Social Brand Voice

Brand voice guide creator for social media. Define your brand's tone, vocabulary, writing rules, and examples across platforms — so every post sounds consist...

Security Scan

The skill is internally coherent for generating brand-voice guides, but the included shell script expects local tooling (openclaw CLI, python3) that the skill metadata doesn't declare and it will send any user input to the configured OpenClaw agent process — review that before use.

Purpose & Capability

Name/description (brand voice guide) matches the behavior: the script builds a prompt and asks an agent to generate a multi-part brand voice guide. Nothing in the code suggests functionality beyond content generation.

Instruction Scope

analyze.sh constructs a full prompt from the user's input and runs 'openclaw agent --local ...' to produce the guide, then formats output with python3. The script does not read arbitrary files, environment variables, or external hard-coded endpoints. Note: all user-provided input is forwarded to the agent invocation — avoid sending secrets.

Install Mechanism

No install spec (instruction-only plus a helper script). No downloads or archive extraction. Nothing writes to system paths or attempts to install third-party code.

Credentials

The skill declares no required binaries or env vars, but analyze.sh invokes the 'openclaw' CLI and 'python3' at runtime. The missing declared requirements is an inconsistency. Also, while no credentials are requested by the skill, the openclaw agent will run using whatever agent configuration/credentials exist on the host — that could cause user input to be sent to a remote model provider depending on the user's OpenClaw configuration.

Persistence & Privilege

always:false and the skill does not modify system or other-skill configs. It does not request persistent presence or elevated privileges.

Assessment

This skill appears to do what it says (generate a brand voice guide) and contains a small helper script that invokes your OpenClaw agent. Before installing or running it: 1) Confirm you have the openclaw CLI and python3 available (the metadata doesn't list them but analyze.sh requires them). 2) Review and avoid passing any sensitive secrets or private customer data to the script — the input is forwarded to your agent and may be sent to whatever model endpoint your OpenClaw configuration uses. 3) If you want clearer safety, ask the publisher to add required-binaries (openclaw, python3) to the metadata and to document whether the agent runs completely locally or contacts a hosted API. 4) If you are uncertain about where your data will go, run the script in an isolated environment or with dummy inputs first.

Build a complete brand voice guide so your content always sounds like YOU.

Usage

brand voice: DTC skincare brand targeting millennial women
tone of voice: B2B fintech startup professional but approachable
brand guide: personal brand for senior software engineer
voice guide: outdoor adventure e-commerce brand fun and bold

What You Get

1. 4 Voice Dimensions — personality traits with do/don't examples
2. Tone Spectrum — where you sit on 5 key tone axes
3. Vocabulary Guide — words to use and words to ban
4. Platform Voice Variants — how the voice adapts per platform
5. Before/After Examples — rewrites showing voice in action
6. Quick Reference Card — one-page cheat sheet for your team