Навыки md-context-writer

📦

md-context-writer

Name: md-context-writer
Author: nexaiguy

v1.1 Ревизия содержимого r1 Безопасно ⚙️ Внешние команды🌐 Доступ к сети🔑 Переменные окружения

Write Repository-Grounded Agent Instructions

Stale agent instructions cause incorrect commands and repeated repository mistakes. This guide helps agents review repository facts and draft concise instructions without claiming unavailable automation.

Поддерживает: Claude Codex Code(CC)

🥉 77 Бронза

Maintain this Skill? Claim it 🥉 77 Бронза

Установить с помощью моего Агента

Скопируйте этот запрос в своего Агента. Он содержит каноническую страницу Skill и манифест.

Запрос агента

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

Ваш Агент по-прежнему должен показать план и запросить все подтверждения, требуемые политикой безопасности.

Ресурсы для AI-агентов

Используйте эти ссылки, когда AI-агенту, crawler или script нужен чистый контекст вместо полной страницы.

Markdown-детали GET /skills/nexaiguy-md-context-writer.md Подписанный manifest GET /api/skills/nexaiguy-md-context-writer/manifest Подписанный lockfile GET /api/skills/nexaiguy-md-context-writer/lockfile

Протестировать

Использование «md-context-writer». Review an old instruction file containing an obsolete test command, a removed source directory, and an embedded database password.

Ожидаемый результат:

Command review: Flag the obsolete command and propose the current CI command only after confirming it in repository configuration.
Path review: Identify the removed directory and reference a replacement only when repository files support the change.
Secret review: Remove the credential value, retain only the variable name, and recommend rotation without repeating the password.
Validation status: Manual review only; the referenced linter is not included.

Использование «md-context-writer». Plan a shorter instruction file for a monorepo with separate frontend and backend conventions.

Ожидаемый результат:

Shared instructions: Keep repository-wide commands and completion checks in the root file.
Scoped rules: Propose separate frontend and backend rules tied to verified directory paths.
Review checkpoint: Present the proposed diff and explain moved or removed sections before applying changes.

Аудит безопасности

Безопасно

v1 • 02.11.2026 Открыть версионный отчет

All 20 static findings are false positives involving Markdown formatting, attribution links, and an example advising credential removal and rotation. No evidence found of malicious command execution, credential access, exfiltration, reconnaissance, or prompt injection in the supplied guide. Referenced scripts and templates are absent, so their behavior and claimed test coverage cannot be verified.

Просканировано файлов

116

Проанализировано строк

Пункты проверки

Ложные срабатывания проигнорированы

Факторы риска

⚙️ Внешние команды (16)

SKILL.md:22 SKILL.md:24 SKILL.md:26 SKILL.md:27 SKILL.md:34 SKILL.md:64-67 SKILL.md:67-68 SKILL.md:68-69 SKILL.md:69-75 SKILL.md:75-81 SKILL.md:81 SKILL.md:82 SKILL.md:84-87 SKILL.md:87-89 SKILL.md:89-93 SKILL.md:93-97

🌐 Доступ к сети (2)

SKILL.md:14 SKILL.md:115

🔑 Переменные окружения (1)

SKILL.md:84

Последний завершенный статический и семантический аудит не обнаружил подтвержденных проблем безопасности. Это не доказывает отсутствие побочных эффектов у навыка.

Аудитор:: codex

Поделиться и цитировать этот отчет

Делитесь версионным отчетом об оценке, нейтральным значком, встраиваемой карточкой и цитатами. Skillstore публикует доказательства, не решая, безопасен ли этот Skill.

