blog-polish-eng-single-image
v1.0.5Polish a technical blog draft into a 1000–1200 word, 4–5 section en-US article, preserve technical terms/code, and generate one consistent hero image prompt.
⭐ 0· 46·0 current·0 all-time
byJeff Yang@j3ffyang
MIT-0
Download zip
LicenseMIT-0 · Free to use, modify, and redistribute. No attribution required.
Security Scan
OpenClaw
Benign
high confidencePurpose & Capability
The skill's name and description match the inputs and outputs declared in SKILL.md: it reads a draft markdown (defaulting to a workspace path), rewrites into a polished markdown, and produces one hero-image prompt/PNG path. It requests no binaries, env vars, or credentials unrelated to this task.
Instruction Scope
The runtime instructions stay within the expected scope (editing the draft, preserving code blocks, producing one image prompt and a PNG filename). They rely on default workspace paths (~/.openclaw/workspace/...) which is consistent with content editing. The SKILL.md leaves the actual image-generation mechanism unspecified (it requires a PNG file/path and a single-line prompt but does not name an API or tool), which grants the agent discretion about how the image is produced — this is a functional ambiguity rather than an outright risk, but worth noting.
Install Mechanism
No install spec or code files are present; this is an instruction-only skill so nothing will be written to disk by an installer. Low installation risk.
Credentials
The skill declares no required environment variables, secrets, or config paths. There is no disproportionate credential request.
Persistence & Privilege
Skill flags use defaults (always: false, model invocation allowed). It does not request permanent presence or elevated system-wide privileges.
Assessment
This skill appears internally consistent and low-risk: it only needs access to your draft and an output directory in the workspace. Before installing, confirm how your agent will produce the PNG (does the agent have an image-generation connector or will it just write a prompt/placeholder?), and test the skill on non-sensitive drafts first. Also verify default paths (~/.openclaw/workspace/...) point to the intended files to avoid accidental exposure of unrelated content. If you rely on an external image API, review that connector's permissions and logs so image data/metadata isn't sent where you don't expect.Like a lobster shell, security has layers — review code before you run it.
latestvk976dh9e1r9f3epats7hjez1sh84b48v
License
MIT-0
Free to use, modify, and redistribute. No attribution required.