Technical Article Writer
v1.1.2Write compelling technical articles and blog posts for developer audiences. Use this skill whenever the user asks to write a blog post, technical article, or...
⭐ 0· 130·0 current·0 all-time
bySamuel Berthe@samber
MIT-0
Download zip
LicenseMIT-0 · Free to use, modify, and redistribute. No attribution required.
Security Scan
OpenClaw
Benign
high confidencePurpose & Capability
The name and description (technical article writing) align with the skill's contents: a phase-gated writing workflow, title/hooks references, templates, and guidance. There are no unrelated required binaries, environment variables, or config paths.
Instruction Scope
The SKILL.md stays within the scope of drafting and editing technical articles (intake questions, outlines, title generation, examples, image prompt suggestions). It enforces a mandatory intake phase before drafting, reducing unwanted autonomous output. One caveat: the skill's allowed-tools list includes Read/Edit/Write/Grep/WebFetch/WebSearch/Agent which give an agent the ability to read or write workspace files and fetch web content; the instructions do not explicitly require reading arbitrary local files or secrets, but those tool permissions broaden what the agent could do at runtime if the agent is allowed to use them. This is a capability note rather than an explicit instruction to access unrelated data.
Install Mechanism
No install spec and no code files — instruction-only. Nothing is downloaded or written to disk by the skill itself, minimizing install-time risk.
Credentials
The skill requires no environment variables, secrets, or external credentials. References to generating Midjourney prompts or using web references do not request API keys in the skill metadata; any integration with external services would need explicit credentials provided separately by the user.
Persistence & Privilege
always is false and the skill does not request persistent system-wide changes. The instructions do not direct modifying other skills or global agent settings.
Scan Findings in Context
[no-code-files-to-scan] expected: The regex-based scanner had no code files to analyze because this is an instruction-only skill. That's expected for a documentation/writing skill; absence of findings is not an additional safety signal but is consistent with the package contents.
Assessment
This skill appears coherent and focused on writing technical articles. Before installing, consider: (1) The skill allows the agent to use file and web tools (Read/Edit/Write/Grep/WebFetch/WebSearch/Agent). If you permit the agent those capabilities, it may read or write workspace files or fetch web pages for research — ensure you trust the agent and scope those permissions appropriately. (2) The skill does not request credentials or install code, so there is no hidden network-install risk. (3) The SKILL.md enforces asking the user before drafting (good), but verify your agent's runtime policy: if you do not want the agent autonomously reading or writing local files or calling external services, restrict or review the allowed-tools/runtime permissions. (4) If you plan to use image-generation integrations (e.g., Midjourney), supply any required API keys separately and only if you trust that integration. Overall this is internally consistent for a writing assistant.Like a lobster shell, security has layers — review code before you run it.
latestvk977rbfb02ggcn4wxxkpj0thp583yspn
License
MIT-0
Free to use, modify, and redistribute. No attribution required.
Runtime requirements
📝 Clawdis