CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

docker-compose-security

Regras rígidas de segurança para Docker Compose - NUNCA expor variáveis de ambiente

Quality

69%

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

Fix and improve this skill with Tessl

tessl review fix ./skills/infrastructure/docker-compose/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

75%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 content is highly actionable, with concrete forbidden/correct YAML examples, complete .env templates, and an executable validation script backed by a pre-commit checklist. Its main weaknesses are redundancy — the same rules are repeated across bullet lists, validation steps, and the checklist — and an only-implicit fix-and-revalidate loop.

Suggestions

Consolidate the redundant restatements: the ❌ bullet list, ✅ ALWAYS list, and final checklist each repeat the golden rule and validation steps — one authoritative rule statement plus the checklist would cut tokens meaningfully.

Make the error-recovery loop explicit in the validation section: on grep match, apply the CORRECT env_file pattern, move the offending variable to the appropriate .env.* file, and re-run the script until clean before committing.

DimensionReasoningScore

Conciseness

The body teaches nothing Claude already knows and every section carries real guidance, but the same rules are restated across the six-item ❌ bullet list, the ✅ ALWAYS list, the numbered validation steps, and the final checklist — noticeable tightening is possible. This sits between 'mostly efficient but could be tightened' (3) and 'efficient with minor trim' (4); the duplication across three sections is more than minor, so 3.

3 / 5

Actionability

Guidance is fully executable and copy-paste ready: a concrete forbidden YAML example, a correct env_file-based YAML example, a project file tree, a complete .env.example template with placeholders, and a runnable grep validation command with defined failure behavior ('ERRO CRÍTICO - não commitar'). This matches the anchor for fully executable guidance covering the common cases.

5 / 5

Workflow Clarity

There is a clear sequence — apply the golden rule, set up the .env structure, run the four numbered pre-commit validation steps with an explicit failure instruction, then confirm via checklist — matching 'clear sequence with most checkpoints present'. It falls short of 5 because the error-recovery loop is only 'do not commit'; the fix-then-revalidate retry is implicit rather than an explicit step.

4 / 5

Progressive Disclosure

The single-file skill (~130 lines) has no bundle files and is organized into clear, well-labeled sections (golden rule, .env structure, validation, checklist) with all content appropriately inlined for this size. This matches 'good structure; most content appropriately placed; minor organization gaps' — the inlined .env templates could arguably live in assets/ files, keeping it below the clear-overview-with-references anchor 5.

4 / 5

Total

16

/

20

Passed

Description

50%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 communicates a clear single rule (never expose environment variables in Docker Compose) but omits any 'when to use' guidance and covers few natural trigger variations. Its very broad frontmatter trigger list increases the risk of firing on unrelated Docker tasks.

Suggestions

Add an explicit trigger clause, e.g. 'Use when creating or editing docker-compose.yml files that define environment variables, secrets, or credentials', to satisfy completeness.

Broaden trigger coverage with natural synonyms users actually say: secrets, credentials, API keys, .env files, docker-compose.yml (currently only docker-compose/env/variables are covered).

State the concrete actions the skill performs in third person — e.g. 'Moves secrets from the environment block to env_file, creates .env.example placeholders, and validates docker-compose.yml before commit' — to raise specificity and distinguish it from generic Docker skills.

DimensionReasoningScore

Specificity

The description names its domain ("segurança para Docker Compose") and one concrete rule ("NUNCA expor variáveis de ambiente"), matching the anchor for a domain plus 1-2 concrete actions without comprehensive coverage. It does not list several specific actions (not 4), but goes beyond bare domain-naming like 'Processes PDF files' (not 2).

3 / 5

Completeness

The 'what' is stated (strict Docker Compose security rules: never expose environment variables) but there is no 'Use when...' clause or equivalent explicit trigger guidance, which per the judging guidelines caps completeness at 3. The 'what' is clear, so it does not fall to 2.

3 / 5

Trigger Term Quality

"Docker Compose" and "variáveis de ambiente" are relevant natural keywords, but common variations users would say are missing (secrets, credentials, API keys, .env, docker-compose.yml), matching the 'some relevant keywords but missing variations' anchor. It is not generic like 'Works with files' (not 2), nor does it have the good coverage of a 4.

3 / 5

Distinctiveness Conflict Risk

The niche (env-var secrecy in Docker Compose) is somewhat specific, but the frontmatter triggers list (docker, compose, container, env, environment, variables) is so broad that virtually any Docker or environment question would match, creating real overlap risk with general Docker/container skills — the 'somewhat specific but could still overlap' anchor. Not 4 because the trigger breadth undermines distinctiveness; not 2 because the topic itself is not generic.

3 / 5

Total

12

/

20

Passed

Validation

93%

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

Validation — 15 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

frontmatter_unknown_keys

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

Warning

Total

15

/

16

Passed

Repository

fernandezbaptiste/cursor-multiagent-system

Path

skills/infrastructure/docker-compose/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.