ClawHub

ML Engineering

v1.0.0

Provides end-to-end methodology for defining, engineering, experimenting, deploying, and operating production ML/AI systems at scale.

⭐ 0· 514·0 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
Benign
high confidence
✓
Purpose & Capability
Name/description (end-to-end ML engineering) lines up with the provided SKILL.md and README: both are extensive methodology and templates for problem framing, data engineering, experiments, deployment, monitoring, and MLOps. No unrelated capabilities, binaries, or credentials are requested.
ℹ
Instruction Scope
The SKILL.md contains broad, actionable guidance (templates, checklists, deployment patterns). That breadth is appropriate for an ML engineering playbook, but many suggested operational tasks (deploying models, configuring monitoring, CI/CD, cloud infra) will in practice require external credentials and tooling. The skill itself does not instruct the agent to read secrets or local system files, but following its recommendations will typically lead a human/operator to use credentials or make infrastructure changes.
✓
Install Mechanism
No install spec and no code files — instruction-only. This is the lowest-risk install profile because nothing is written to disk or fetched at install time by the skill itself.
✓
Credentials
The skill declares no required environment variables, no primary credential, and no config paths. That is proportionate to an instruction-only playbook. Note: real deployments described by the playbook will require credentials, but the skill does not request them.
✓
Persistence & Privilege
always is false and the skill is user-invocable. It does not request permanent presence or modify other skills or system-wide settings. Autonomous invocation is permitted by default but is not combined with other red flags here.
Assessment
This skill is an offline playbook (no code installed, no secrets requested) and appears coherent for ML engineering guidance. Before using: (1) do not paste production credentials or secrets into the agent when following deployment steps unless you trust the destination tooling; (2) verify any external commands or links (the README points to AfrexAI pages and a 'clawhub install' command) before running them; (3) when you follow instructions that interact with cloud providers or CI/CD, use least-privilege credentials and test in a safe environment; (4) treat the playbook as guidance — validate recommendations against your org's security, compliance, and cost requirements.

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

aivk97fgyvs3mdyh79pcnxbz9fmzx81es67data-sciencevk97fgyvs3mdyh79pcnxbz9fmzx81es67latestvk97fgyvs3mdyh79pcnxbz9fmzx81es67machine-learningvk97fgyvs3mdyh79pcnxbz9fmzx81es67mlvk97fgyvs3mdyh79pcnxbz9fmzx81es67

License

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

Comments