CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

ov-server-operate

Operate and maintain OpenViking server - configure, install, start, stop, and cleanup the server. Use when need to setup or manage OpenViking service deployment.

67

Quality

84%

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

77%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.

A highly actionable, well-sequenced operations runbook whose destructive-cleanup workflow is a model of validation and safety. Its weaknesses are verbosity in the inline cleanup script and duplicated verification content, plus a monolithic single-file layout that makes no use of progressive disclosure.

Suggestions

Move the full cleanup workflow into scripts/cleanup.sh and reference it from SKILL.md, keeping only the when-to-use guidance and safety summary inline — this trims ~100 lines of tokens and directly improves both conciseness and progressive_disclosure.

Extract the troubleshooting section into references/troubleshooting.md with a one-line pointer, and keep a short health-check verification snippet inline; this removes the duplication between the startup-verification and troubleshooting sections.

De-duplicate repeated steps (e.g., 'mkdir -p ~/.openviking/log' appears in both Environment Setup and Server Startup) and strip the echo banner/comment-decoration padding from inline scripts.

DimensionReasoningScore

Conciseness

The body is mostly command-driven with no conceptual padding (no explanation of what nohup or uv is), but it could be tightened: the ~110-line inline cleanup script is padded with echo step-banners and decorative separators, log-directory creation ("mkdir -p ~/.openviking/log") is repeated in both Environment Setup and Server Startup, and the four "Verify Server is Running" methods duplicate material that reappears in Verification and Troubleshooting. This lands on anchor 3 rather than 4, where only minor trimming would be needed.

3 / 5

Actionability

Everything is copy-paste ready: a complete server config JSON with placeholders clearly flagged for replacement, exact curl commands with expected outputs ("Expected: {\"status\": \"ok\"}"), a ready-to-run cleanup script, and troubleshooting entries structured as Check/Solution pairs with executable commands. It matches the top anchor — specific examples cover the common cases.

5 / 5

Workflow Clarity

Every procedure is explicitly sequenced with validation checkpoints and feedback loops: startup saves the PID and verifies via the health endpoint; shutdown escalates graceful kill to force-kill and verifies the process is gone; and the destructive cleanup stops the server first (aborting with an error if it cannot), creates a timestamped backup, requires a typed 'DELETE' confirmation, and reports the restore command. The destructive-operation validation cap does not apply — this matches the top anchor.

5 / 5

Progressive Disclosure

No bundle files exist (references/, scripts/, assets/ are absent), and all ~440 lines live in SKILL.md. Section headers and a table of contents give real structure, but content that clearly belongs in separate files — the full cleanup script and the troubleshooting guide — is inlined, which fits anchor 3 rather than 4 (where most content would be appropriately split into referenced files).

3 / 5

Total

16

/

20

Passed

Description

83%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 answers both what and when explicitly, lists five concrete actions, and is anchored to a distinctly named system. Reaching the top marks would only require broadening the trigger clause (restart/upgrade/troubleshoot) and cleaning up its phrasing.

DimensionReasoningScore

Specificity

The description lists multiple concrete actions — "configure, install, start, stop, and cleanup the server" — giving comprehensive coverage of the server-operations domain with no vague filler. It clearly matches the top anchor rather than anchor 4, since the action list covers the skill's full scope (setup, runtime control, and cleanup) rather than leaving minor gaps.

5 / 5

Completeness

Both parts are explicitly present: the "what" is five concrete actions ("Operate and maintain OpenViking server - configure, install, start, stop, and cleanup") and the "when" is stated ("Use when need to setup or manage OpenViking service deployment"). It sits at anchor 4 rather than 5 because the trigger clause covers only setup/manage and the slightly garbled phrasing ("Use when need to") makes it less crisp than the anchor-5 example's concrete, well-formed trigger phrases.

4 / 5

Trigger Term Quality

Natural trigger phrases like "Use when need to setup or manage OpenViking service deployment" are present, alongside operation verbs users would actually say (start, stop, install). It falls short of anchor 5 because common variations users might say — restart, upgrade, troubleshoot, deploy — are missing from the trigger clause.

4 / 5

Distinctiveness Conflict Risk

The named system ("OpenViking server") creates a clear niche with distinct triggers; no other plausible skill would fire on these phrases, so conflict risk is minimal — matching the top anchor.

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

volcengine/OpenViking

Path

examples/skills/ov-server-operate/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.