Открыть версионный отчет

Копировать ссылку на отчёт

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

Значок Markdown

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

Значок HTML

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

Встраиваемая карточка

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

Академические ссылки (APA · BibTeX · CFF)

Цитата APA

nexaiguy. (2026). md-context-writer security audit report (audit version 1) [Author version 1.1]. Skillstore. https://skillstore.io/skills/nexaiguy-md-context-writer/audits/1

Цитата BibTeX

@techreport{nexaiguy-nexaiguy-md-context-writer-2026,
  author = {nexaiguy},
  title = {md-context-writer security audit report (audit version 1)},
  institution = {Skillstore},
  year = {2026},
  number = {1},
  url = {https://skillstore.io/skills/nexaiguy-md-context-writer/audits/1},
  note = {Author version 1.1}
}

CITATION.cff

cff-version: 1.2.0
message: "If you use this Skill, cite its author and this versioned security audit report."
title: "md-context-writer security audit report (audit version 1)"
version: "1.1"
type: report
authors:
  - name: "nexaiguy"
date-released: "2026-11-02"
url: "https://skillstore.io/skills/nexaiguy-md-context-writer/audits/1"
identifiers:
  - type: other
    value: "skillstore:nexaiguy-md-context-writer:audit:1"
    description: "Skillstore immutable audit report identifier"

Оценка Skillstore

Почему такая оценка Достоверность доказательств: Средний

Архитектура

Сопровождаемость

Контент

Сообщество

Соответствие спецификации

Что вы можете построить

Create Instructions for a New Repository

Draft concise agent guidance from manifests and CI configuration, marking anything that still requires maintainer confirmation.

Review Stale Onboarding Guidance

Compare an existing instruction file with current commands and paths, then review proposed corrections before accepting a diff.

Organize Monorepo Rules

Separate shared instructions from area-specific rules and identify where automated drift checks would require additional tooling.

Попробуйте эти промпты

Draft a Basic Instruction File

Draft CLAUDE.md from this repository's manifests and CI files. Keep it under 200 lines. Mark unverified commands and do not run missing helpers.

Review Existing Instructions

Review AGENTS.md against current repository files. Identify stale commands, missing paths, and conflicting rules. Show a proposed diff with reasons before applying changes.

Separate Scoped Rules

Propose splitting this CLAUDE.md into shared instructions and path-scoped .claude/rules files. Verify directory paths and preserve existing intent. Show the complete proposed diff.

Plan Evidence-Based Drift Checks

Audit instructions across this monorepo using workspace manifests and CI configuration. Record evidence, flag unverifiable claims, and propose drift checks without assuming missing scripts exist.

Лучшие практики

Ground each command and path in current repository files, and distinguish configured commands from commands actually executed.
Keep shared instructions concise and scope specialized rules to verified paths.
Review the proposed diff and redact secret values; rotate exposed credentials rather than only deleting them from documentation.

Избегать

Assuming the referenced scripts, templates, or claimed tests are included in this package.
Copying example commands or paths without checking the target repository.
Embedding credential values or silently deleting maintainer instructions during a rewrite.

Часто задаваемые вопросы

Does this package include a working linter?

No. It contains only the public guide. The referenced fact collector and linter scripts are not included.

Can I use the guide with Claude, Codex, and Claude Code?

Yes, as documentation guidance. Actual file loading and instruction precedence depend on the target tool and must be checked separately.

How does this differ from an initial instruction draft?

It emphasizes repository evidence, reviewing existing instructions, and organizing scoped rules. Continuous automated checks require separate tooling.

Will it rewrite my files without approval?

The guide directs the agent to show a diff and explain removals. Your agent's permission settings still control actual file changes.

Can it prevent instruction drift in CI?

The guide describes CI linting, but provides no executable implementation. Obtain and review suitable tooling before adding a check.

How should exposed credentials be handled?

Remove credential values from instructions, retain variable names when useful, and rotate exposed credentials. Do not reproduce secret values in review output.

Сведения для разработчиков

Автор

nexaiguy

Лицензия

MIT

Версия автора

v1.1

Ревизия Skillstore

Примечание о версии

Заявленная автором версия не соответствует SemVer.

Репозиторий

https://github.com/nexaiguy/nex-ai-skills/tree/463aaff26593654193deb52f24d18e80ec21e323/skills/md-context-writer

Ссылка

3ddfdca559084abffbfdd188f2ba14b597dcfd9c

Актуальность поддержки

02.11.2026

Использование

0 загрузок · 0 просмотров

Структура файлов

📄 SKILL.md