Ready to supercharge your AI agents?

Install any skill in seconds. Free to start, no credit card required.

EVE Lab Topology Discovery — measured AI agent skill | DecimalAI

automateyournetwork/eve-lab-topology-discovery

NewSkillScoreMaintained

Gather missing requirements for EVE-NG topology design. Use when the request is vague or incomplete, when you need discovery questions, defaults, trade-off framing, image recommendations, or domain guidance before proposing a topology.

DevOpsby automateyournetwork

Links this skill to your agents and keeps it current with the author’s updates.

Automatic

DevOps & SRE pack

1 · One-time — install the CLI (docs ↗)

pip install decimalai

2 · Get the skill — writes .claude/skills/automateyournetwork-eve-lab-topology-discovery/SKILL.md

decimalai skills pull automateyournetwork-eve-lab-topology-discovery --out .claude/skills/

No CLI? Get the same file — curl · raw file

curl -fsSL --create-dirs -o .claude/skills/automateyournetwork-eve-lab-topology-discovery/SKILL.md https://app.decimal.ai/s/automateyournetwork-eve-lab-topology-discovery/SKILL.md

Raw file: /s/automateyournetwork-eve-lab-topology-discovery/SKILL.md ↗ · machine-readable summary at /s/automateyournetwork-eve-lab-topology-discovery.json ↗

In productionGlobal

how this skill behaves on real traffic · last 30 days

No production data for this skill yet — usage numbers appear here once agents start running it.

Anonymized aggregate across every org using this skill — proof from real production use, not a demo.

Does this skill help? · Benchmark: with vs. withoutsign in to run this on your agents

22 test cases from the publisher’s eval.yaml · each run twice on gemini-3.6-flash — with the skill injected, then without · last run 2h ago

Yes — +41% lift-23% tokens0% turns82% of whole cases pass with skill (18/22)

Test case	Without → With	Effect	Δ tokens	Δ turns
case-14	✗→✓	▲ Improved	-35%	0%
case-12	✗→✓	▲ Improved	-21%	0%
case-01	✗→✓	▲ Improved	-10%	0%
case-02	✗→✓	▲ Improved	-59%	0%
case-07	✗→✓	▲ Improved	12%	0%

Showing 5 of 22 cases

SkillSafety

✓ 3 of 3 passed

Code scan15 of 15 checks clean

0 critical · 0 warning · 0 info — scanner v4 — 8/3/2026

live_secretremote_code_executionreverse_shelldata_exfiltrationssrf_metadataagent_snoopinganti_refusaldestructive_commandsobfuscated_unicodeunicode_homoglyphopaque_blobsuspicious_urltool_overreachtrigger_abuseprompt_injection_phrasing

IntentSafe

LLM judge · does the skill do what it claims

ContentClean

LLM judge · policy & harmful-content review

Source

Imported

automateyournetwork / netclaw

workspace/skills/eve-lab-topology-discovery/SKILL.md

View on GitHub ↗

License Apache-2.0Imported 8/3/2026Version v1Bundled 3 files

Skill contents

references/

SKILL.md

EVE Lab Topology Discovery

Use this skill only for the requirements and options phase of topology work.

Workflow

Decide whether the request is vague or already specific.
If vague, ask only the missing questions from {baseDir}/references/question-bank.md.
Offer labeled defaults from {baseDir}/references/defaults-and-options.md when the user skips details.
Summarize the requirements into a connectivity matrix, required links list, and resilience declaration.
If platform/image selection matters, read {baseDir}/references/domain-and-image-guidance.md.

Guardrails

Never ask more than 5 questions in one turn.
Group related questions.
Do not generate a generic topology before topology type and scale are known.
Label all assumptions explicitly.

Want to see if automateyournetwork/eve-lab-topology-discovery would activate on your phrasing? Try it before you install — no LLM call, no signup.

Other measured skills in the registry, with their headline benchmark lift.