internal-comms

An agent skill by anthropics, from anthropics/skills. Tags: anthropic, documents, office.

What it does

A set of resources to help me write all kinds of internal communications, using the formats that my company likes to use. Claude should use this skill whenever asked to write some sort of internal communications (status reports, leadership updates, 3P updates, company newsletters, FAQs, incident reports, project updates, etc.).

Install

With the skills CLI, which installs into Claude Code, Codex, Cursor and other agents:

npx skills add anthropics/skills --skill internal-comms

Or copy the skill folder into Claude Code's skills directory by hand (~/.claude/skills for every project, or .claude/skills inside one):

git clone --depth 1 https://github.com/anthropics/skills
cp -r skills/skills/internal-comms ~/.claude/skills/internal-comms

Safety box score

Grade A, minimal risk: 9 of 100 risk points, rated 2026-10-20. The grade rates what the skill and its scripts can reach on the machine of whoever installs it, across eight categories from shell execution to secrets access. How the score works.

This is a documentation-only skill for drafting internal communications; it ships no executable code. The main risk is that it encourages the agent to pull from broad internal sources like Slack, email, Drive, and Calendar, so installing it can expose company-internal information if those connectors are enabled.

Category levels, from 0 (none) to 3 (high)
Category	Level	Why
Code & shell execution	0 (none)	No scripts, shell commands, or code execution are included; the files are plain markdown guidance.
Network access	1 (low)	The guides direct the agent to use remote company systems such as Slack, Email, Google Drive, and Calendar to gather material, but there is no custom outbound networking code.
Filesystem reach	0 (none)	There are no instructions to read, write, or delete local files outside the skill directory.
Secrets & credentials	1 (low)	The workflows can surface internal Slack, email, document, and calendar content, but the skill never asks for passwords, tokens, keychains, or `.env` files.
Privilege & persistence	0 (none)	Nothing here requires sudo, global installs, services, shell profile edits, or OS settings changes.
Instruction hijack surface	0 (none)	I found no prompt injection, hidden instructions, or commands to ignore higher-priority rules; the only workflow text is ordinary clarification guidance.
Irreversible actions	0 (none)	The skill drafts communications only; it does not send, publish, merge, pay, book, or delete anything.
Transparency	0 (none)	All shipped files are readable markdown; there are no binaries, base64 blobs, installers, or runtime-decoded content.

Before installing

Confirm the agent only has read access to the intended Slack, Email, Drive, and Calendar sources.
Decide whether executive emails and large-company channels should be in scope before enabling the connectors.
If you want to limit exposure, test it first in a sandbox or redacted workspace.

Rated 2026-10-20 by an automated review of 6 files from the skill's repository.

Source

Repository: anthropics/skills (all skills from this repository)
Path: skills/internal-comms/SKILL.md
Branch: main
Updated: 2026-09-19

discernment-nudge — After you give a substantive answer or draft that the user may act on — advice or recommendations, drafted artifacts such as goals, plans, pitches, proposals.
doc-coauthoring — Guide users through a structured workflow for co-authoring documentation.
docx — Use this skill whenever the user wants to create, read, edit, or manipulate Word documents (.docx files) or Word templates (.dotx files). Triggers include.
pdf — Use this skill whenever the user wants to do anything with PDF files.
pptx — Use this skill any time a .pptx or .potx file is involved in any way — as input, output, or both. This includes: creating slide decks, pitch decks.
theme-factory — Toolkit for styling artifacts with a theme. These artifacts can be slides, docs, reportings, HTML landing pages, etc.