Name: netalertx-docker-prune
Rating: 72.8 (1 reviews)
Author: netalertx

netalertx-docker-prune

Clean up unused Docker resources. Use this when asked to prune docker, clean docker, remove unused images, free disk space, or docker cleanup. DANGEROUS operation. Requires human confirmation.

Quality

88%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Medium

Suggest reviewing before use

Quality

Content

87%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 an exemplary lean, actionable, well-sectioned single-task skill. Its only gap is that a destructive batch operation lacks an explicit verification/feedback checkpoint beyond the script's own confirmation prompt, which the rubric caps at 2 for workflow clarity.

Suggestions

Add a pre-flight verification step, e.g. run `docker ps -a --filter status=exited` or the script's dry-run/list mode before confirming, so Claude can surface what will be destroyed.

Add a post-run verification such as `df -h` or `docker system df` to confirm space was reclaimed.

Show the confirmation prompt the script emits so Claude knows what to expect and can guide the human through it.

Dimension	Reasoning	Score
Conciseness	The body is lean and assumes Claude's competence: a danger banner, one executable command, a delete list, trigger list, and a one-line safety note — every token earns its place with no padding.	3 / 3
Actionability	It provides a single concrete, copy-paste-ready executable path (/workspaces/NetAlertX/.devcontainer/scripts/confirm-docker-prune.sh) with no pseudocode, matching the level-3 anchor.	3 / 3
Workflow Clarity	The single action is unambiguous and a human-confirmation checkpoint is noted, but for a destructive batch operation the body lacks an explicit pre-flight verification (e.g. dry-run/listing of what will be removed) and post-run confirmation, which caps destructive workflows at 2 per the rubric.	2 / 3
Progressive Disclosure	The skill is under 50 lines, needs no external references, and is organized into clearly labeled sections (Command, What Gets Deleted, When to Use, Safety), satisfying the simple-skill exception for a level-3 score.	3 / 3
	Total	11 / 12 Passed

Description

90%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 concise, third-person, and clearly states both the capability and explicit trigger conditions, with strong natural-language triggers. Its only weakness is that the capability is stated as a single general action rather than enumerating the distinct resources it prunes.

Suggestions

Expand the opening capability clause to enumerate specific actions, e.g. "Remove stopped containers, unused images, volumes, and networks to free disk space."

Consider noting the scope boundary (e.g. running containers are preserved) to further reduce conflict risk with adjacent skills.

Dimension	Reasoning	Score
Specificity	"Clean up unused Docker resources" names the domain and a general action but does not list multiple specific concrete actions (e.g. removing images vs volumes vs networks), so it falls short of the level-3 anchor.	2 / 3
Completeness	It explicitly answers what ("Clean up unused Docker resources") and when ("Use this when asked to prune docker...") with explicit triggers, satisfying the level-3 anchor for both what and when.	3 / 3
Trigger Term Quality	"prune docker, clean docker, remove unused images, free disk space, or docker cleanup" gives good coverage of natural phrases a user would actually say, matching the level-3 anchor.	3 / 3
Distinctiveness Conflict Risk	Docker prune is a clear niche with distinct triggers and an explicit danger/confirmation marker, making it unlikely to fire for an unrelated skill.	3 / 3
	Total	11 / 12 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: netalertx/NetAlertX
Path: .github/skills/docker-prune/SKILL.md
Commit: 20ddf48

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.