Tessl • The management layer for AI agent skills

SkillPublic

rails-dev

Opinionated Rails conventions: rich models, concerns, CRUD-everything, state-as-records, minimal dependencies, Minitest with fixtures. Load this skill BEFORE any code-level thinking, not only before editing a file. It is required the moment a task touches Rails code in ANY way: designing or even just discussing a data model, schema, migration, entity, association, field, validation, class, or method name; writing, planning, reviewing, analyzing, testing, debugging, or refactoring; or proposing any model, table, column, route, or code snippet inline in chat. If you are about to name a model or sketch a column you are already in scope, even in an exploratory back-and-forth where no file is written yet. Do not let a "we're just discussing" framing defer it. Do NOT use for non-Rails backends, NestJS, or general architecture (use nestjs-modular-monolith or coding-guidelines).

Quality

92%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Low

Low-risk findings worth noting

Quality

Content

86%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 well-structured conventions skill: lean overview, highly actionable Don't/Do code examples, and a clean one-level reference table that keeps the body short while routing detail to 24 verified reference files. Minor conciseness trim possible in the reference-selection preamble.

Suggestions

Tighten the Reference Selection preamble — the "guessing from the codebase is how the wrong convention gets shipped" sentence restates the prior point and can be cut without losing the directive.

Add one explicit checkpoint in the reference-loading flow (e.g. "after reading the reference, confirm the planned approach matches it before writing") to nudge workflow_clarity from 4 to 5.

Dimension	Reasoning	Score
Conciseness	Mostly lean with terse bullets and tight Don't/Do code pairs that assume Rails knowledge, but the Reference Selection paragraph ("This table is an index, not the content ... guessing from the codebase is how the wrong convention gets shipped") is somewhat preachy and could be trimmed.	4 / 5
Actionability	Every coding-style rule ships a complete, executable Ruby Don't/Do pair (conditionals, method order, visibility, bang methods, naming, comments, errors) — copy-paste ready and covering the common cases.	5 / 5
Workflow Clarity	The reference-loading protocol is clear (match task to table row, read that file end-to-end before designing/writing/reviewing) but there are no explicit validation checkpoints; acceptable since this is a conventions skill with no destructive or batch operations.	4 / 5
Progressive Disclosure	SKILL.md is a clean overview/index: a task-to-file table points to 24 one-level-deep reference files (all verified present), with only genuinely cross-cutting coding style kept inline — textbook progressive disclosure.	5 / 5
	Total	18 / 20 Passed

Description

95%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 strong, highly specific description that names the domain, enumerates concrete conventions, gives exhaustive trigger conditions, and explicitly fence-lines against conflicting skills. The only minor gap is that the listed items are conventions rather than discrete user-facing actions.

Dimension	Reasoning	Score
Specificity	Lists several concrete conventions ("rich models, concerns, CRUD-everything, state-as-records, minimal dependencies, Minitest with fixtures") but these are principles/scope markers rather than discrete executable actions, so it sits just below the comprehensive-actions anchor at 5.	4 / 5
Completeness	Explicitly answers both what ("Opinionated Rails conventions: ...") and when ("required the moment a task touches Rails code in ANY way: designing or even just discussing a data model ... writing, planning, reviewing, analyzing, testing, debugging, or refactoring") with concrete trigger phrases.	5 / 5
Trigger Term Quality	Comprehensive natural-term coverage with synonyms a user would actually say — "Rails", "data model", "schema", "migration", "entity", "association", "field", "validation", "table", "column", "route", "testing", "debugging", "refactoring", "Minitest", "fixtures".	5 / 5
Distinctiveness Conflict Risk	Clear Rails niche with explicit disambiguation — "Do NOT use for non-Rails backends, NestJS, or general architecture (use nestjs-modular-monolith or coding-guidelines)" — minimizing overlap with sibling skills.	5 / 5
	Total	19 / 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: tech-leads-club/agent-skills
Path: packages/skills-catalog/skills/(development)/rails-dev/SKILL.md
Revision: 1da2195

Reviewed: 1 month ago

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.

rails-dev

Table of Contents

Is this your skill?