CtrlK
BlogDocsLog inGet started
Tessl Logo

aif-dockerize

Analyze project and generate Docker configuration: Dockerfile (multi-stage dev/prod), compose.yml, compose.override.yml (dev), compose.production.yml (hardened), and .dockerignore. Includes production security audit. Use when user says "dockerize", "add docker", "docker compose", "containerize", or "setup docker".

73

Quality

92%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

SecuritybySnyk

Low

Low-risk findings worth noting

SKILL.md
Quality
Evals
Security

Quality

Content

85%

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

The content is highly actionable with a clear multi-mode workflow, explicit validation checkpoints, and clean progressive disclosure to verified reference files. The main weakness is repetition of the Angie-preference rationale and security-hardening details across multiple steps, which inflates length without adding information.

Suggestions

Consolidate the security-hardening directives: state them once in compose.production.yml (Step 4.4) and have Steps 5 and 7 reference SECURITY-CHECKLIST.md rather than re-listing the same cap_drop/tmpfs/resource-limit items.

State the Angie-over-Nginx preference once (e.g. in Step 2.5) and drop the repeated rationale in Steps 1.3 and 4.2, linking to ANGIE-ACME.md instead.

Move the duplicated detection tables in Steps 2.1-2.2 into a single reference (e.g. PROJECT-PROFILES.md) so the main body stays a lean overview.

DimensionReasoningScore

Conciseness

The body is dense and operational (tables, glob/grep patterns, checklists) and avoids explaining basic Docker concepts, but repeats material across steps — the Angie preference and security-hardening list each reappear in Steps 2.5/4.2, 4.4, 5, and 7 — so it could be tightened.

2 / 3

Actionability

Provides concrete executable guidance throughout: specific Glob/Grep scans, base-image version sourcing rules (e.g. "go 1.24" -> "golang:1.24-alpine"), exact hardening directives ("cap_drop: [ALL]", "tmpfs" with "noexec,nosuid,size=100m", "127.0.0.1:5432:5432"), and a WebSearch step for image tags.

3 / 3

Workflow Clarity

A clearly sequenced 9-step flow with mode branching (generate/enhance/audit) and explicit validation checkpoints — the "Quality Checks (Before Writing)" checkbox list, the over-engineering check, and Step 7's always-run security checklist with a fix-before-presenting loop.

3 / 3

Progressive Disclosure

SKILL.md is an overview pointing to 9 well-signaled one-level-deep references, each with a "read when..." purpose statement; templates form a separate tier, and all referenced files (ANGIE-ACME, COMPOSE-PATTERNS, SECURITY-CHECKLIST, etc.) were verified to exist.

3 / 3

Total

11

/

12

Passed

Description

100%

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, complete, and distinctive, listing concrete artifacts and an explicit natural-language trigger clause. It avoids vague language and clearly communicates both capability and invocation context.

DimensionReasoningScore

Specificity

Enumerates multiple concrete outputs ("Dockerfile (multi-stage dev/prod), compose.yml, compose.override.yml (dev), compose.production.yml (hardened), and .dockerignore") plus a "production security audit", matching the multiple-specific-actions anchor.

3 / 3

Completeness

Explicitly answers both what (generate the listed Docker artifacts + security audit) and when via an explicit "Use when user says..." trigger clause, satisfying the both-what-and-when anchor.

3 / 3

Trigger Term Quality

Provides natural phrasings users would say ("dockerize", "add docker", "docker compose", "containerize", "setup docker"), giving good coverage of common variations rather than jargon.

3 / 3

Distinctiveness Conflict Risk

The Docker/containerization-config niche with distinct trigger phrases is clearly separated from other skills and unlikely to fire for the wrong skill.

3 / 3

Total

12

/

12

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.

Validation13 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

skill_md_line_count

SKILL.md is long (531 lines); consider splitting into references/ and linking

Warning

allowed_tools_field

'allowed-tools' contains unusual tool name(s)

Warning

frontmatter_unknown_keys

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

Warning

Total

13

/

16

Passed

Repository
lee-to/ai-factory
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.