原型 · 预览版:收录官方注册中心里的全部服务器,每 30 分钟同步一次。使用 Google 登录即可撰写评价。原型 · 每 30 分钟更新
PopNx MCP为使用 AI 的人准备的 MCP 服务器 · 用大白话讲清楚

defending-code-reference-harness Skill

代码仓库 ↗

作者:anthropics★ 7,758 (whole repo)9 个 skill

★ Stars are for the whole repo, not each skill

Pick the skill to install

What it does

This repo is a collection of 9 skills

  • Connects Instruction files the AI reads, with steps that call an outside service
  • Account or key Some steps need a key for Anthropic, CLAUDE_CODE_OAUTH_TOKEN (per the README)
  • Category 写代码
Maker’s original description
Skills for threat modeling, scanning, triage, patching, plus an autonomous scanning harness you can /customize
给作者:在 README 中加徽章

如果你是作者,可把这段代码贴到 README。徽章会链接回本页。

[![Featured on PopNx MCP](https://mcp.popnx.com/badge/skill/anthropics-defending-code-reference-harness.svg)](https://mcp.popnx.com/en/skills/anthropics-defending-code-reference-harness)

可搭配使用

在同一工作中把 AI 连到服务的 MCP

REA

Reverse engineer anything from your terminal or agent with one CLI and MCP server.

作者:morluto广泛使用↓ 38.9万/周★ 46.4万5天前更新

MCP · 连接服务在你的电脑上运行

Fallow

Codebase intelligence for TypeScript and JavaScript, exposed as structured MCP analysis tools.

作者:fallow-rs广泛使用↓ 244.1万/周★ 5374今天更新

MCP · 连接服务在你的电脑上运行

Desktop Commander

MCP server for terminal commands, file operations, and process management

作者:wonderwhy-er广泛使用↓ 74万/周★ 1万5天前更新

MCP · 连接服务在你的电脑上运行

相似的 Skill

同类工作,排序与 Skill 列表相同

与相似项目对比
本项
defending-code-reference-harness
reaandrej-karpathy-skillsgraphifyMoneyPrinterTurbo
作者anthropicsmorlutomultica-aiGraphify-Labsharry0703
Skill 数91111
GitHub 星标7,758463,670233,682148,887143,987
最近代码更新2026年8月7日2026年11月17日2026年4月20日2026年11月17日2026年11月16日
许可证–MIT–Apache-2.0MIT

anthropics 提供的 9 个 Skill(指令集),AI 读取后照做 · 不是 MCP server

Pick the skill to install

Install only the ones you use. Open a skill to see how to install it

Install the whole set (9)

If you want every one, let the AI install them in one go. Know 2 things first

  • Every installed skill’s description is loaded into every chat. The more you install, the easier it is for the AI to pick the wrong one
  • Some skills duplicate tools the AI already has built in. Installing only the ones you use works better
Where to install
Please install all 9 skills from https://github.com/anthropics/defending-code-reference-harness: customize, dnr-hunt, dnr-respond, patch, quickstart, threat-model, triage, verify, vuln-scan, for all my projects, putting each at ~/.claude/skills/<skill name> (in Codex use ~/.agents/skills/<skill name>, in Cursor ~/.cursor/skills/<skill name>). Folders in the repo: customize = .claude/skills/customize · dnr-hunt = .claude/skills/dnr-hunt · dnr-respond = .claude/skills/dnr-respond · patch = .claude/skills/patch · quickstart = .claude/skills/quickstart · threat-model = .claude/skills/threat-model · triage = .claude/skills/triage · verify = .claude/skills/verify · vuln-scan = .claude/skills/vuln-scan. First show me every file and tell me whether any has scripts or changes machine settings, then tell me the full path you will install each one to and wait for me to agree.
Please install all 9 skills from https://github.com/anthropics/defending-code-reference-harness: customize, dnr-hunt, dnr-respond, patch, quickstart, threat-model, triage, verify, vuln-scan, into the project this chat is open in (at .claude/skills/<skill name>; in Codex use .agents/skills/<skill name>, in Cursor .cursor/skills/<skill name>). Folders in the repo: customize = .claude/skills/customize · dnr-hunt = .claude/skills/dnr-hunt · dnr-respond = .claude/skills/dnr-respond · patch = .claude/skills/patch · quickstart = .claude/skills/quickstart · threat-model = .claude/skills/threat-model · triage = .claude/skills/triage · verify = .claude/skills/verify · vuln-scan = .claude/skills/vuln-scan. First show me every file and tell me whether any has scripts or changes machine settings, then tell me the project name and the full path you will install each one to and wait for me to agree.

