skill-claw

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

Quality

67%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Critical

Do not install without reviewing

Fix and improve this skill with Tessl

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

Quality

Content

77%Weight 40%Scale 1-3

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 highly actionable, well-sequenced operations runbook with strong validation checkpoints and copy-paste commands. Its main weaknesses are cross-section redundancy and the absence of any progressive-disclosure reference files for a broad multi-domain skill.

Suggestions

De-duplicate lifecycle/CLI commands by keeping the full reference in one place and linking from the other, and consolidate the 'never expose 18789 / use Tailscale' rule to a single canonical statement.

Split per-platform diagnostics and channel/tailscale integration details into reference files (e.g. DIAGNOSTICS.md, CHANNELS.md) referenced one level deep from SKILL.md to improve progressive disclosure.

Keep the SKILL.md body as a concise overview + process skeleton, moving exhaustive per-platform command catalogs to the references.

Dimension	Reasoning	Score
Conciseness	Predominantly lean and command-dense with no concept-explaining fluff, but contains genuine redundancy — lifecycle commands appear in both the service table and CLI quick reference, and the 'use Tailscale / never expose 18789' rule is restated across the hardening checklist, Tailscale section, and Red Flags table.	2 / 3
Actionability	Provides fully executable, copy-paste-ready commands with platforms and flags throughout (uname, openclaw status/health/doctor, curl installer, systemctl, tailscale serve), plus platform-to-method and action-to-command tables.	3 / 3
Workflow Clarity	Uses an explicit four-phase sequence (Detect → Assess → Execute → Verify) with validation checkpoints, and the update workflow enforces backup-before-update and verify-after, satisfying the feedback-loop requirement for destructive operations.	3 / 3
Progressive Disclosure	Well-organized into clear sections, but with no bundle files present the ~350-line multi-domain runbook (per-platform diagnostics, channels, tailscale, integrations) is entirely inline where some content could be split into one-level-deep reference files.	2 / 3
	Total	10 / 12 Passed

Description

57%Weight 40%Scale 1-3

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 about its OpenClaw niche and target platforms, but relies on a single generic verb and omits explicit 'Use when' trigger guidance from the description field itself. Pushing concrete actions and a trigger clause into the description would lift it from good to strong.

Suggestions

Expand 'manage hosts' into specific actions in the description, e.g. 'install, update, migrate, harden, back up, and monitor OpenClaw instances'.

Add an explicit 'Use when...' clause to the description naming natural trigger phrases (e.g. 'Use when the user asks to manage, update, secure, or back up an OpenClaw instance').

Include common action verbs (install, upgrade, doctor, security audit, channel setup) directly in the description rather than only in the trigger field.

Dimension	Reasoning	Score
Specificity	Names the domain (OpenClaw instance administration) and enumerates concrete platforms (macOS, Ubuntu/Debian, Docker, OCI, Proxmox), but bundles all actions under the single general verb 'manage' rather than listing multiple specific concrete actions.	2 / 3
Completeness	Clearly answers 'what' (OpenClaw administration across named platforms) but the description field lacks an explicit 'Use when...' clause; explicit trigger guidance lives only in the separate trigger field, capping completeness at 2.	2 / 3
Trigger Term Quality	Includes several relevant natural keywords (OpenClaw and the platform names), but the common action verbs a user would say (update, install, secure, backup) appear only in the separate trigger field, not in the description itself.	2 / 3
Distinctiveness Conflict Risk	The OpenClaw proper noun defines a clear, distinct niche scoped by named platforms, making it unlikely to trigger for the wrong skill.	3 / 3
	Total	9 / 12 Passed

Validation

93%

Warnings & errors only

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

Criteria	Description	Result
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	15 / 16 Passed

Repository: nyldn/claude-octopus
Path: .claude/skills/skill-claw/SKILL.md
Commit: 9f39f0c

Reviewed: 7 days ago

Table of Contents

Discovery Implementation Validation

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.