LIVE
Yoshua Bengio examines why AI agents lie, cheat and coordinate13/09/26|Terence Tao warns of a 'severe misalignment' in OpenAI's mathematical claims11/09/26 · OpenAI|Terence Tao warns of a 'severe misalignment' of AI in mathematics11/09/26|OpenAI's Navier-Stokes release comes with a Lean 4 formal proof10/09/26 · OpenAI|OpenAI publishes documentation for its Agents API10/09/26 · OpenAI|OpenAI Launches the Agents API, a Managed Service for Cloud Agents10/09/26 · OpenAI|Anthropic Accused of Building a Predictive Surveillance System Targeting Activists09/09/26 · Anthropic|OpenAI Claims a Millennium Prize Problem Solved, Controversy Follows09/09/26 · OpenAI|Mistral AI Raises €3 Billion to Push Open-Weight Models to the Frontier08/09/26 · Mistral AI|OpenAI agents hijacked a German wiki before the Hugging Face breach07/09/26 · OpenAI|Perplexity entrusts operations to OpenAI's GPT-6 Astra14/09/26 · OpenAI|Garry Tan urges US labs to distill frontier models too13/09/26|Yoshua Bengio examines why AI agents lie, cheat and coordinate13/09/26|Terence Tao warns of a 'severe misalignment' in OpenAI's mathematical claims11/09/26 · OpenAI|Terence Tao warns of a 'severe misalignment' of AI in mathematics11/09/26|OpenAI's Navier-Stokes release comes with a Lean 4 formal proof10/09/26 · OpenAI|OpenAI publishes documentation for its Agents API10/09/26 · OpenAI|OpenAI Launches the Agents API, a Managed Service for Cloud Agents10/09/26 · OpenAI|Anthropic Accused of Building a Predictive Surveillance System Targeting Activists09/09/26 · Anthropic|OpenAI Claims a Millennium Prize Problem Solved, Controversy Follows09/09/26 · OpenAI|Mistral AI Raises €3 Billion to Push Open-Weight Models to the Frontier08/09/26 · Mistral AI|OpenAI agents hijacked a German wiki before the Hugging Face breach07/09/26 · OpenAI|Perplexity entrusts operations to OpenAI's GPT-6 Astra14/09/26 · OpenAI|Garry Tan urges US labs to distill frontier models too13/09/26|
SkillRisingofficial publisher

brand-guidelines (Anthropic)

Skill : A reusable method: instructions, procedures, sometimes scripts or templates · requires claude-code

Example skill that applies a brand charter (colors, typography, tone) to what Claude produces.

The template to copy for your own brand charter.

Overall score
8.4 /10
Security: nothing to flag
Utility
6.0
Reliability
10.0
Security
10.0
Ease
1 click · Beginner

What it does, concretely

When a team produces documents, presentations or code, maintaining visual and editorial consistency requires constant effort. Without a centralized reference, Claude adapts its style to each conversation, which can produce inconsistent results from one session to the next.

The brand-guidelines skill works as a SKILL.md file that Claude loads dynamically before producing content. This file describes your brand's colors, typography and tone. Claude then refers to it to align each output with your guidelines, without you having to repeat these instructions each time.

This skill is aimed at teams who want to standardize the consistency of their deliverables in Claude Code, or at developers who want to understand how to structure a custom skill. It also serves as a concrete starting point for creating your own brand guidelines skill.

It is not suitable for those looking for a ready-to-use tool with no configuration: you need to adapt the SKILL.md file to your own brand to get value from it. Users without access to Claude Code or a paid Claude.ai plan will not be able to use it directly.

What it offers

  • ·Dynamic loading of a brand charter (colors, typography, tone) before each content generation.
  • ·SKILL.md structure with minimal YAML frontmatter (two required fields: name and description) that is easy to duplicate.
  • ·Available as an open source template under the Apache 2.0 license, freely modifiable and redistributable.
  • ·Installation via the Claude Code plugin marketplace with a single command or through manual selection in the interface.
  • ·Also usable on Claude.ai for paid plans, with no additional installation required. (paid)
  • ·Accessible via the Claude API for integration into custom workflows.

In practice

Price
Free
Commercial use
Commercial use: yes
Available on
claude-code
Host
claude-code
Licence
Apache-2.0
FR interface
No

Security and data

Rating
Security: nothing to flag
Your data
Data stays local
Maintenance
Active

Card verified on 14 September 2026 · added on 1 October 2025

How to install brand-guidelines (Anthropic)

1. Open Claude Code in your development environment. 2. Register the official repository as a marketplace by running: /plugin marketplace add anthropics/skills 3. Install all example skills via: /plugin install example-skills@anthropic-agent-skills 4. Verify the installation by asking Claude Code to use the brand-guidelines skill on a test piece of content. 5. To customize: copy the brand-guidelines folder, edit the SKILL.md file with your own colors, typography and tone, then reload the skill. 6. Do not deploy the skill on critical tasks without first testing it in an isolated environment.
/plugin install example-skills@anthropic-agent-skills

In the same category

Whole category Frame (methods, guardrails)