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 pinned exactly to effect@4.0.3 — 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

Passed

No findings from the security scan

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 lean, well-routed hub skill: exact version policy, non-negotiable patterns with exact API names, and a properly disclosed reference structure. The only deductions are the missing versions.json bundle file, the absence of an inline code example for the dominant patterns, and verification steps presented without explicit ordering.

Suggestions

Add versions.json to the skill bundle (or inline the version matrix in the body) — the body links to it but the file is absent, leaving a broken reference.

Include one minimal inline Context.Service definition (service + static readonly Default layer) so the dominant pattern is copy-paste visible without opening core-patterns.md.

Order the Verification section as an explicit sequence (e.g., 1. pnpm typecheck 2. pnpm --filter @composio/cli test 3. validate + check-examples after skill edits) with a stated pass/fail gate.

DimensionReasoningScore

Conciseness

The ~70-line body is dense with repo-specific policy ("all pinned exactly to 4.0.3 — never ^", "ESLint bans them in ts/packages/cli/src", "V4 does not generate a layer for you") and defers detail to references ("See '"Effect.gen' vs 'Effect.fn' in core-patterns"). Nothing explains general concepts Claude already knows; the one long bullet about Effect.fn is per-clause actionable guidance, not padding.

5 / 5

Actionability

Concrete, copy-paste commands are given ("pnpm typecheck", "pnpm --filter @composio/cli test", "node .agents/skills/effect-v4/scripts/check-examples.mjs") and every pattern names exact APIs ("Layer.succeed/Layer.effect/Layer.provide", "Effect.catchTag/catchTags/Match", "Effect.tryPromise({ try, catch })"). It falls short of anchor 5 only because no complete inline code example covers the common case (defining a Context.Service) — code excerpts are delegated to the references.

4 / 5

Workflow Clarity

Validation checkpoints are explicit (typecheck, filtered test run, skill validators, example compilation) with a stated gate ("the compiler is the compatibility gate") and a feedback loop ("when it and a reference disagree, trust the file and fix the reference"). Not anchor 5 because the body presents verification as a command block without an ordered sequence, and the main multi-step procedure (the upgrade workflow) lives in a reference rather than being sequenced here; not anchor 3 because checkpoints are present and explicit.

4 / 5

Progressive Disclosure

Clean overview/hub structure: three clearly signaled one-level-deep references with content summaries (all three exist in references/), scripts/check-examples.mjs present, and details appropriately split out of the body. One real gap against the actual bundle: "See [versions.json](versions.json) for the full matrix" points to a file that is absent from the skill directory, and typescript-testing/references/effect-v4-cli.md is a cross-skill path unverifiable from this bundle — minor navigation gaps that keep this below anchor 5.

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.

A model description: concrete capabilities, an explicit multi-trigger 'Use when' clause, and negative routing to sibling skills. Every phrase is a capability or a trigger; there is no padding to penalize.

DimensionReasoningScore

Specificity

"Write, review, or upgrade Effect v4 code in the Composio CLI, cli-keyring, and json-schema-to-effect-schema packages" names multiple concrete actions (write, review, upgrade, answer API questions, bump pins, verify against the vendored oracle) and grounds each in specific surfaces: "Context.Service and explicit layers, Schema.TaggedError and typed recovery, the effect/cli command surface". Coverage is comprehensive, matching the anchor-5 example's breadth rather than the 'minor gaps' of anchor 4.

5 / 5

Completeness

Both halves are explicit: the 'what' opens the description ("Write, review, or upgrade Effect v4 code... all pinned exactly to effect@4.0.3") and the 'when' is a full "Use when..." clause with concrete trigger phrases. This is a direct structural match to the anchor-5 exemplar, not merely the adequate-but-looser anchor-4 form.

5 / 5

Trigger Term Quality

The trigger vocabulary is exactly what a developer in this repo would say: "Effect v4 code", "v4 API question", "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". For this domain the API names are the natural user terms, and the list spans seven distinct trigger scenarios with synonyms (write/review, pinned/version language).

5 / 5

Distinctiveness Conflict Risk

The niche is tightly scoped (Effect v4 in three named packages at an exact pin), and it adds explicit negative routing: "Do not use for CLI command UX/wiring design (use cli-command) or CLI E2E tests (use cli-e2e)". That boundary guidance actively steers adjacent queries to sibling skills, minimizing conflict risk beyond even the anchor-5 exemplar.

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.