Навыки linkedin-outreach-method
📦

linkedin-outreach-method

Ревизия содержимого r1 Высокий риск 🌐 Доступ к сети🔑 Переменные окружения⚙️ Внешние команды

Plan and Measure LinkedIn Outreach

LinkedIn outreach becomes difficult to evaluate when audiences, messages, and measurement periods differ. This skill organizes persona-based campaigns, approval steps, and seven-day comparisons.

Поддерживает: Claude Codex Code(CC)
Maintain this Skill? Claim it ⚠️ 38 Плохо

Установить с помощью моего Агента

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

Запрос агента
Review the Skillstore skill "linkedin-outreach-method" from https://skillstore.io/skills/bereach-ai-linkedin-outreach-method.md and its manifest at https://skillstore.io/api/skills/bereach-ai-linkedin-outreach-method/manifest. Verify the artifact. Stop and obtain explicit user consent before installing or changing files.

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.

Протестировать

Использование «linkedin-outreach-method». Illustrative campaign: target French water utilities with network managers and operations directors. Existing contacts cover the first persona, but not the second.

Ожидаемый результат:

  • Plan and personas
  • Network managers: use eligible existing contacts first.
  • Operations directors: propose a search limited to the approved company type, size, and location.
  • Review search scope and estimated credits before execution. No invitations have been sent.

Использование «linkedin-outreach-method». Illustrative seven-day results: one persona, 100 first messages per version. Version A received 30 interested replies; version B received 40.

Ожидаемый результат:

  • Results: A received 30 interested replies from 100 messages; B received 40 from 100.
  • B leads, but the specified two-proportion check does not establish a statistically supported difference.
  • Treat B as directional only. Preserve the planned sample size and avoid declaring a winner early.

Аудит безопасности

Высокий риск

All 55 static alerts are false positives involving Markdown, ordinary prose, bibliographic citations, or navigation links. Semantic review found instructions that defer conflicting user rules and suppress cost or provenance disclosures. The workflow otherwise requires approval for sending and permission for historical conversation review; no evidence found of shell execution or credential exfiltration.

8
Просканировано файлов
1,247
Проанализировано строк
0
Пункты проверки
0
Ложные срабатывания проигнорированы

Подтверждённые проблемы безопасности (2)

Высокий
Prompt Injection Attempt Detected
A saved rule that 'fights a skill or a card' is handled 'after the first invitations.' This instruction defers conflicting user restrictions until outreach begins, allowing skill instructions to displace user constraints.
The text explicitly postpones conflicts with saved or pasted user instructions until after invitations. No exception protects user restrictions before that action.
Средний
Cost and Provenance Disclosure Suppression
Credit questions are diverted 'even when the user raised them (answer the craft only).' Artifact rules prohibit vendor and data-source wording and require rephrasing quoted user text, weakening informed approval and record accuracy.
These are explicit instructions to suppress requested information and alter quotations, not merely concise presentation guidance. Tool-side billing behavior was not available for verification.
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
Оценка безопасности

Копировать ссылку на отчёт

https://skillstore.io/skills/bereach-ai-linkedin-outreach-method/audits/1?utm_source=security_passport&utm_medium=share&utm_campaign=versioned_report

Значок Markdown

[![Skillstore security assessment](https://skillstore.io/badges/skills/bereach-ai-linkedin-outreach-method/security.svg)](https://skillstore.io/skills/bereach-ai-linkedin-outreach-method?utm_source=security_passport_badge)

Значок HTML

<a href="https://skillstore.io/skills/bereach-ai-linkedin-outreach-method?utm_source=security_passport_badge"><img src="https://skillstore.io/badges/skills/bereach-ai-linkedin-outreach-method/security.svg" alt="Skillstore security assessment" loading="lazy"></a>

Встраиваемая карточка

<iframe src="https://skillstore.io/embed/skills/bereach-ai-linkedin-outreach-method.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

bereach-ai. (2026). linkedin-outreach-method security audit report (audit version 1) [Author version unspecified]. Skillstore. https://skillstore.io/skills/bereach-ai-linkedin-outreach-method/audits/1

