CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

container-manager

Use this skill when the user wants to manage Docker containers, build images, inspect logs, handle Docker Compose, or work with container orchestration.

Quality

83%

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

76%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 lean, highly actionable API reference whose copy-paste Python recipes cover the common Docker and Compose cases well. Its main weakness is the absence of validation around destructive operations (remove, compose down -v) — no exit-code checks, existence checks, or error-recovery guidance — which caps workflow clarity, plus minor redundancy between the code sections and the quick reference table.

Suggestions

Add validation around destructive operations: check subprocess returncode in compose_up/compose_down and raise or report failures, and verify a container exists (e.g. wrap client.containers.get in try/except docker.errors.NotFound) before remove_container or compose_down -v.

Add an explicit warning or confirmation guideline before remove_container(force=True) and compose_down(volumes=True) since these irreversibly delete containers and volumes.

Drop or slim the Quick Reference table (or keep only the table and drop duplicated code comments) to remove redundancy with the code sections above it.

DimensionReasoningScore

Conciseness

The body is nearly all executable code with no concept explanations, assuming Claude's competence, but the Quick Reference table restates methods already demonstrated in the code above, a minor redundancy that could be trimmed. This fits the efficient-with-minor-trimmable-instances anchor 4 rather than the every-token-earns-its-place anchor 5.

4 / 5

Actionability

Every section provides complete, copy-paste-ready Python functions with imports, parameters, and return values, plus a worked example ("# Example: check nginx config"). This matches the fully-executable, common-cases-covered anchor 5; there are no missing key details.

5 / 5

Workflow Clarity

Content is organized as an API reference with unambiguous single-call recipes, but it includes destructive operations — remove_container(force=True) and compose_down with volumes deletion — with no validation: subprocess calls never check result.returncode, and container lookups have no existence-check or error-recovery guidance. Per the judging guideline, destructive operations without validation/verification steps cap workflow clarity at 3.

3 / 5

Progressive Disclosure

Sections are clearly labeled and well-organized with no nested references, and the compact API content is appropriately inline for a skill with no bundle files. At ~130 lines of body it exceeds the under-50-line simple-skill threshold, so it fits the good-structure-with-minor-gaps anchor 4 rather than a 5.

4 / 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 with an explicit 'Use when...' trigger and several concrete, natural capability phrases anchored firmly in the Docker domain. Its only weaknesses are minor coverage gaps in named actions and the slightly generic "container orchestration" phrase.

DimensionReasoningScore

Specificity

The description lists several concrete actions — "manage Docker containers, build images, inspect logs, handle Docker Compose" — with only minor coverage gaps (start/stop, exec, stats unnamed), though "work with container orchestration" is generic. This matches the several-specific-actions-with-minor-gaps anchor rather than the comprehensive anchor at 5 or the 1-2-actions anchor at 3.

4 / 5

Completeness

It explicitly answers both what (managing containers, building images, inspecting logs, handling Compose) and when ("Use this skill when the user wants to manage Docker containers...") with concrete trigger phrases. The when-clause is explicit and specific, matching the clearly-both anchor 5 rather than the could-be-more-specific anchor 4.

5 / 5

Trigger Term Quality

It includes natural phrases users would say — "Docker containers", "build images", "inspect logs", "Docker Compose" — but misses common variations like "start/stop containers", "docker ps", or "exec into a container". Good keyword coverage with a few natural terms missing fits anchor 4, not the comprehensive synonym/extension coverage of anchor 5.

4 / 5

Distinctiveness Conflict Risk

The Docker container-management niche is clear and mostly distinct, but the phrase "work with container orchestration" is broad and could overlap with Kubernetes-style orchestration skills this skill does not cover. Minor overlap risk with closely related skills fits anchor 4 rather than the minimal-conflict anchor 5.

4 / 5

Total

17

/

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

ProwlrBot/prowlr-marketplace

Path

skills/container-manager/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.