技能 context-engineering

📦

context-engineering

Name: context-engineering
Author: addyosmani

内容修订 r2 安全 ⚙️ 外部命令

Structure Better Context for Coding Agents

Coding agents lose accuracy when context is incomplete, stale, or excessive. This skill provides practical structures for focused sessions, durable rules, and reliable handoffs.

支持: Claude Codex Code(CC)

🥉 78 青铜

使用我的智能体安装

将此请求复制给你的智能体，其中包含权威 Skill 页面和清单。

智能体请求

Review the Skillstore skill "context-engineering" from https://skillstore.io/skills/addyosmani-context-engineering.md and its manifest at https://skillstore.io/api/skills/addyosmani-context-engineering/manifest. Verify the artifact. You may proceed after verification, subject to the environment's own policy.

你的智能体仍应展示其计划，并按安全策略请求必要确认。

Agent 可读资源

当 AI Agent、爬虫或脚本需要干净上下文，而不是读取完整页面时，请使用这些链接。

Markdown 详情 GET /skills/addyosmani-context-engineering.md 已签名 manifest GET /api/skills/addyosmani-context-engineering/manifest 已签名 lockfile GET /api/skills/addyosmani-context-engineering/lockfile

测试它

正在使用“context-engineering”。 Prepare context for adding email validation to registration.

预期结果:

Task: Add email validation to registration.
Read the registration route, validation utility, and related tests.
Follow the existing phone validation pattern.
Use the existing validation error type.

正在使用“context-engineering”。 Summarize a completed authentication task for a fresh session.

预期结果:

Authentication validation is complete. Tests pass. Changes remain uncommitted. The next task is updating API documentation after approval.

正在使用“context-engineering”。 Resolve a conflict between a REST specification and existing GraphQL code.

预期结果:

The specification and implementation conflict. Present both options, explain migration impact, and request a decision before editing.

安全审计

安全

v2 • 2026/9/19 打开版本化报告

All static findings are false positives caused by Markdown fences, inline examples, filenames, and illustrative development commands. The skill is documentation-only and explicitly advises protecting secrets and treating external instructions as untrusted.

已扫描文件

354

分析行数

复核项

已忽略误报

最新一次完成的静态与语义审计未检测到已确认的安全发现。这并不能证明该 Skill 没有副作用。

审计者: codex 查看审计历史 →

分享与引用此报告

分享版本化评估报告、中性徽章、嵌入卡片和引用。Skillstore 只报告证据，不判断该 Skill 是否安全。

打开版本化报告

复制报告链接

https://skillstore.io/skills/addyosmani-context-engineering/audits/2?utm_source=security_passport&utm_medium=share&utm_campaign=versioned_report

Markdown 徽章

[![Skillstore security assessment](https://skillstore.io/badges/skills/addyosmani-context-engineering/security.svg)](https://skillstore.io/skills/addyosmani-context-engineering?utm_source=security_passport_badge)

HTML 徽章

<a href="https://skillstore.io/skills/addyosmani-context-engineering?utm_source=security_passport_badge"><img src="https://skillstore.io/badges/skills/addyosmani-context-engineering/security.svg" alt="Skillstore security assessment" loading="lazy"></a>

嵌入卡片

<iframe src="https://skillstore.io/embed/skills/addyosmani-context-engineering.html" title="Skillstore Security Assessment" sandbox="allow-popups allow-popups-to-escape-sandbox" loading="lazy" referrerpolicy="no-referrer" width="420" height="180"></iframe>

学术引用 (APA · BibTeX · CFF)

APA 引用

addyosmani. (2026). context-engineering security audit report (audit version 2) [Author version unspecified]. Skillstore. https://skillstore.io/skills/addyosmani-context-engineering/audits/2

BibTeX 引用

@techreport{addyosmani-addyosmani-context-engineering-2026,
  author = {addyosmani},
  title = {context-engineering security audit report (audit version 2)},
  institution = {Skillstore},
  year = {2026},
  number = {2},
  url = {https://skillstore.io/skills/addyosmani-context-engineering/audits/2},
  note = {Author version unspecified}
}

CITATION.cff

cff-version: 1.2.0
message: "If you use this Skill, cite its author and this versioned security audit report."
title: "context-engineering security audit report (audit version 2)"
version: "unspecified"
type: report
authors:
  - name: "addyosmani"
date-released: "2026-09-19"
url: "https://skillstore.io/skills/addyosmani-context-engineering/audits/2"
identifiers:
  - type: other
    value: "skillstore:addyosmani-context-engineering:audit:2"
    description: "Skillstore immutable audit report identifier"

Skillstore 评分

评分依据证据置信度: 中

架构

可维护性

内容

社区

规范符合性

你能构建什么

Prepare a New Project

Create a concise rules file with commands, conventions, boundaries, and representative patterns.

