ClawHub

AI Coding Toolkit

v1.0.0

Provides a comprehensive methodology to optimize productivity and tool use across multiple AI coding assistants through assessment, selection, context engine...

⭐ 0· 398·0 current·0 all-time
by@1kalin
MIT-0
Download zip
LicenseMIT-0 · Free to use, modify, and redistribute. No attribution required.
Security Scan
VirusTotalVirusTotal
Benign
View report →
OpenClawOpenClaw
Suspicious
medium confidence
✓
Purpose & Capability
Name/description claim a methodology for using AI coding assistants; the skill is instruction-only and requests no binaries, env vars, or config paths—this is consistent with a purely procedural guide and expected capabilities.
ℹ
Instruction Scope
SKILL.md focuses on context engineering, creating rules files (.cursorrules, AGENTS.md, CLAUDE.md), running helpful local commands (e.g., 'tree -I node_modules -L 3'), and telling the agent to 'Set up AI coding for my project.' These actions legitimately require reading/writing project files and running local commands, but the instructions are somewhat open-ended and could lead an agent to access broad filesystem context or execute arbitrary local commands if invoked autonomously—so review generated actions before allowing them.
✓
Install Mechanism
No install spec, no downloads, and no code files—low installation risk. README references 'clawhub install afrexai-ai-coding-toolkit' (a marketplace command), but there is no hidden installer or external archive in the skill bundle.
✓
Credentials
The skill declares no required environment variables, credentials, or config paths. For a methodology/guide skill, requesting no secrets is proportionate and appropriate.
✓
Persistence & Privilege
Flags show always:false and normal autonomous invocation allowed. The skill does not request persistent system-level presence or modify other skills' configs according to the provided metadata.
What to consider before installing
This skill appears to be a methodological guide (no code or credentials requested) but exercise caution before enabling it for an agent that can act autonomously. Specifically: - The publisher/source is unknown and there is no official homepage in the registry—try to verify the author (AfrexAI) and the URLs referenced in README before trusting it. - The instructions ask the agent to read project files and create policy/rules files in your repo; review any generated .cursorrules / AGENTS.md / CLAUDE.md before committing them. - Don't grant the agent broad filesystem or network access or automatic commit rights without manual review—the guidance is intentionally open-ended and could cause broad context collection. - Be wary of the paid 'context packs' links in the README; they point to an external site (inspect that site independently before entering payment details). - If you try it, run it in a sandbox or a small test repository first and monitor what files/commands the agent actually uses. If you want higher assurance, ask the publisher for a verifiable source (GitHub repo or homepage) and a short changelog/maintainer contact before installing.

Like a lobster shell, security has layers — review code before you run it.

aivk9717k8f9wem61axb2yew9rw8x821s7yclaudevk9717k8f9wem61axb2yew9rw8x821s7ycodingvk9717k8f9wem61axb2yew9rw8x821s7ycopilotvk9717k8f9wem61axb2yew9rw8x821s7ycursorvk9717k8f9wem61axb2yew9rw8x821s7ylatestvk9717k8f9wem61axb2yew9rw8x821s7yvibe-codingvk9717k8f9wem61axb2yew9rw8x821s7ywindsurfvk9717k8f9wem61axb2yew9rw8x821s7y

License

MIT-0
Free to use, modify, and redistribute. No attribution required.
Termshttps://spdx.org/licenses/MIT-0.html

Comments