Uploading to Claude on the web and apps: you need 9 uploads, one ZIP per skill. Open each skill in the list below to download it

Checked against official docs 2026年11月12日 · Source: support.claude.com, code.claude.com, learn.chatgpt.com, cursor.com

  • customize

    Adapt this C/C++ ASAN vulnerability pipeline to a different vulnerability class, target shape, language, or detection mechanism. Use when the user wants to port, migrate, retarget, customize, or fork the pipeline for something other than C/C++ memory-safety bugs — web apps, smart contracts, deseria…

  • dnr-hunt

    Proactive threat hunt over web/application logs — no alert in hand. Profiles the corpus, runs a hypothesis-driven hunt loop with a mandatory written ledger, confirms suspects in source, detonates a local PoC, and writes INCIDENTS.json + INCIDENT_REPORT.md. Use when asked to "hunt the logs", "find t…

  • dnr-respond

    Incident response workup for a lead in hand — an alert, an IOC, or a /dnr-hunt finding. Scopes the lead across the logs, verdicts whether the attack succeeded, quantifies blast radius, confirms root cause in source with a local PoC, and writes a proposed (never executed) containment/remediation/rec…

  • patch

    Generate candidate fixes for verified security findings. Consumes TRIAGE.json (preferred), VULN-FINDINGS.json, INCIDENTS.json, or a vuln-pipeline results directory. Pipeline input is delegated to the execution-verified `vuln-pipeline patch` ladder; static-analysis input gets a per-finding patch sub…

  • quickstart

    The front door for this repo. With no argument: a 30-second intro, then an offer to walk you through your first run on the canary target. With a question: answers it from this repo's own docs and source, cites where it looked, and hands you the next command. Use for "how do I…", "why does…", "where…

  • threat-model

    Build a threat model for a target codebase. Three modes: "interview" walks an application owner through the four-question framework and produces a threat model from their answers; "bootstrap" derives a threat model from the code plus past vulnerabilities (CVEs, git history, pentest reports) when no…

  • triage

    Triage a batch of raw security findings. Verify each is real, collapse duplicates, re-rank by derived exploitability, and tag with an owner. Takes a directory or file of scanner output and writes TRIAGE.json + TRIAGE.md sorted by what actually needs engineering attention. Use when asked to "triage…

  • verify

    Verify harness changes end-to-end without docker — drive the real pinned CLI against a header-capturing stub server with the exact env resolve_auth_env() produces.

  • vuln-scan

    Static source-code vulnerability scan. Reads a target directory (and THREAT_MODEL.md if present), spawns parallel review subagents per focus area, and writes VULN-FINDINGS.json + .md for /triage to consume. Read-only — no building, running, or network. For execution-verified crashes, use vuln-pipel…

Skill 和 MCP 有什么不同

MCP = 手

把 AI 连到外部服务或数据,例如读取 Notion 或开发票。需要有程序或服务器在运行。

Skill = 手册

教 AI 怎么做某项工作的文本文件,不连接任何服务。

有些会重叠:少数 Skill 带有调用工具的脚本,少数 MCP 只提供知识。请从你想完成的工作出发。

适用的应用

Claude Code

依据开发者 README 和 repo 中的文件夹

安装

Pick a skill first

This repo has 9 skills. Pick one from the list above; its page shows every way to install it, including letting the AI install it and a ZIP

Let the AI install it
Upload to claude.ai

Go to the skill list ↑

讨论

提问、分享技巧或报告无法使用。按“有帮助”数量排序。

还没有帖子,欢迎第一个提问或分享。

此处内容由用户撰写,不代表 PopNx 团队。

登录后发帖

来自 GitHub

GitHub 星标
7,758
Stars are for the whole repo, not each skill
开发者
anthropics
许可证
未注明许可证 此 repo 未注明许可证,默认作者保留所有权利;转发或商用前请先询问作者。
最近代码更新
2026年8月7日
repo 中的 SKILL.md 文件(含译本和模板)
9
主题
security