CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

verify-service-connection

Check the local OpenMeld Service connection loop. The computer is shown as connected only while the session is online, stopping is idle, and quitting does not reconnect. Use when changing the service run loop, toHealthProjection, or classifyConnectionFailureReason.

Quality

95%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide
SecuritybySnyk

Critical

Do not install without reviewing

SKILL.md
Quality
Evals
Security

Quality

Content

100%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 exemplary skill body: lean and dense with non-obvious project knowledge, a single unambiguous executable check with explicit failure diagnostics and remediation, and clean sectioning that keeps everything the skill needs inline without bloat. Nothing trimmable and no gaps in executability.

DimensionReasoningScore

Conciseness

Every sentence carries project-specific, non-inferable information (the health-state mapping, the sha256-pinned TLC 1.7.4 jar, the "Confirmed against commit 965d9eb..." anchor with an explicit reconfirmation protocol) with zero padding or explanation of concepts Claude already knows. The version pins are functional (download verification, maintenance protocol) rather than stale-prone date conditionals, so the time-sensitivity penalty does not apply.

5 / 5

Actionability

The body gives a copy-paste command ("node .agents/skills/verify-service-connection/check.mjs"), exit-code semantics ("Exit 0 means... all hold"), prerequisites ("Java 11 or newer must be on PATH", "pnpm install is not required"), and per-failure diagnostics with concrete remediation ("Check markStopping and the while (!stopRequested) loop"), fully covering the common cases.

5 / 5

Workflow Clarity

This is a single-action skill whose one action is unambiguous (run the check from the repository root, interpret exit code), which qualifies for the simple-skill exception; additionally the "What a failure means" section supplies an explicit validate-to-diagnose feedback loop for each failure mode, and "After a change that skipped this skill" gives a recovery path.

5 / 5

Progressive Disclosure

No bundle files exist (references/, scripts/, assets/ are absent) and the body is under 50 lines, cleanly organized into When this applies / Run / What a failure means / Scope / After a change that skipped this skill. Per the under-50-line exception, well-organized sections alone merit the top score, and the referenced repo paths (check.mjs, view.mjs, ServiceConnection.tla) are one level deep and clearly signaled.

5 / 5

Total

20

/

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 strong description: it states a concrete verification target, the expected behaviors, and an explicit 'Use when' trigger clause naming the exact functions whose changes should invoke it. The only minor gap is that a few trigger terms enumerated in the body are absent from the description itself.

DimensionReasoningScore

Specificity

"Check the local OpenMeld Service connection loop" names a concrete action, and the description enumerates specific verified behaviors ("connected only while the session is online, stopping is idle, and quitting does not reconnect"). It stops short of anchor 5 because it describes one checking action with its targets rather than a comprehensive list of distinct actions.

4 / 5

Completeness

The description explicitly answers both 'what' ("Check the local OpenMeld Service connection loop" plus the expected health behaviors) and 'when' ("Use when changing the service run loop, toHealthProjection, or classifyConnectionFailureReason") with concrete trigger phrases, matching the anchor-5 example structure.

5 / 5

Trigger Term Quality

"Use when changing the service run loop, toHealthProjection, or classifyConnectionFailureReason" provides good natural trigger terms for a code-change-triggered skill. A few natural terms the body lists (markStopping, service-connection-state.ts, service-runner.ts) are missing, so it falls short of comprehensive synonym coverage.

4 / 5

Distinctiveness Conflict Risk

"OpenMeld Service connection loop" plus codebase-specific function names (toHealthProjection, classifyConnectionFailureReason) carves out a clear niche with distinct triggers and minimal risk of firing for an unrelated skill.

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

amplifthq/opentag

Path

.agents/skills/verify-service-connection/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.