/claude-skill-registry | 666 | 1 repos | ~3.3k | Automated safety check: Pass | MIT | |
| Prompt EngineerJeffallan/claude-skills | 12k | 1 repos | ~1.5k | Automated safety check: Pass | MIT | |
| LangchainOrchestra-Research/AI-Research-SKILLs | 13k | 2 repos | ~3.2k | Automated safety check: Pass | MIT |
AnastasiyaW/codex-claude-code-config
Designing agent harnesses and tool systems — risk taxonomy for tools, permission decisions, draft/commit pattern, structured tool results, agent budgets (10 types), context trust labels against…
kid-sid/claude-spellbook
A skill your agent uses when building production LLM applications — designing RAG pipelines, choosing vector databases, implementing agent orchestration, optimizing cost, or adding AI safety…
majiayu000/claude-skill-registry
A skill your agent uses when a support or sales bot on a live website must behave: persona/system prompt, grounding so it cannot invent prices or policy, jailbreak and injection defense, the human…
Jeffallan/claude-skills
Designs, tests and refines LLM prompts: zero-shot, few-shot and chain-of-thought patterns, system prompts, structured output schemas and evaluation test suites.
Orchestra-Research/AI-Research-SKILLs
Framework for building LLM-powered applications with agents, chains, and RAG.
jeremylongshore/tons-of-skills-marketplace
Build and deploy generative AI agents on Vertex AI: Gemini model selection, RAG with grounded retrieval, function calling, multimodal extraction, evaluation, and Agent Engine deployment with…
telagod/code-abyss
Scans code with a bundled Node scanner for injection, secret leaks and other dangerous patterns, and requires documented decisions for accepted risks.
telagod/code-abyss
Distills a recurring agent voice from conversations into a restricted Persona Voice Card, validates it for schema, safety and distinctness, and prepares it for community submission.
telagod/code-abyss
Distills repeated workflows into new skills, improves existing ones and promotes them through local, project and community tiers after a default-deny safety scan.
telagod/code-abyss
Routes Word document tasks to the right tool: pandoc for text, raw OOXML for structure and comments, docx-js for new files, and a mandatory redlining flow for edits to others' documents.
telagod/code-abyss
Picks the right Python library or CLI tool for a PDF task, text and table extraction, merging, splitting, OCR, watermarking or form filling, and points to a matching recipe.
telagod/code-abyss
Checks what a code change touched, how far its impact reaches and whether design docs, tests and README files kept up, before commit or in review.
Works with
Categories
AI agent and LLM system engineering reference covering single-agent dev (ReAct, tool calling, plan-execute), multi-agent coordination (swarm, role decomposition, file locking), LLM security (prompt…. Building Agent Systems is an agent skill from telagod/code-abyss. AI agent and LLM system engineering reference covering single-agent dev (ReAct, tool calling, plan-execute), multi-agent coordination (swarm, role decomposition, file locking), LLM security (prompt injection, jailbreak defense, output filtering), RAG architecture (chunking, hybrid retrieval, rerank), and prompt engineering / evaluation (RAGAS, LLM-as-Judge).
Building Agent Systems fits situations like: building AI agents; designing RAG pipelines; orchestrating multi-agent workflows; hardening LLM apps.
Run `npx skills add telagod/code-abyss --skill building-agent-systems -a claude-code`. Or copy the skill folder (skills/building-agent-systems in telagod/code-abyss) into .claude/skills/building-agent-systems in your project. Claude Code loads it when a task matches its description.
Run `npx skills add telagod/code-abyss --skill building-agent-systems -a codex`. Or copy the skill folder (skills/building-agent-systems in telagod/code-abyss) into .agents/skills/building-agent-systems in your project. Codex loads it when a task matches its description.
Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add telagod/code-abyss --skill building-agent-systems -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/building-agent-systems, .gemini/skills/building-agent-systems, .github/skills/building-agent-systems and .opencode/skills/building-agent-systems in your project.
SKILL.md names no scripts, command-line tools or credentials: Building Agent Systems is instructions for the agent only.
SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.
Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.
Building Agent Systems is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.
About 691 tokens (SKILL.md is roughly 2.8k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full. Its references folder adds about 13k tokens, read only when the agent opens those files.
Skills that share tags, products or a category with Building Agent Systems: Agent Harness Design (AnastasiyaW/codex-claude-code-config, 154 stars), AI Engineer (kid-sid/claude-spellbook, 189 stars), Chatbot (majiayu000/claude-skill-registry, 666 stars) and Prompt Engineer (Jeffallan/claude-skills, 12k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
telagod (a GitHub user) maintains it in telagod/code-abyss, which has 243 GitHub stars. The repository holds 38 skills in this directory. The repository was last updated on July 19, 2026.
Source: telagod/code-abyss on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.
