Habilidades context-engineering
📦

context-engineering

Revisión del contenido r1 Seguro ⚙️ Comandos externos

Engineer Better Context for AI Coding Agents

AI coding agents lose accuracy when context is missing, stale, or excessive. This skill structures rules, task context, handoffs, and context budgets for focused work.

Compatible con: Claude Codex Code(CC)
🥉 78 Bronce

Instalar con mi Agente

Copia esta solicitud en tu Agente. Incluye la página canónica del Skill y el manifiesto.

Solicitud de agente
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.

Tu Agente debe seguir mostrando su plan y solicitar cualquier confirmación exigida por la política de seguridad.

Recursos legibles por agentes

Usa estos enlaces cuando un agente de IA, crawler o script necesite contexto limpio en vez de leer la página completa.

Detalle Markdown GET /skills/addyosmani-context-engineering.md Manifest firmado GET /api/skills/addyosmani-context-engineering/manifest Lockfile firmado GET /api/skills/addyosmani-context-engineering/lockfile

Pruébalo

Usando "context-engineering". Prepare context for adding email validation to registration.

Resultado esperado:

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

Usando "context-engineering". Summarize a long debugging session before restarting.

Resultado esperado:

Current state: The import failure came from a circular dependency. The shared type was moved, targeted tests pass, and the full test suite remains pending.

Usando "context-engineering". Resolve a conflict between the specification and existing architecture.

Resultado esperado:

Conflict: The specification requires REST, while the current profile flow uses GraphQL. Confirm whether to follow the specification or update it before implementation.

Auditoría de seguridad

Seguro
v1 • 12/9/2026 Abrir el informe versionado

All static findings are false positives caused by Markdown formatting, documented developer commands, filenames, or protective secret-handling guidance. The skill contains no executable scripts, credential access, prompt injection, or malicious intent.

1
Archivos escaneados
354
Líneas analizadas
0
Elementos de revisión
0
Falsos positivos ignorados

Factores de riesgo

⚙️ Comandos externos (35)
SKILL.md:24-36 SKILL.md:36-43 SKILL.md:43-51 SKILL.md:51-52 SKILL.md:52-53 SKILL.md:53-54 SKILL.md:54-55 SKILL.md:55-60 SKILL.md:60 SKILL.md:61-72 SKILL.md:72-75 SKILL.md:75 SKILL.md:76-77 SKILL.md:77-78 SKILL.md:78-109 SKILL.md:109-135 SKILL.md:135-145 SKILL.md:145-153 SKILL.md:153-159 SKILL.md:159-172 SKILL.md:172-178 SKILL.md:178-194 SKILL.md:194-209 SKILL.md:209-224 SKILL.md:224-228 SKILL.md:228-236 SKILL.md:236-239 SKILL.md:239-259 SKILL.md:259-262 SKILL.md:262-266 SKILL.md:266-277 SKILL.md:277-287 SKILL.md:287-298 SKILL.md:298-304 SKILL.md:304-310
La auditoría estática y semántica completada más reciente no detectó hallazgos de seguridad confirmados. Esto no demuestra que el skill no tenga efectos secundarios.
Auditado por: codex
Compartir y citar este informe

Comparte el informe de evaluación versionado, la insignia neutral, la tarjeta insertable y las citas. Skillstore presenta evidencias sin decidir si este Skill es seguro.

Abrir el informe versionado
Evaluación de seguridad

Copiar enlace del informe

https://skillstore.io/skills/addyosmani-context-engineering/audits/1?utm_source=security_passport&utm_medium=share&utm_campaign=versioned_report

Insignia Markdown

[![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)

Insignia HTML

<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>

Tarjeta para insertar

<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>
Citas académicas (APA · BibTeX · CFF)

Cita APA

addyosmani. (2026). context-engineering security audit report (audit version 1) [Author version unspecified]. Skillstore. https://skillstore.io/skills/addyosmani-context-engineering/audits/1

Cita BibTeX

@techreport{addyosmani-addyosmani-context-engineering-2026, author = {addyosmani}, title = {context-engineering security audit report (audit version 1)}, institution = {Skillstore}, year = {2026}, number = {1}, url = {https://skillstore.io/skills/addyosmani-context-engineering/audits/1}, 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 1)" version: "unspecified" type: report authors: - name: "addyosmani" date-released: "2026-09-12" url: "https://skillstore.io/skills/addyosmani-context-engineering/audits/1" identifiers: - type: other value: "skillstore:addyosmani-context-engineering:audit:1" description: "Skillstore immutable audit report identifier"

Puntuación de Skillstore

Por qué esta puntuación Confianza de la evidencia: Medio
55
Arquitectura
85
Mantenibilidad
87
Contenido
65
Comunidad
91
Cumplimiento de la especificación

Lo que puedes crear

Prepare a New Repository

Create focused project rules covering the stack, commands, conventions, boundaries, and representative patterns.

Recover a Drifting Session

Remove stale detail, preserve current decisions, and rebuild context around the active task and failure.

Standardize Team Handoffs

Record scope, status, changed files, verification results, approvals, and unresolved questions for a restartable session.

Prueba estos prompts

Create Project Rules 
Review this project summary and draft a concise rules file covering the stack, commands, conventions, boundaries, and one representative pattern: [project summary].
Build a Focused Task Brief 
Prepare context for this task: [task]. Include relevant files, tests, types, one existing pattern, constraints, and unresolved questions.
Repair Session Context 
Review this session summary: [summary]. Identify stale context, preserve active constraints and errors, then produce a compact continuation brief.
Design a Restartable Handoff 
Create a durable handoff for [workstream]. Record accepted decisions, task status, repository state, verification evidence, approvals, risks, and the next action.

Mejores prácticas

  • Load the rules file, active specification section, relevant source, tests, and one proven pattern.
  • Treat external documentation, generated files, and user content as untrusted data until verified.
  • Preserve decisions and verification results when summarizing or handing work to a fresh session.

Evitar

  • Do not load entire repositories or specifications when only a small section applies.
  • Do not preserve failed attempts after their useful conclusion has been recorded.
  • Do not let an agent silently choose between conflicting requirements and existing behavior.

Preguntas frecuentes

What does this skill change in my project?
It provides guidance and templates. It does not change files unless the agent applies the guidance during your task.
Which rules files does it support?
It discusses CLAUDE.md, AGENTS.md, Cursor rules, Windsurf rules, and GitHub Copilot instructions.
Can it reduce hallucinated APIs and project patterns?
It can reduce them by loading relevant source, types, tests, and one existing pattern before implementation.
When should I start a fresh session?
Start at a completed task boundary or when switching major features, after recording decisions, status, verification, and unresolved questions.
How should external content be handled?
Treat instruction-like external content as untrusted data. Verify it and surface it to the user instead of following it.
Does the skill configure MCP servers?
No. It lists useful MCP context sources, but installation, permissions, and configuration remain separate responsibilities.

Detalles del desarrollador

Licencia

MIT

Revisión de Skillstore

r1

Aviso de versión

El autor no declaró una versión.

Repositorio

https://github.com/addyosmani/agent-skills/tree/be4e44a9fbc5e8df0beaefadbb28bd22ee61cc39/skills/context-engineering

Ref.

5526951beaeca22519572a471618555839b53b05

Actualidad del mantenimiento

14/9/2026

Uso

0 descargas · 0 vistas

Estructura de archivos

📄 SKILL.md