cli-anything-adguardhome

Command-line interface for AdGuard Home - Network-wide ad blocking and DNS management via AdGuard Home REST API. Designed for AI agents and power users who need to manage filtering, DNS rewrites, clients, DHCP, and query logs without a GUI.

Quality

76%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Low

Low-risk findings worth noting

Fix and improve this skill with Tessl

tessl review fix ./adguardhome/agent-harness/cli_anything/adguardhome/skills/SKILL.md

Quality

Content

82%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.

The body is an actionable, well-structured CLI reference with executable examples and a sensible agent workflow including validation guidance; its main weaknesses are minor verbosity and references that point to external package docs rather than bundled skill files.

Suggestions

Trim the duplicated opening paragraph (it restates the frontmatter description) and the trailing 'Version: 1.0.0' line to tighten token efficiency.

Add an explicit feedback loop for destructive commands (e.g. 'list before remove', or 'verify with `show` after `add`') to strengthen workflow validation.

If README.md/TEST.md/HARNESS.md are bundled with the skill, reference them as relative paths (e.g. [README.md](README.md)) and clarify they ship with the skill; otherwise drop the vague 'in the package' pointers.

Dimension	Reasoning	Score
Conciseness	The body is mostly lean command tables and executable examples with no over-explanation of concepts Claude already knows; only minor padding (the opening paragraph repeats the description, and the trailing version/'More Information' lines) could be trimmed.	4 / 5
Actionability	Provides copy-paste-ready, fully executable commands across the common cases (status, filter add/refresh, rewrite add, clients add, stats with --json), covering the typical usage surface concretely.	5 / 5
Workflow Clarity	The 'For AI Agents' section gives a clear numbered sequence with checkpoints ('Test connection first with config test') and validation ('Check return codes', 'Parse stderr for error messages on failure'); minor gaps remain for per-command feedback on destructive ops like remove/restart.	4 / 5
Progressive Disclosure	Content is well-organized into clearly headed command-group sections with examples; references to README.md/TEST.md/HARNESS.md are present and one level deep, though they point to package files rather than skill-bundled files and could be signaled more clearly.	4 / 5
	Total	17 / 20 Passed

Description

70%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.

The description is specific, well-targeted to a distinct product niche, and uses natural trigger terms, but it lacks an explicit 'Use when...' clause that tells Claude when to invoke the skill, capping completeness at 3.

Suggestions

Add an explicit trigger clause, e.g. 'Use when managing AdGuard Home, or when the user mentions ad blocking, DNS rewrites, DHCP leases, or query logs on an AdGuard Home server.'

Include a few natural synonyms/variations (e.g. 'blocklists', 'DNS overrides') to broaden trigger coverage toward the comprehensive anchor.

Dimension	Reasoning	Score
Specificity	Names the domain ('Command-line interface for AdGuard Home') and lists several concrete capabilities ('manage filtering, DNS rewrites, clients, DHCP, and query logs'), with only minor gaps in coverage of each action.	4 / 5
Completeness	It has a clear 'what' but no explicit 'Use when...' trigger clause; the 'Designed for AI agents and power users who need to manage...' phrase describes the audience rather than a trigger, which caps completeness at 3 per the rubric guideline.	3 / 5
Trigger Term Quality	Includes natural terms users would say ('ad blocking', 'DNS', 'DNS rewrites', 'AdGuard Home', 'filtering', 'DHCP', 'query logs'); a few common synonyms/variations are missing, so it falls just below the comprehensive anchor.	4 / 5
Distinctiveness Conflict Risk	Tied to a specific product ('AdGuard Home REST API') with distinct triggers, giving it a clear niche and minimal conflict risk with other skills.	5 / 5
	Total	16 / 20 Passed

Validation

100%

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 — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository: HKUDS/CLI-Anything
Path: adguardhome/agent-harness/cli_anything/adguardhome/skills/SKILL.md
Commit: 34f5195

Reviewed: 1 day 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.