CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

docker-management

Manage Docker containers, images, volumes, and Compose.

Quality

70%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide
SecuritybySnyk

High

Do not use without reviewing

Fix and improve this skill with Tessl

tessl review fix ./optional-skills/devops/docker-management/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

71%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 highly actionable, well-organized Docker reference with strong command coverage, good safety warnings, and explicit verification steps. Its main weaknesses are token inefficiency (duplicated Quick Reference table, re-teaching basic Docker commands) and a monolithic structure with no progressive disclosure despite a length that clearly warrants splitting into reference files.

Suggestions

Remove the Quick Reference table or the duplicated commands in the Procedure section — the two cover nearly identical ground.

Split the pitfalls table, compose.yml example, and Dockerfile optimization tips into references/ files (e.g. PITFALLS.md, COMPOSE.md, DOCKERFILE.md) linked from SKILL.md to enable progressive disclosure.

Trim basic commands Claude already knows (docker ps/stop/start/rm) and keep the skill focused on curated guidance: pitfalls, warnings, verification, and decision rules.

DimensionReasoningScore

Conciseness

Command listings are dense, but the Quick Reference table duplicates ~10 commands that reappear verbatim in the Procedure section, and much of the body recites standard Docker CLI usage (docker ps/stop/start/rm) that Claude already knows. Anchor 3 ("mostly efficient but includes some unnecessary explanation or could be tightened") fits better than anchor 4 because the duplication and re-teaching of basics is more than minor.

3 / 5

Actionability

Every section is copy-paste-ready executable commands with concrete examples (nginx, postgres:16, port mappings, resource limits), plus a pitfalls table pairing problems with exact fixes and a per-task verification list. Matches the anchor-5 "fully executable; specific examples cover the common cases".

5 / 5

Workflow Clarity

There is a clear structure (identify domain → per-domain operations → cleanup) with explicit safety checkpoints: "Always start with a diagnostic before cleaning", "confirm with user first!", "DESTROYS DATA", and a Verification checklist. Falls short of anchor 5 because the procedure is a domain reference map rather than a sequenced workflow with per-step validate-and-retry feedback loops — validation is grouped in a terminal section instead of at each checkpoint.

4 / 5

Progressive Disclosure

The body is well-sectioned but monolithic: a 270-line single file with no references/ directory, inlining a full compose.yml example, an 8-row pitfalls table, and a Dockerfile optimization list that would fit better in separate reference files. Anchor 3 ("content that should be separate is inline") is the best fit; not 4 because there is no reference file structure at all.

3 / 5

Total

15

/

20

Passed

Description

60%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 short, distinct, domain-anchored description that names the right objects but relies on a single generic verb and omits any explicit 'use when' trigger guidance. It would not fire spuriously, but it also under-sells the skill's concrete capabilities and lacks natural trigger phrasing beyond the core Docker terms.

Suggestions

Add a 'Use when...' trigger clause, e.g. 'Use when the user mentions Docker, containers, Dockerfile, Compose, or asks to debug/build/clean up containerized workloads.'

Replace the generic verb 'Manage' with concrete actions: 'Run, stop, and debug Docker containers; build, tag, and prune images; manage volumes, networks, and Compose stacks.'

Include missing natural trigger terms such as 'Dockerfile' and 'container logs' to broaden natural-language matching.

DimensionReasoningScore

Specificity

The only action verb is the generic "Manage", mirroring the anchor-2 example "Processes PDF files" — it names the domain (Docker) and enumerates objects (containers, images, volumes, Compose) but offers no concrete actions. It does not reach anchor 3, which requires 1-2 concrete actions like "extracts content".

2 / 5

Completeness

The "what" is clear (manage containers, images, volumes, Compose) but there is no "Use when..." clause or equivalent trigger guidance, capping this dimension at 3 per the judging guidelines. Not score 2 because the "what" is specific, not vague.

3 / 5

Trigger Term Quality

"Docker containers, images, volumes, and Compose" are all natural terms a user would say, giving good keyword coverage. Falls short of anchor 5's comprehensive synonym coverage — no "Dockerfile", "container logs", "debug container", or similar common variations.

4 / 5

Distinctiveness Conflict Risk

"Docker" plus its sub-objects (containers, images, volumes, Compose) forms a clear niche with distinct trigger terms and minimal overlap risk with other skills; no generic language that would fire for the wrong skill.

5 / 5

Total

14

/

20

Passed

Validation

81%

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation — 13 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

metadata_version

'metadata.version' is missing

Warning

metadata_field

'metadata' should map string keys to string values

Warning

frontmatter_unknown_keys

Unknown frontmatter key(s) found; consider removing or moving to metadata

Warning

Total

13

/

16

Passed

Repository

NousResearch/hermes-agent

Path

optional-skills/devops/docker-management/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.