Publisher: Anthropic · Editorial profile by AI Tools Ratings · Review method
Not runtime tested; source-document review only. No security certification.
What task is this skill designed for?
Draft a weekly project update that clearly separates completed work, next actions and blockers without adding unsupported progress claims.
What input and output should you expect?
Input: Approved facts, the audience, the update period, the desired communication type and any sensitive details that must be omitted.
Output: Expected, not independently tested: a draft internal message suited to the selected format. Creating the draft does not send email or post to a team channel.
What does it need to run?
A Claude-compatible skill environment and the accompanying examples directory. No messaging account is required for drafting; publishing needs a separately authorized channel integration.
Published by Anthropic as a Claude skill example; its repository documents Claude Code installation. Not independently installed or executed here.
How should you approach installation?
- Read the pinned source and inspect the format examples that match your use case.
- Install the complete folder so referenced guidance is available.
- Trial a synthetic weekly update and review factual accuracy before using real internal material.
Installation guide: discovery, dependencies and runtime checks
What files, accounts or data can it access?
Reads project context and writes a draft. Internal reports can expose staffing, customer or incident details, so confirm the intended audience before copying content into another system.
What does the skill cost?
The skill has no listed purchase price. Agent usage and any external publishing service are separate.
What are its limits and alternatives?
Generic example formats do not automatically match a company’s policy or incident process. The skill cannot verify that a project is on schedule or that an incident is resolved without supporting evidence.
Use a fixed template when the update is entirely mechanical. Choose doc-coauthoring for a long argument or decision memo rather than a routine team communication.
What could you ask in a small trial?
Try this with a small sample:
Draft a weekly update from these approved facts, using completed work, next actions and blockers. Keep dates and owners exactly as supplied and leave missing facts as questions. Do not send the message.
How would you verify the result?
- Check every completion claim and date against the supplied facts.
- Verify that action owners and blockers are explicit.
- Have the responsible person approve the audience and content before any message is sent.
Use a baseline and record acceptance evidence before treating a successful task as a reliable workflow.
Which source and license were checked?
Read the reviewed SKILL.md at its pinned commit · Complete reviewed folder
Repository and current publisher guidance
Checked:
Apache-2.0 — identified in skills/internal-comms/LICENSE.txt at the reviewed commit. Third-party assets and dependencies may have separate terms. License evidence
Version details and review scope
Source: anthropics/skills/skills/internal-comms
Reviewed commit: dbd4588f9e1033efb41dad4bef2f7947c8993d44
SKILL.md SHA-256: 067b7587a344a928fc6534ef66b1bcd591fc7c26d207ea7ca3334aeb678d6475
Source-document review. Source text and stated dependencies were inspected for this profile. Referenced code was not comprehensively audited, no runtime test was performed, and source files are not mirrored here.