CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

connectivity-triage

Use this skill when debugging active macOS connectivity failures, when an API or MCP service times out or disconnects, when DNS resolution is failing or inconsistent, or when video calls or other interactive traffic show packet loss or latency. Isolate local-LAN, DNS, upstream-path, and remote-service/application fault domains with built-in, non-destructive tools.

73

Quality

92%

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

SKILL.md
Quality
Evals
Security

Quality

Content

92%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.

An excellent instruction-only skill body: fully executable bounded commands at every step, an explicitly sequenced workflow with real validation checkpoints, and a clean one-level-deep split into a single well-signaled reference file. The only trimmable content is mild repetition of the no-remediation constraint across three sections.

DimensionReasoningScore

Conciseness

The body is dense and assumes competence — no concept explanations, every section carries non-obvious interpretive judgment (e.g., "A silent or changing hop is an observation, not proof that the hop is broken"). It falls just short of anchor 5 because the non-mutation constraint is stated three times (intro, "When to Use", "Safety and Boundaries") and a few sentences restate the flow diagram, i.e., minor instances that could be trimmed — anchor 4.

4 / 5

Actionability

Every step ships a complete, executable, bounded command: `ping -c 5`, `scutil --dns`, `dig +time=2 +tries=1`, `traceroute -n -q 1 -m 20`, `nettop -n -L 3 -p`, and a full copy-paste-ready `curl -sS -w '...' --connect-timeout 5 --max-time 15 '<url>'` invocation, with placeholders clearly marked. This matches anchor 5.

5 / 5

Workflow Clarity

The sequence is explicit (symptom → LAN → DNS → reachability → app activity → timing → assessment, mirrored by numbered steps 1-6) with real validation checkpoints: stop-early guidance, Observed/Inferred/Unknown evidence labeling, "Return exactly one primary category", conflict handling ("prefer inconclusive"), and a structured incident result format. This is a read-only diagnostic workflow, so the destructive-operation validation cap does not apply. Anchor 5 fits.

5 / 5

Progressive Disclosure

The body is a genuine overview (workflow, evidence rules, output format, safety) while per-command interpretation, ambiguity cases, and worked examples are split into `references/details.md`, which exists, is referenced exactly once, clearly signaled ("Read `references/details.md` for command-by-command interpretation, ambiguity handling, intermittent-failure guidance, and worked examples"), and is one level deep — `details.md` contains no nested references. Anchor 5 fits the actual bundle structure.

5 / 5

Total

19

/

20

Passed

Description

87%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.

A well-crafted description with explicit and multi-scenario trigger guidance, a clear capability statement, and a distinctive diagnostic (non-remediation) niche. The only gap is that capabilities are stated at the fault-domain level rather than naming the concrete diagnostic probes used.

Suggestions

Name one or two concrete diagnostic actions (e.g., bounded ping/dig/curl timing probes) in the what-clause so capabilities are described at the same specificity as the triggers.

Add one or two common colloquial trigger phrasings (e.g., "no internet", "network seems slow or dropping") to broaden natural keyword coverage.

DimensionReasoningScore

Specificity

The description names the domain and several concrete capability areas — "Isolate local-LAN, DNS, upstream-path, and remote-service/application fault domains with built-in, non-destructive tools" — but stops at the fault-domain level without naming the actual diagnostic actions or tools (e.g., ping, DNS queries, path tracing, HTTP timing). It fits anchor 4 (several specific actions, minor gaps) rather than 5, which expects a comprehensive enumeration of concrete actions, and is clearly above anchor 3 (only 1-2 concrete actions).

4 / 5

Completeness

Both halves are explicit: an explicit "Use this skill when..." clause enumerating four concrete trigger scenarios, followed by a clear what-it-does statement ("Isolate local-LAN, DNS, upstream-path, and remote-service/application fault domains with built-in, non-destructive tools"). This matches anchor 5 exactly; nothing is merely implied.

5 / 5

Trigger Term Quality

Strong natural trigger phrasing with variations — "an API or MCP service times out or disconnects", "DNS resolution is failing or inconsistent", "video calls or other interactive traffic show packet loss or latency" — which are phrases users would genuinely say. It falls short of anchor 5's comprehensiveness because common user phrasings like "no internet", "network is slow", "Wi-Fi keeps dropping", or "site is down" are absent, but it is well above anchor 3's partial keyword coverage.

4 / 5

Distinctiveness Conflict Risk

A clear, narrow niche — active macOS connectivity failure triage that isolates fault domains diagnostically without remediation — with trigger terms (timeouts, disconnects, DNS, packet loss) that are unlikely to fire for unrelated skills. Anchor 5 fits: distinct triggers, minimal conflict risk.

5 / 5

Total

18

/

20

Passed

Validation

100%

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

Validation — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository

wshobson/agents

Path

plugins/incident-response/skills/connectivity-triage/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.