CtrlK
BlogDocsLog inGet started
Tessl Logo

configuration

Where a configuration value belongs — app config schema, agent-native.config.ts, or an environment variable — and how the layers resolve. Use before adding an env var, a configure*/set* function, a plugin option, or a register* function, and when deciding whether something is config or a registry.

66

Quality

83%

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

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 body is a tight, opinionated guide with concrete code, file paths, and a clear field-addition sequence, plus a useful antipatterns section. It is strong across the board but does not hit the top anchor on any dimension due to implicit validation checkpoints and illustrative rather than exhaustive examples.

DimensionReasoningScore

Conciseness

The body is dense and opinionated with no padding of concepts Claude already knows, opening with a pointed stat ('301 distinct environment variables') and assuming domain fluency. A few narrative asides ('This skill exists so the next value does not do the same thing') could be trimmed, keeping it just below the leanest 5.

4 / 5

Actionability

It gives concrete, near-executable guidance: real file paths ('packages/core/src/app-config/'), a complete z.object example with .meta({ env }), and a defineAppConfig plugin example. The examples are mostly copy-paste ready but are illustrative fragments rather than covering every common case, so it sits at 4.

4 / 5

Workflow Clarity

The 'Adding a field' section lays out a clear sequence (domain file -> schema.ts line -> read via getAppConfig -> set from server/plugins/config.ts -> add descriptor + parser coverage), and resolution order is explicit. Checkpoints are implicit rather than bolded validate-then-proceed steps, so it does not reach the explicit-validation 5.

4 / 5

Progressive Disclosure

Content is well organized into clear sections (The rule, Where a value goes, Adding a field, Resolution order, Config or registry?, Antipatterns, Deprecated paths) with one-level references ('see the secrets skill', a plan file). No bundle files exist and nothing clearly belongs in a separate file, but at 165 lines it exceeds the simple-skill 50-line exception that would allow a 5.

4 / 5

Total

16

/

20

Passed

Description

87%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 is strong: it concisely states what the skill does and gives explicit, concrete use-when triggers tied to specific internal surfaces. It is third-person and free of fluff, with only minor room to broaden trigger-term synonyms.

DimensionReasoningScore

Specificity

Names concrete placement surfaces ('app config schema, agent-native.config.ts, or an environment variable') and several concrete trigger actions ('adding an env var, a configure*/set* function, a plugin option, or a register* function'). It lists several specific actions, but the framing is about where a value belongs rather than an exhaustive enumerated verb set, so it stops short of the fully comprehensive 5.

4 / 5

Completeness

It explicitly answers both what ('Where a configuration value belongs ... and how the layers resolve') and when ('Use before adding an env var ... and when deciding whether something is config or a registry') with concrete trigger phrases, matching the top anchor.

5 / 5

Trigger Term Quality

Trigger terms like 'env var', 'configure*/set* function', 'plugin option', and 'register* function' are phrases a developer on this codebase would naturally say. Coverage is good and domain-appropriate, though it leans on internal jargon and omits a few common synonyms, keeping it just below the comprehensive 5.

4 / 5

Distinctiveness Conflict Risk

It carves a clear niche — config-value placement across named internal surfaces — with distinct triggers ('config or a registry', 'register* function') that are unlikely to fire for unrelated skills, giving minimal conflict risk.

5 / 5

Total

18

/

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
BuilderIO/agent-native
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.