CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

secure-runtime-config

Use when a task reads credentials or runtime configuration from environment variables, setup-generated files, or a prepared eval workspace.

Quality

73%

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/secure-runtime-config/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

86%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 tight, well-structured instruction skill: every rule is specific and secret-handling guidance is unambiguous, with explicit validation checkpoints and a completion checklist. The only gaps are minor — unspecified fingerprint/error-message mechanics and no explicit recovery loop for failed validations.

DimensionReasoningScore

Conciseness

Lean and directive throughout: every line is an instruction ('Never paste their values into source code', 'Keep credentials out of logs, snapshots, generated files, and exception details') with zero padding and no explanation of concepts Claude already knows. It is not 4 because there are no instances of over-explanation to trim.

5 / 5

Actionability

Concrete, unambiguous directives cover the common cases: runtime reads from the process environment, treating missing and whitespace-only values as configuration errors with the variable named but the value excluded. Minor gaps keep it below fully executable: the one-way fingerprint mechanism and the actionable error-message shape are mentioned but not specified.

4 / 5

Workflow Clarity

A clear numbered sequence with explicit validation checkpoints (step 3's configuration-error handling, step 6's test run) plus a Completion Check checklist. Not 5 because the error-recovery feedback loop is incomplete — what to do when tests fail or a value is missing beyond raising the error is not addressed; not 3 because validation checkpoints are explicitly present, not merely implied.

4 / 5

Progressive Disclosure

Under 50 lines with no need for external references, and the content is well organized into Workflow, Prepared Workspaces, and Completion Check sections — this meets the simple-skill exception where well-organized sections alone warrant a 5. No bundle files exist, and none are needed.

5 / 5

Total

18

/

20

Passed

Description

47%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 well-targeted trigger clause with natural keywords and a distinct niche, but it is only half a description: it says precisely when to use the skill while saying nothing about what the skill does. Adding a 'what' clause with the skill's concrete actions would move it to the 4-5 range.

Suggestions

Add a 'what' clause before the 'Use when' clause stating the skill's actions, e.g. 'Reads credentials from the process environment at runtime, validates required values, and keeps secret values out of source code, logs, and generated files. Use when...'

Include the natural trigger synonyms users actually say, such as 'secrets', 'API keys', or '.env files', to improve trigger-term coverage.

Trim the jargon-leaning phrases ('setup-generated files', 'prepared eval workspace') or pair them with plainer equivalents so the trigger reads like user language rather than internal scenario terminology.

DimensionReasoningScore

Specificity

The description names its domain concretely ('credentials or runtime configuration from environment variables, setup-generated files, or a prepared eval workspace') but states no actions the skill performs — it is purely a trigger clause, matching the anchor 'Names the domain but actions are minimal or generic'. It is not 1 because the trigger sources are specific rather than abstract, and not 3 because that anchor requires 1-2 concrete actions to be listed.

2 / 5

Completeness

Only the 'when' is present without a 'what': the description fully specifies when to invoke the skill but never states what it does (runtime reads, validation, keeping secrets out of logs and generated files are all absent). This matches anchor 2 ('only when is present without what'); it is not 3 because that anchor requires a clear 'what', and scoring only explicit text, none is stated.

2 / 5

Trigger Term Quality

Good natural keyword coverage: 'credentials', 'runtime configuration', and 'environment variables' are phrases a user would naturally say when needing this skill. Not 5 because common synonyms and file extensions users say ('secrets', 'API keys', '.env') are missing; not 3 because coverage goes well beyond one or two generic terms.

4 / 5

Distinctiveness Conflict Risk

Mostly distinct: the credential-handling-in-prepared-workspace niche ('setup-generated files', 'prepared eval workspace') has clear triggers with only minor overlap risk from the broadly applicable 'reads ... runtime configuration from environment variables' phrasing, which could also match general setup/config skills. Not 5 because env-var reading is a widely applicable trigger.

4 / 5

Total

12

/

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

tessl-fe/eval-capabilities-demo

Path

skills/secure-runtime-config/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.