CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

effect

Work with Effect v4 TypeScript code in this repo

Quality

67%

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 ./.agents/skills/effect/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 body is a lean, well-structured set of terse, actionable directives with concrete Effect v4 APIs and a clear sequenced source-of-truth procedure. It would benefit from a couple of full executable code examples and an explicit validate-and-retry loop.

Suggestions

Add 1-2 small complete code blocks (e.g. a minimal Effect.gen service method and a testEffect(...)) to lift actionability from directive to copy-paste ready.

Make the source-of-truth workflow an explicit validate->fix->retry loop (e.g. 'If the cloned reference lacks the API, search nearby repo code; if still missing, say so before implementing').

De-duplicate the 'do not answer from memory / verify against the reference' guidance, which appears in both Source Of Truth and Guidelines.

DimensionReasoningScore

Conciseness

The body is efficient and assumes Claude's competence — guidelines are terse directives like 'Use Effect.gen(function* () { ... })' with no padding about what Effect is; only minor redundancy between the 'Source Of Truth' and 'Guidelines' lists keeps it from a 5.

4 / 5

Actionability

It gives specific, executable API names (Effect.fn('Name'), Schema.TaggedErrorClass, testEffect(...), it.live(...)) and concrete file paths, though most guidance is directive rather than full copy-paste examples.

4 / 5

Workflow Clarity

The 'Source Of Truth' section is a numbered, sequenced procedure with an explicit verification checkpoint ('Do not answer from memory. Verify against .opencode/references/effect'), but it lacks an explicit validate->fix->retry loop, which keeps it at 4 rather than 5.

4 / 5

Progressive Disclosure

Content is well-organized into clear sections (Source Of Truth, Guidelines, Testing Patterns) and points to one-level-deep external references (.opencode/references/effect, packages/core/test/lib/effect.ts); it stays just under 50 lines with no nested references, leaving only minor room to improve.

4 / 5

Total

16

/

20

Passed

Description

42%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 identifies the domain but omits concrete actions and any 'Use when' trigger guidance, which caps its completeness. It is reasonably distinct but generic in what it promises to do.

Suggestions

Add concrete actions, e.g. 'Write Effect.gen workflows, define Schema types and branded IDs, compose layers, and write Effect tests'.

Add a 'Use when...' clause naming natural triggers like 'Use when writing or refactoring Effect/TS services, schemas, layers, or Effect tests in this repo'.

Tighten specificity by listing the main capabilities (services, schemas, workflows, HTTP handlers, tests) rather than the single generic 'Work with'.

DimensionReasoningScore

Specificity

Names the domain ('Effect v4 TypeScript code in this repo') but gives no concrete actions — it does not list what work it performs, only the subject area.

3 / 5

Completeness

It states a vague 'what' (work with Effect code) but provides no 'when'/'Use when' clause, capping completeness at 3 and dropping to 2 for the weakness of the 'what'.

2 / 5

Trigger Term Quality

'Effect v4 TypeScript' is a relevant technical keyword, but it is a framework name rather than natural user phrasing and lacks synonyms a user would say.

3 / 5

Distinctiveness Conflict Risk

The Effect v4 + repo-scoped framing is a fairly clear niche with minor overlap risk against general TypeScript skills.

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

divaltor/starlight

Path

.agents/skills/effect/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.