CtrlK
BlogDocsLog inGet started
Tessl Logo

varlock-claude-skill

Secure environment variable management ensuring secrets are never exposed in Claude sessions, terminals, logs, or git commits

31

Quality

25%

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/varlock-claude-skill/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

11%Scale 1-5

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

This skill is essentially a placeholder — it repeats its own description three times and provides no actionable content whatsoever. For a security-focused skill about preventing secret exposure, the complete absence of concrete patterns, commands, validation steps, or examples is particularly problematic. It fails to teach Claude anything it could act on.

Suggestions

Add concrete, executable examples showing how to securely load environment variables (e.g., using .env files with dotenv, reading from a secrets manager) without exposing them in logs or terminal output.

Define a clear workflow with validation steps: e.g., 1) check .gitignore includes .env, 2) load secrets via specific pattern, 3) verify no secrets appear in command output, 4) validate git staging doesn't include secret files.

Add specific anti-patterns and guardrails, such as 'Never use echo $SECRET or print(os.environ[...])' and 'Always use subprocess with env parameter rather than shell interpolation'.

Remove the redundant 'When to Use' and 'Instructions' sections that just repeat the overview, and replace them with actual instructional content.

DimensionReasoningScore

Conciseness

The content is padded with repetitive descriptions — the overview, 'when to use' section, and instructions all say essentially the same thing. Despite being short, it wastes tokens by repeating the description three times without adding any new information.

2 / 5

Actionability

There is zero concrete guidance — no code, no commands, no specific steps, no examples. The entire content is a vague description that tells Claude nothing about how to actually manage environment variables securely.

1 / 5

Workflow Clarity

No steps, no sequence, no validation checkpoints. For a skill involving security-sensitive operations (secrets management), the complete absence of any workflow or safety checks is a critical gap.

1 / 5

Progressive Disclosure

There are section headers providing minimal structure, but no bundle files exist and the only reference is an external GitHub link with no indication of what it contains. There's no meaningful content to organize or disclose progressively.

2 / 5

Total

6

/

20

Passed

Description

39%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 identifies a clear domain (environment variable/secret management) and conveys a security-focused purpose, which gives it some distinctiveness. However, it lacks concrete actions describing what the skill actually does and has no explicit 'Use when...' clause, making it difficult for Claude to know precisely when to select it. The trigger terms are reasonable but incomplete, missing common user phrases like '.env', 'API keys', or 'credentials'.

Suggestions

Add concrete actions describing what the skill does, e.g., 'Reads .env files, injects environment variables into processes, validates secret configurations, and prevents accidental exposure in output.'

Add an explicit 'Use when...' clause with trigger terms, e.g., 'Use when the user mentions environment variables, .env files, secrets, API keys, credentials, or needs to manage sensitive configuration values.'

Include common synonyms and file extensions users might reference, such as '.env', 'env vars', 'API keys', 'credentials', 'dotenv', and 'secret management'.

DimensionReasoningScore

Specificity

Names the domain ('environment variable management') and mentions a goal ('ensuring secrets are never exposed'), but does not list concrete actions like 'read .env files', 'inject variables', 'rotate keys', etc. The description is more about a principle than specific capabilities.

2 / 5

Completeness

The 'what' is vaguely stated as 'secure environment variable management' without concrete actions. There is no explicit 'when' clause or trigger guidance telling Claude when to select this skill. Per rubric guidelines, missing a 'Use when...' clause caps completeness at 3, and the vague 'what' brings it down further.

2 / 5

Trigger Term Quality

Includes relevant terms like 'environment variable', 'secrets', 'git commits', 'logs', and 'terminals', which are somewhat natural. However, it misses common synonyms and variations users might say such as '.env', 'API keys', 'credentials', 'dotenv', 'secret management', or 'env vars'.

3 / 5

Distinctiveness Conflict Risk

The focus on environment variables and secrets is fairly distinct and unlikely to overlap heavily with most other skills. However, it could potentially overlap with general security skills or git-related skills due to the mention of 'git commits' and 'logs'.

4 / 5

Total

11

/

20

Passed

Validation

90%

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

Validation10 / 11 Passed

Validation for skill structure

CriteriaDescriptionResult

frontmatter_unknown_keys

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

Warning

Total

10

/

11

Passed

Repository
administrakt0r/AI-Agents-Safe-Coding-Skills
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.