CtrlK
BlogDocsLog inGet started
Tessl Logo

skill-claw

OpenClaw instance administration — manage hosts across macOS, Ubuntu/Debian, Docker, OCI, and Proxmox

62

Quality

72%

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

Fix and improve this skill with Tessl

tessl review fix ./.claude/skills/skill-claw/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

77%

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

The content is highly actionable with a rigorous, well-sequenced workflow and strong verification discipline. Its weaker points are mild redundancy that hurts conciseness and a monolithic single-file structure with no progressive disclosure to deeper reference materials.

Suggestions

Split per-platform deep dives and the channel integration tables into referenced reference files (e.g., references/platforms.md, references/channels.md) with one-level-deep links from SKILL.md.

Dedupe content that appears in both the Security Hardening checklist and the Red Flags table, and remove gateway commands repeated in the CLI quick reference, to tighten the token budget.

DimensionReasoningScore

Conciseness

The body is command-dense and avoids concept explanation, but has redundancy — the CLI quick reference repeats gateway lifecycle commands and the Red Flags table partly reiterates the Security Hardening checklist — so it is mostly efficient but could be tightened.

2 / 3

Actionability

It provides extensive copy-paste-ready bash per platform, service lifecycle tables, an update workflow, and a CLI quick reference, matching the 'fully executable code/commands; copy-paste ready' anchor.

3 / 3

Workflow Clarity

A clear four-phase sequence (Detect → Assess → Execute → Verify) is enforced by a MANDATORY contract and Iron Law, with explicit verification, backup-before-update, and red-flag checkpoints for destructive operations.

3 / 3

Progressive Disclosure

It is well-organized into sections but is a single ~360-line file with no bundle files (references/scripts/assets absent); per-platform deep dives and channel integration that could be split into referenced files remain inline, fitting the 'some structure but content that should be separate is inline' anchor.

2 / 3

Total

10

/

12

Passed

Description

67%

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 is specific and distinctive, naming a clear product niche and five concrete platforms. Its main weakness is the absence of an explicit 'Use when...' trigger clause, which caps completeness and leaves trigger-term quality mid-range.

Suggestions

Add an explicit 'Use when...' trigger clause listing natural user phrasings (e.g., 'Use when installing, updating, hardening, or troubleshooting OpenClaw instances').

Include more natural trigger terms users would actually say (e.g., 'install OpenClaw', 'harden OpenClaw', 'OpenClaw gateway not starting') alongside the platform list.

DimensionReasoningScore

Specificity

"manage hosts across macOS, Ubuntu/Debian, Docker, OCI, and Proxmox" lists multiple concrete platforms and the concrete action of host management, matching the anchor for several specific concrete actions.

3 / 3

Completeness

It clearly states what the skill does (instance administration, manage hosts) but provides no "Use when..." clause or equivalent explicit trigger for when to invoke it, so completeness is capped at 2 per the guidelines.

2 / 3

Trigger Term Quality

It names the product and platforms but uses technical phrasing rather than the natural terms a user would say; it lacks common variations like "install OpenClaw", "harden", or "troubleshoot", fitting the 'some relevant keywords but missing variations' anchor.

2 / 3

Distinctiveness Conflict Risk

"OpenClaw instance administration" is a clear niche tied to a specific product with distinct platform triggers, making it unlikely to fire for an unrelated skill.

3 / 3

Total

10

/

12

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.

Validation16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository
nyldn/claude-octopus
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.