Concrete Language Rewriter
v1.0.0Rewrite abstract, theoretical, or jargon-heavy passages into sensory, schema-based language the audience can already picture — using three named techniques (...
⭐ 0· 36·0 current·0 all-time
byHung Quoc To@quochungto
MIT-0
Download zip
LicenseMIT-0 · Free to use, modify, and redistribute. No attribution required.
Security Scan
Capability signals
These labels describe what authority the skill may exercise. They are separate from suspicious or malicious moderation verdicts.
OpenClaw
Benign
high confidencePurpose & Capability
Name, description, and provided reference materials align: the skill rewrites abstract prose into concrete language and requires no external services, binaries, or credentials to do that.
Instruction Scope
SKILL.md confines runtime actions to asking for the draft and audience context, optionally checking common local files (audience-profile.md, brief.md, persona.md), and producing side-by-side rewrites; it explicitly forbids inventing unsupported sensory details and asks the agent to surface assumption flags.
Install Mechanism
No install spec and no code files—this is instruction-only so nothing is downloaded or written to disk beyond normal output files the agent creates.
Credentials
The skill requires no environment variables, credentials, or config paths; its occasional checks for locally named audience files are proportional to its purpose (anchoring rewrites to audience reference material).
Persistence & Privilege
always:false and no requests to modify agent/system configuration or to persist credentials; autonomous invocation is allowed by platform default but the skill itself does not request elevated persistence.
Assessment
This is a low-risk, instruction-only writing skill. Before installing, note that the agent may read local document files (e.g., audience-profile.md, brief.md, persona.md) if present to build audience anchors — remove or redact sensitive content from those files if you don't want them used. The skill promises not to invent unsupported sensory details, but always review rewrites for any factual assumptions (the output template includes explicit '[assumption — verify]' caveats). Because it is instruction-only, there is no external code being pulled in, and no credentials are requested. If you expect the agent to run unattended with access to a workspace that contains sensitive documents, consider restricting that workspace or providing only the specific passages and audience notes needed.Like a lobster shell, security has layers — review code before you run it.
analogyvk973pwpzhyemh8avvh0chc5bk584wpqbbookforgevk973pwpzhyemh8avvh0chc5bk584wpqbclarityvk973pwpzhyemh8avvh0chc5bk584wpqbcommunicationvk973pwpzhyemh8avvh0chc5bk584wpqbconcrete-languagevk973pwpzhyemh8avvh0chc5bk584wpqbcopywritingvk973pwpzhyemh8avvh0chc5bk584wpqblatestvk973pwpzhyemh8avvh0chc5bk584wpqbmessagingvk973pwpzhyemh8avvh0chc5bk584wpqbmetaphorvk973pwpzhyemh8avvh0chc5bk584wpqbpitchvk973pwpzhyemh8avvh0chc5bk584wpqbplain-languagevk973pwpzhyemh8avvh0chc5bk584wpqbrewritingvk973pwpzhyemh8avvh0chc5bk584wpqb
License
MIT-0
Free to use, modify, and redistribute. No attribution required.
Runtime requirements
📚 Clawdis