ClawHub

Agentic Engineering

v1.0.0

Workflow pattern for AI-assisted engineering using eval-first execution, task decomposition, and cost-aware model routing. Trigger phrases: agentic engineeri...

⭐ 0· 75·0 current·0 all-time
byDeonte Cooper@djc00p
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 (agentic engineering, eval-first, decomposition, model routing) matches the content of SKILL.md and reference files; nothing in the package asks for unrelated capabilities (no cloud creds, no unusual binaries).
✓
Instruction Scope
SKILL.md and references limit themselves to process guidance (write evals, decompose tasks, route by model tier, review checklist). They do not instruct the agent to read arbitrary files, export secrets, or call external endpoints.
✓
Install Mechanism
No install spec and no code files—this is instruction-only, so nothing is downloaded or written to disk during installation.
✓
Credentials
The skill declares no environment variables, credentials, or config paths; the guidance about model tiers is conceptual and does not require additional secrets from the user.
✓
Persistence & Privilege
always:false (default) and no install actions that modify agent state are present. The skill is user-invocable and can be invoked autonomously by the agent (platform default), which is expected for skills of this type.
Assessment
This skill is a set of best-practice instructions (eval-first, 15-minute units, model-tier routing) and contains no code, installs, or credential requests—so it is internally coherent. Before enabling: confirm you understand the platform's model access and billing (the skill recommends routing to model tiers named Haiku/Sonnet/Opus but does not provision them), avoid feeding sensitive secrets into prompts when testing, and consider whether you want the agent to invoke skills autonomously (the platform default) in your environment. If you need higher assurance, ask the author for provenance or run the guidance in a sandbox before applying it to real projects.

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

latestvk97613qb7zbn736589k5c9w8y984bbz7

License

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

Runtime requirements

🤖 Clawdis
OSLinux · macOS · Windows

Comments