← Back to Skills Marketplace
Technical Blog Writing
by
Ömer Karışman
· GitHub ↗
· v0.1.5
912
Downloads
1
Stars
5
Active Installs
2
Versions
Install in OpenClaw
/install technical-blog-writing
Description
Technical blog post writing with structure, code examples, and developer audience conventions. Covers post types, code formatting, explanation depth, and dev...
Usage Guidance
This skill appears to be a legitimate guide for writing technical blog posts, but it tells you to install and use a third-party CLI (inference.sh) by piping a remote script to sh and to run commands that contact inference.sh services. Before running any installer: inspect the install script manually (do not pipe to sh blindly), verify checksums from the provided URL, prefer installing in an isolated environment (container or VM) if you want to test, and consider whether you are comfortable sending draft content or prompts to an external service. Also note the metadata doesn't declare the infsh binary as required — if you trust and need infsh, add it explicitly or avoid the install. If you want a purely offline skill, do not follow the installer steps.
Capability Analysis
Type: OpenClaw Skill
Name: technical-blog-writing
Version: 0.1.5
The skill is classified as suspicious due to the inclusion of `curl -fsSL https://cli.inference.sh | sh` for installation, which executes a remote script directly, and more critically, the instruction to use `infsh app run infsh/python-executor` in SKILL.md. This `python-executor` capability allows the AI agent to execute arbitrary Python code, creating a significant prompt injection vulnerability that could lead to remote code execution if the agent is manipulated. While the provided examples are benign and align with the stated purpose, the inherent risk of these capabilities warrants a 'suspicious' classification.
Capability Assessment
Purpose & Capability
The SKILL.md content is a coherent technical-blog-writing guide and aligns with the skill name/description. It does, however, rely on the external inference.sh CLI for research and image generation (infsh commands shown) even though the skill metadata lists no required binaries or environment variables — a minor mismatch between declared requirements and the documented runtime tools.
Instruction Scope
The instructions explicitly tell users/agents to run a remote install command (curl -fsSL https://cli.inference.sh | sh) and to invoke infsh app run commands that will contact inference.sh services. That means content may be transmitted to an external service and an installer script from the network will be executed if followed. The rest of the writing guidance stays on-topic and does not ask the agent to read unrelated files or secrets.
Install Mechanism
There is no registry install spec, but SKILL.md recommends a remote installation via curl | sh from cli.inference.sh and points to dist.inference.sh for checksums. This is a higher-risk install pattern (remote script execution); while checksums are referenced, the domain is not a well-known release host like GitHub in the doc and the skill does not enforce/declare the CLI as a required binary in metadata.
Credentials
The skill requests no environment variables, credentials, or config paths in metadata. The instructions likewise do not ask for unrelated secrets or to read system credentials. The only external dependency is the optional inference.sh service/CLI referenced in the doc.
Persistence & Privilege
The skill is instruction-only, has always:false, and does not request persistent system privileges in its metadata. That said, following the SKILL.md installer would add a third-party CLI to the system — the skill itself does not request or claim persistent privileges.
How to Use
- Make sure OpenClaw is installed (local or Docker)
- Run the install command in chat:
/install technical-blog-writing - After installation, invoke the skill by name or use
/technical-blog-writing - Provide required inputs per the skill's parameter spec and get structured output
Version History
v0.1.5
technical-blog-writing 0.1.5
- Added detailed SKILL.md describing technical blog writing structure, conventions, and best practices for developer-focused content.
- Included clear post type templates (tutorials, deep dives, benchmarks, postmortems, architecture).
- Outlined writing rules, code example guidelines, explanation depth, and developer audience engagement patterns.
- Provided sample CLI usage instructions and install notes for [inference.sh](https://inference.sh).
- Listed word count ranges, structural templates, and diagram usage recommendations for different post types.
v0.1.0
- Initial release of the technical-blog-writing skill.
- Provides structured templates for five common technical post types: tutorial, deep dive, postmortem, benchmark, and architecture.
- Includes writing conventions tailored to developers, such as code formatting, explanation depth, and engagement patterns.
- Offers rules and best practices for writing, code examples, diagram usage, and post structure.
- Details word count guidelines and when to use visuals or diagrams in technical blog posts.
Metadata
Frequently Asked Questions
What is Technical Blog Writing?
Technical blog post writing with structure, code examples, and developer audience conventions. Covers post types, code formatting, explanation depth, and dev... It is an AI Agent Skill for Claude Code / OpenClaw, with 912 downloads so far.
How do I install Technical Blog Writing?
Run "/install technical-blog-writing" in the OpenClaw or Claude Code chat to install it in one step — no extra setup required.
Is Technical Blog Writing free?
Yes, Technical Blog Writing is completely free (open-source). You can download, install and use it at no cost.
Which platforms does Technical Blog Writing support?
Technical Blog Writing is cross-platform and runs anywhere OpenClaw / Claude Code is available (cross-platform).
Who created Technical Blog Writing?
It is built and maintained by Ömer Karışman (@okaris); the current version is v0.1.5.
More Skills