effect-v3-to-v4

Use this skill when migrating a codebase from Effect v3 to Effect v4, upgrading `effect` or any `@effect/*` package across the v3/v4 boundary.

Quality

88%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Passed

No findings from the security scan

Quality

Content

88%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 an exemplary migration runbook: executable commands, explicit validation feedback loops, and a well-sequenced workflow with hard prohibitions as guardrails. Its main weakness is minor rationale padding and a monolithic single-file structure that leans lightly on progressive disclosure.

Suggestions

Trim operational-rationale sentences (e.g. why per-file work is context-hungry) to tighten conciseness toward 5.

Consider moving the rg recipe catalog or repo-level change details into a reference file referenced from SKILL.md to improve progressive disclosure.

Dimension	Reasoning	Score
Conciseness	The body is lean and assumes Claude's competence — it never explains what Effect is or basic concepts — but contains a few rationale sentences (e.g. 'Per-file migration work is context-hungry; do it in sub-agents so the main session's context survives') that could be trimmed. It is not a 5 because of those minor over-explanation instances, and not a 3 because it is mostly efficient rather than padded.	4 / 5
Actionability	Fully executable, copy-paste-ready guidance throughout: concrete `git clone` commands, multiple specific `rg` search recipes covering symbol/module/import-map lookups, `tsc --noEmit`, and validation commands (`git -C .repos/effect remote get-url origin`, `node -p "require(...).version"`). This matches the score-5 anchor of executable commands covering common cases.	5 / 5
Workflow Clarity	A clear 6-step numbered workflow with explicit validation checkpoints (validate existing checkout, type-check error inventory, 'iterate until the type-check is clean' feedback loop) and a defined done condition. The validate→fix→retry loop for a batch/destructive codebase migration matches the score-5 anchor with feedback loops and a checklist.	5 / 5
Progressive Disclosure	Well-organized into clearly signaled, cross-referenced sections (Workflow, Setup, Reading Order, Repo-Level Changes, Delegating, Hard Prohibitions, Done Condition) with no nested references and no bundle files present. It is not a 5 because the entire guide is a single monolithic file that could offload some material (e.g. the rg recipes or repo-level change catalog) into reference files, and not a 3 because structure and navigation are clearly good.	4 / 5
	Total	18 / 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 explicit, specific, and well-triggered: it states both what the skill does and when to use it with concrete package-level keywords. Its only weakness is modest breadth in enumerated actions and a few missing natural synonyms.

Suggestions

Optionally broaden the action coverage (e.g., mention handling renames, removed modules, and package consolidation) to push specificity toward 5.

Add a natural synonym or two (e.g., 'Effect-TS' or 'TypeScript') to round out trigger-term coverage.

Dimension	Reasoning	Score
Specificity	Names the domain and several concrete actions — 'migrating a codebase from Effect v3 to Effect v4, upgrading `effect` or any `@effect/*` package across the v3/v4 boundary' — with only minor gaps in coverage (e.g., it does not enumerate renames/signature changes/package consolidation). It is not a 5 because the action list is not comprehensive, and not a 3 because it lists more than 1-2 concrete actions.	4 / 5
Completeness	Explicitly answers both 'what' (migrating a codebase from Effect v3 to v4, upgrading packages) and 'when' via a concrete 'Use this skill when...' trigger clause, matching the score-5 anchor. It cannot improve toward a neighboring anchor since it already cleanly satisfies both requirements.	5 / 5
Trigger Term Quality	Strong natural keyword coverage — 'migrating', 'Effect v3', 'Effect v4', 'upgrading', `effect`, `@effect/*`, 'v3/v4 boundary' — which a user would plausibly say. It is not a 5 because a few natural synonyms/variants (e.g. 'Effect-TS', 'TypeScript') are missing, and not a 3 because coverage is clearly good rather than partial.	4 / 5
Distinctiveness Conflict Risk	A tightly scoped niche (Effect v3→v4 migration) with distinct package-level triggers and minimal overlap with any other skill. It clearly matches the score-5 'clear niche with distinct triggers' anchor rather than the more generic score-4 anchor.	5 / 5
	Total	18 / 20 Passed

Validation

100%

Warnings & errors only

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: xchromo/osn
Path: .agents/skills/effect-v3-to-v4/SKILL.md
Commit: 7a77cbd

Reviewed: 1 day ago

Table of Contents

Discovery Implementation Validation

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.