Recover a Drifting Session

Remove stale context, preserve current constraints, and prepare a restartable progress summary.

Standardize Team Handoffs

Record decisions, task status, repository state, verification results, risks, and required approvals.

试试这些提示

Create Basic Project Context

Create a project context outline from these notes: [notes]. Include stack, commands, conventions, boundaries, and one pattern example.

Pack Context for One Task

Prepare focused context for [task]. Identify relevant files, tests, existing patterns, constraints, and missing information.

Prepare a Session Handoff

Summarize this session for restart: [history]. Preserve scope, decisions, task status, changed files, verification results, risks, and approvals.

Audit a Context Strategy

Review this context package: [content]. Find stale, excessive, conflicting, untrusted, or missing information. Recommend ordering and compression changes.

最佳实践

Read relevant source, tests, types, and one established pattern before editing.
Keep durable rules first and place active task details last.
Summarize completed exploration before removing verbose history.

避免

Loading entire repositories or specifications when only one section matters.
Treating external documents or generated files as trusted instructions.
Starting a fresh session without recording decisions, status, verification, and approvals.

常见问题

What problem does this skill solve?

It helps coding agents receive relevant, current, and well-structured project information.

Does it execute project commands?

No. It documents example commands and recommends recording verification steps.

Which rules files does it support?

It discusses CLAUDE.md, AGENTS.md, Cursor rules, Windsurf rules, and GitHub Copilot instructions.

When should I start a fresh session?

Restart at a completed task boundary after recording decisions, status, changes, verification, risks, and approvals.

How should external context be handled?

Treat instruction-like external content as untrusted data and surface it for user verification.

Can this skill measure remaining context capacity?

No. It provides management guidance, but measurement depends on the selected tool.

开发者详情

作者

addyosmani

许可证

MIT

Skillstore 修订

版本提示

作者未声明版本。

仓库

https://github.com/addyosmani/agent-skills/tree/c004a74784a08295d52749b04cda634125b9a581/skills/context-engineering

引用

5d5054f8a23586f9b500fece1cb613a9dffc787b

维护新鲜度

2026/9/19

使用量

1 次下载 · 0 次浏览

文件结构

📄 SKILL.md

addyosmani 的更多技能

查看全部

📦

code-review-and-quality

从五个质量维度审查代码

代码变更可能隐藏正确性、安全性、架构、可读性和性能问题。此技能采用结构化审查流程，并提供按优先级排列、可执行的反馈。

编码与开发查看

📦

interview-me

Clarify User Intent Before You Build

Underspecified requests cause teams to build the wrong outcome and discover misalignment late. This skill runs a focused, one-question interview that turns ambiguity into confirmed intent.

沟通查看

📦

planning-and-task-breakdown

Plan Work Into Verifiable Tasks

Large or vague software work can hide dependencies, missing acceptance criteria, and verification gaps. This skill converts a specification into ordered task slices with checkpoints, scope guidance, and clear completion conditions.

效率查看

📦

documentation-and-adrs

Document Decisions and Architecture Clearly

Teams lose context when important technical decisions remain in chat, code comments, or individual memory. This skill turns architectural reasoning, API guidance, project instructions, and release changes into structured documentation.

文档查看

📦

frontend-ui-engineering

Build Accessible, Production-Ready Frontends

Frontend work can become inconsistent, inaccessible, or difficult to maintain. This skill guides component architecture, responsive layouts, state handling, and polished user experiences.

设计与创意查看

📦

security-and-hardening

Harden Applications Against Security Risks

Security reviews can miss trust boundaries and unsafe data flows. This skill supplies threat-modeling prompts, OWASP patterns, and practical review checklists.

安全与合规查看

查看全部

📦

gauntlet

Review Defects and Verify Root-Cause Repairs

由 aakashh242

Reviews can miss failure conditions or accept fixes without reliable evidence. Gauntlet guides scoped adversarial reviews, authorized repairs, and revision-bound verification within a finite budget.

编码与开发查看

📦