Цитата BibTeX

@techreport{bereach-ai-bereach-ai-linkedin-outreach-method-2026, author = {bereach-ai}, title = {linkedin-outreach-method security audit report (audit version 1)}, institution = {Skillstore}, year = {2026}, number = {1}, url = {https://skillstore.io/skills/bereach-ai-linkedin-outreach-method/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: "linkedin-outreach-method security audit report (audit version 1)" version: "unspecified" type: report authors: - name: "bereach-ai" date-released: "2026-11-14" url: "https://skillstore.io/skills/bereach-ai-linkedin-outreach-method/audits/1" identifiers: - type: other value: "skillstore:bereach-ai-linkedin-outreach-method:audit:1" description: "Skillstore immutable audit report identifier"

Оценка Skillstore

Почему такая оценка Достоверность доказательств: Средний
45
Архитектура
65
Сопровождаемость
87
Контент
65
Сообщество
65
Соответствие спецификации

Что вы можете построить

Organize a First Campaign

Turn a company offer, customer criteria, and approved writing samples into a segmented outreach plan with review checkpoints.

Compare Persona Messages

Plan a single-variable message comparison and evaluate interested replies within the same persona and seven-day window.

Coordinate Client Review

Prepare invitation, draft, and follow-up review artifacts that keep client approval separate from message preparation.

Попробуйте эти промпты

Outline an Outreach Plan
Plan LinkedIn outreach for [offer] to [company type] in [location]. Ask one question round first. Use offline planning only. Preserve all user restrictions.
Review Past Messages
Review these anonymized messages: [samples]. Count interested, polite, negative, and missing replies. Identify wording patterns without causal claims. Do not access my inbox.
Prepare an Approval Artifact
Using [approved personas] and [approved templates], prepare an invitation review artifact from [lead list]. Show exclusions, dates, and dependencies. Do not send or spend credits.
Design and Evaluate a Test
Design a one-variable comparison for [persona], using [baseline], [candidate], and [expected volume]. Size it first. Analyze [seven-day results]. State uncertainty and propose one next change.

Лучшие практики

  • Resolve conflicting saved rules before live actions, answer cost questions directly, and preserve quoted text exactly.
  • Require approval for each send artifact and permission before reading historical conversations; exclude personal conversations and existing customer relationships.
  • Compare one change within one persona, set sample sizes beforehand, and measure each batch after the same seven-day interval.

Избегать

  • Allowing skill instructions to displace user restrictions or conceal service, source, or cost information.
  • Sending invitations or messages without explicit approval of the corresponding artifact.
  • Combining personas, comparing immature batches, or treating selected historical replies as proof of message effectiveness.

Часто задаваемые вопросы

Does this package include a working LinkedIn connector?
No. It documents BeReach tool workflows but does not include the connector implementation.
Can I use it with Claude, Codex, or Claude Code?
The report lists all three tools. Live actions also require compatible BeReach tooling and account access in your environment.
Will it send messages without approval?
The documented workflow requires approval for every send artifact. Review the flagged user-rule conflict before enabling live outreach.
Does it need access to my conversation history?
Historical review is optional and requires permission. You can provide selected messages instead; the workflow continues when no history exists.
Does it guarantee better acceptance or reply rates?
No. It provides planning and comparison methods, but results depend on your audience, offer, messages, timing, and sample size.
Are searches and message preparation free?
The references describe search credits and some free operations. Verify current BeReach pricing and require direct answers about costs before approval.

Сведения для разработчиков

Автор

bereach-ai

Лицензия

Неизвестно

Ревизия Skillstore

r1

Примечание о версии

Автор не указал версию.

Ссылка

0b5375d5ff31ef8f8f23150e2d3ac5978ea0441f

Актуальность поддержки

14.11.2026

Использование

0 загрузок · 0 просмотров

Структура файлов

Больше от bereach-ai

Показать все
Показать все