CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

effect-v4

Write, review, or upgrade Effect v4 code in the Composio CLI, cli-keyring, and json-schema-to-effect-schema packages, all using the matching range effect@^4.1.0 — Context.Service and explicit layers, Schema.TaggedError and typed recovery, the effect/cli command surface, and the vendored effect source oracle. Use when writing or reviewing Effect v4 code, answering a v4 API question, working in effect/cli, defining a Context.Service service, modeling an error with Schema.TaggedError, bumping the Effect pins, or verifying an unfamiliar API against ts/vendor/effect. Do not use for CLI command UX/wiring design (use cli-command) or CLI E2E tests (use cli-e2e).

Quality

92%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide
SecuritybySnyk

Low

Low-risk findings worth noting

SKILL.md
Quality
Evals
Security

Quality

Content

82%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, high-signal reference skill: dense non-negotiables grounded in the actual source, well-signaled one-level references, and concrete verification commands. The main gaps are a broken versions.json link, no inline pattern examples, and no explicit re-validate feedback loop in the verification workflow.

Suggestions

Add versions.json to the bundle (or remove the 'See versions.json' link) so every cited path resolves.

Include one minimal inline Context.Service + Schema.TaggedError snippet so the core patterns are executable without opening a reference file.

State an explicit fix-and-re-run loop in Verification (e.g., 'if check-examples fails, fix the block or add a no-check fence, then re-run') to close the workflow feedback gap.

DimensionReasoningScore

Conciseness

Lean and dense throughout: 'Every claim below is grounded in the migrated source, not memory of v3', and non-negotiables like 'Wrap fallible Promises with Effect.tryPromise({ try, catch })' deliver non-obvious, project-specific facts with zero padding. Matches the score-5 anchor; not 4 because there is no passage of over-explanation to trim.

5 / 5

Actionability

Gives copy-paste verification commands ('pnpm typecheck', 'node .agents/skills/effect-v4/scripts/check-examples.mjs') and exact API forms ('Effect.gen(function* () {...})', 'static readonly Default/layer'), but complete code examples of the core service/error patterns are deferred to references rather than shown inline. Matches the score-4 anchor (mostly executable, minor gaps); not 5 for the missing inline pattern examples, not 3 because the commands and signatures given are directly executable.

4 / 5

Workflow Clarity

The Verification section sequences checkpoints (typecheck, lint, test, then validate:agent-skills/validate:skill-routing, then check-examples.mjs) and defines a failure convention ('Blocks that quote repo files with unresolvable imports carry a no-check fence info string'). Matches the score-4 anchor; not 5 because no explicit fix-and-re-validate feedback loop is stated, not 3 because most checkpoints are explicit.

4 / 5

Progressive Disclosure

'Read next' cleanly signals three real one-level-deep references (references/core-patterns.md, cli-surface.md, upgrade-workflow.md) with per-file descriptions, plus a real script. However, 'See versions.json for the exact example-check matrix' points to a file not present in the bundle, a broken reference. Matches the score-4 anchor (good structure, minor organization gaps); not 5 due to the missing versions.json, not 3 because the structure is otherwise exemplary.

4 / 5

Total

17

/

20

Passed

Description

100%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 exemplary: it names concrete capabilities, packages, and APIs, gives an explicit multi-trigger 'Use when' clause, and adds explicit negative routing to sibling skills. Third-person voice throughout, with no fluff or over-claims.

DimensionReasoningScore

Specificity

Lists multiple concrete actions — 'Write, review, or upgrade Effect v4 code', 'Context.Service and explicit layers', 'Schema.TaggedError and typed recovery', 'the effect/cli command surface' — covering the skill's surface comprehensively. This matches the score-5 anchor (multiple specific concrete actions, comprehensive coverage), not 4, since there are no meaningful coverage gaps.

5 / 5

Completeness

Explicitly answers both 'what' (write/review/upgrade Effect v4 code with named patterns and version range effect@^4.1.0) and 'when' (a concrete 'Use when...' clause listing seven triggers), plus negative triggers. Matches the score-5 anchor structure; not 4 because the 'when' is fully explicit rather than improvable.

5 / 5

Trigger Term Quality

The 'Use when' clause enumerates natural phrases users would say: 'writing or reviewing Effect v4 code', 'working in effect/cli', 'defining a Context.Service service', 'modeling an error with Schema.TaggedError', 'bumping the Effect pins', 'verifying an unfamiliar API against ts/vendor/effect'. Matches the score-5 anchor's comprehensive coverage including synonyms and concrete artifacts; not 4 because no common variation is missing.

5 / 5

Distinctiveness Conflict Risk

Clear niche (Effect v4 in three named packages) with explicit disambiguation: 'Do not use for CLI command UX/wiring design (use cli-command) or CLI E2E tests (use cli-e2e)'. Matches the score-5 anchor (distinct triggers, minimal conflict risk); not 4 because overlap risk is actively routed away, not merely minor.

5 / 5

Total

20

/

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

relative_links

Relative link issues: 1 missing

Warning

Total

15

/

16

Passed

Repository

ComposioHQ/composio

Path

.agents/skills/effect-v4/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.