Cross Team Plain Language
v1.0.0Rewrite messy, internal, emotional, or jargon-heavy thoughts into clear language that other teams can immediately understand and respond to. Use when the use...
⭐ 0· 99·1 current·1 all-time
bynick@nickzhangai
MIT-0
Download zip
LicenseMIT-0 · Free to use, modify, and redistribute. No attribution required.
Security Scan
OpenClaw
Benign
high confidencePurpose & Capability
Name/description claim to rewrite internal/jargon-heavy text into plain language. The skill is instruction-only, requests no binaries, env vars, or installs, and the SKILL.md contains only rewrite guidelines and templates — everything requested is proportional to the stated purpose.
Instruction Scope
Runtime instructions are limited to extracting audience/intent, cleaning jargon and emotion, and producing multiple rewrite variants. The SKILL.md does not instruct the agent to read unrelated files, environment variables, or transmit data to external endpoints. It asks for minimal clarifying info (audience, tone) when necessary.
Install Mechanism
No install spec and no code files are provided (instruction-only), so nothing is written to disk or fetched at install time — lowest-risk model for this type of skill.
Credentials
The skill declares no required environment variables, credentials, or config paths. There are no instructions that access secrets or unrelated credentials. Note: users may paste sensitive internal content into the skill — this is a privacy concern but not a misalignment of requested permissions.
Persistence & Privilege
always is false and user-invocable is true. disable-model-invocation is false (normal default). The skill does not request persistent system privileges or modify other skills' configs.
Assessment
This skill appears coherent and low-risk: it only describes how to rewrite text and asks for no credentials or installs. The main practical risk is privacy — users often paste internal or sensitive text into rewriting tools. Before using, avoid pasting secrets (passwords, tokens, PII, proprietary data) or check your org policy for sharing internal content with external models. If you need guaranteed data confinement, prefer an on-premise or enterprise model or restrict the skill to manual, user-invoked use rather than automated agent runs.Like a lobster shell, security has layers — review code before you run it.
latestvk97cgnxbgz4pe865mj02nh7yx1835j68
License
MIT-0
Free to use, modify, and redistribute. No attribution required.