CtrlK
BlogDocsLog inGet started
Tessl Logo
PluginPublic

testland/atlas-migrations

Use for any question or task about Atlas or declarative, Terraform-style database schema management, including how it compares with Flyway and Liquibase: Atlas schema apply, migrate diff against a dev database, migrate lint for destructive or locking changes, and migrate hash, across a dozen databases.

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

Overview
Quality
Evals
Security
Files

Quality

Content

92%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 operational skill: fully executable commands at every step, an explicit lint/validate gate with feedback loops before any apply, and clean offloading of HCL details and caveats to genuine one-level reference files. The only visible improvement is trimming repeated source citations and the brief security editorializing in Step 1.

DimensionReasoningScore

Conciseness

The body is efficient and command-dominated - it assumes competence and adds only Atlas-specific knowledge (dev-url scratch-DB semantics, atlas.sum tamper guard, analyzer codes). Minor trimmable spots keep it below the lean anchor: the 'Per [at-start][at-start]' citation is repeated four times, and the install-script security aside ('runs unreviewed remote code') slightly over-explains a practice Claude already knows.

4 / 5

Actionability

Every step ships copy-paste-ready commands with full flags and env vars - brew/docker install, 'atlas schema apply --url ... --to file://schema.sql --dev-url ...', migrate diff/validate/lint/apply with --dry-run, the atlas.hcl lint config, and a complete CI YAML snippet. The worked example traces a realistic NOT NULL column addition end-to-end, covering the common cases the rubric's top anchor asks for.

5 / 5

Workflow Clarity

Nine clearly sequenced steps with an explicit gate ('Lint and validate (Step 5) are the gate: nothing reaches migrate apply (Step 6) until they pass'), a fix-and-re-lint feedback loop ('Re-run atlas migrate diff/migrate hash after editing an unapplied file, then repeat step 2 until it exits 0'), and dry-run verification before the real apply. For database operations this is exactly the validate -> fix -> retry pattern the rubric requires for a top score.

5 / 5

Progressive Disclosure

The core workflow lives in SKILL.md while HCL details and the anti-patterns/limitations catalogue are split into two real, well-signaled reference files linked inline ('see [references/hcl-schema.md]', 'catalogued in [references/atlas-caveats.md]'), each one level deep with no nested-reference chains. Section headers, a step-indexed structure, and a closing references map make navigation easy, matching the clear-overview-with-well-signaled-references anchor.

5 / 5

Total

19

/

20

Passed

Description

88%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 description: it opens with an explicit use-trigger, enumerates four concrete Atlas commands with their risk context, and bounds the domain including comparison tools. The only refinements would be adding common phrasing synonyms such as 'database migrations' and sharpening the boundary against the Flyway/Liquibase sister skills.

DimensionReasoningScore

Specificity

The description lists multiple concrete, command-level actions - 'Atlas schema apply, migrate diff against a dev database, migrate lint for destructive or locking changes, and migrate hash' - comprehensively covering the skill's core commands. It exceeds the 'several specific actions with minor gaps' anchor because the action list matches the skill's actual scope (apply, diff, lint, hash) rather than sampling it.

5 / 5

Completeness

Both what and when are explicitly answered: 'Use for any question or task about Atlas or declarative, Terraform-style database schema management' is a clear trigger clause, and the colon-delimited list states the concrete capabilities. This matches the anchor for explicit what-and-when with concrete trigger phrases, and cannot be 4 since the 'when' is fully explicit rather than merely present.

5 / 5

Trigger Term Quality

Good natural keyword coverage: 'Atlas', 'Terraform-style database schema management', 'Flyway', 'Liquibase', 'destructive or locking changes' are phrases a user with this need would say. A few common variations are missing - e.g. the standalone phrase 'database migrations' or 'schema as code' - which keeps it below the comprehensive-synonyms anchor.

4 / 5

Distinctiveness Conflict Risk

The Atlas-specific niche is clear and the tool name is a distinct trigger, but explicitly claiming 'how it compares with Flyway and Liquibase' creates minor overlap risk with dedicated sister skills covering those tools. It is well above 'somewhat specific but could overlap' since the primary trigger (Atlas) is unambiguous, but not the minimal-conflict anchor.

4 / 5

Total

18

/

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.

Reviewed

On this page