CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

network-engineer

Expert network engineer specializing in modern cloud networking, security architectures, and performance optimization.

Quality

45%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide
SecuritybySnyk

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./plugins/AI-Agents-Safe-Coding-Skills-claude/skills/network-engineer/SKILL.md

The canonical home for this skill is network-engineer in administrakt0r/AI-Agents-Safe-Coding-Skills

SKILL.md
Quality
Evals
Security

Quality

Content

28%Weight 40%Scale 1-5

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

The body is a persona/knowledge resume rather than a working skill: it enumerates technologies Claude already knows in ~140 lines while providing no concrete commands, procedures, or validation steps. Its only external reference is a dangling path to a nonexistent file, leaving a monolithic catalog that adds little actionable value.

Suggestions

Replace the capability catalog with executable procedures, e.g. a layered troubleshooting runbook with actual commands (`ping`, `dig +trace`, `openssl s_client -connect`, `traceroute/mtr`, `ss -tulpn`) and a concrete design checklist.

Move the technology lists into a references/ file (e.g. references/capabilities.md) and fix the broken `resources/implementation-playbook.md` path — no such file or directory exists in the bundle.

Add explicit validation checkpoints to the workflow (e.g. 'verify connectivity after each change with X, roll back if Y') instead of the generic 'Test thoroughly' step.

DimensionReasoningScore

Conciseness

Roughly 90% of the body is a catalog of technologies Claude already knows — 13 capability sections enumerating 'AWS networking: VPC, subnets, route tables, NAT gateways...', 'Diagnostic tools: tcpdump, Wireshark, ss, netstat...' plus a 'Knowledge Base' restating 'Cloud networking services across AWS, Azure, and GCP'. This is noticeably-to-severely padded with zero new information. Not a 1 because it does not prose-explain concepts the way the anchor example does; not a 3 because there is no meaningful content that could not be trimmed or that Claude does not already know.

2 / 5

Actionability

The instructions are abstract ('Clarify goals, constraints, and required inputs', 'Apply relevant best practices and validate outcomes') with no commands, code, or procedures anywhere; the 'Response Approach' steps are generic ('Design network architecture with appropriate redundancy and security'). There are a few high-level hints like 'Tests connectivity systematically at each network layer (physical, data link, network, transport, application)', which is why this lands at 'Minimal concrete guidance; high-level hints but missing the specific steps to execute' rather than the 'entirely vague' anchor 1.

2 / 5

Workflow Clarity

A rough sequence exists ('Response Approach' lists 9 numbered steps: analyze, design, implement, configure, monitor, optimize, document, plan DR, test), but the steps are poorly defined and validation is essentially absent — 'Test thoroughly from multiple vantage points' is the only, purely implicit, checkpoint. This matches 'Rough sequence present but many gaps; steps poorly defined; validation absent'. Not a 3 because even the sequence itself is generic and no explicit checkpoints exist.

2 / 5

Progressive Disclosure

The body has clear section headers (## Capabilities, ## Behavioral Traits, etc.) and one reference pointer, but the 100+ lines of capability catalog are exactly the content that belongs in separate reference files, and the sole reference — 'open `resources/implementation-playbook.md`' — points to a file that does not exist in the bundle (no references/, scripts/, or assets/ directories are present). This matches 'Some structure but could be better organized; references present but not clearly signaled; content that should be separate is inline'. Not a 2 because headers do provide navigable structure; not a 4 because the single reference is broken and the bulk of the content is inlined.

3 / 5

Total

9

/

20

Passed

Description

36%Weight 40%Scale 1-5

Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.

The description uses correct third-person voice and names a clear domain, but it is a persona tagline rather than a capability statement: no concrete actions, no 'Use when...' trigger clause, and no natural variations of the terms users would actually say. Completeness is the biggest weakness since both 'what it does' and 'when to use it' are underspecified.

Suggestions

Replace the persona tagline with concrete actions, e.g. 'Designs cloud network architectures (VPCs, subnets, routing), troubleshoots connectivity issues layer-by-layer, configures load balancers, DNS, and VPNs'.

Append an explicit trigger clause: 'Use when the user mentions networking, VPCs, subnets, DNS, load balancers, VPNs, TLS certificates, packet loss, latency, or network troubleshooting'.

Narrow the scope claim or add distinct triggers so it does not compete with generic cloud/security/DevOps skills for the same prompts.

DimensionReasoningScore

Specificity

The description only says 'Expert network engineer specializing in modern cloud networking, security architectures, and performance optimization' — it names the domain but lists zero concrete actions (no 'designs', 'troubleshoots', 'configures'). This matches the anchor 'Names the domain but actions are minimal or generic'. It is not a 3 because that anchor requires 1-2 concrete actions, and not a 1 because the domain and focus areas are named specifically rather than in purely abstract language.

2 / 5

Completeness

There is a role-based 'what' ('Expert network engineer specializing in...') but no explicit 'when to use' clause at all, which caps completeness at 3 per the judging guidelines. The 'what' is itself vague — it describes a persona, not actions — matching the anchor 'Has a vague what and no when'. Not a 3 because even the 'what' lacks concrete actions; not a 1 because the domain is clearly stated rather than 'both extremely vague'.

2 / 5

Trigger Term Quality

Relevant keywords users might say are present ('network engineer', 'cloud networking', 'security architectures', 'performance optimization'), but common variations and synonyms are missing (VPC, DNS, VPN, load balancing, service mesh, packet loss, connectivity troubleshooting). This matches 'Some relevant keywords but missing common variations or synonyms'. Not a 4 because users troubleshooting a specific network issue would not naturally phrase it in these terms; not a 2 because the keywords are domain-appropriate, not generic filler like 'Works with files'.

3 / 5

Distinctiveness Conflict Risk

The networking niche is somewhat distinct, but the claimed scope spans three broad areas (cloud networking, security, performance optimization) that overlap heavily with generic cloud-engineer, security-engineer, and DevOps skills, and with no distinct trigger phrases to disambiguate. This matches 'Somewhat specific but could still overlap with similar skills'. Not a 4 because there is no 'Use when' guidance to keep it from firing for adjacent cloud/infra tasks; not a 2 because 'network' is a concrete anchor domain, not near-universal overlap.

3 / 5

Total

10

/

20

Passed

Validation

93%

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation — 15 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

frontmatter_unknown_keys

Unknown frontmatter key(s) found; consider removing or moving to metadata

Warning

Total

15

/

16

Passed

Repository

administrakt0r/AI-Agents-Safe-Coding-Skills

Path

plugins/AI-Agents-Safe-Coding-Skills-claude/skills/network-engineer/SKILL.md

Reviewed

Table of Contents

Is this your skill?

If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.