CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

railway-automation

Railway CI/CD integration and automation. Use when setting up GitHub Actions, GitLab CI, automated deployments, migration scripts, or programmatic Railway workflows.

Quality

72%

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

Fix and improve this skill with Tessl

tessl review fix ./skills/railway-automation/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

63%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 highly actionable, well-sectioned body with real executable code, explicit health-check/rollback validation, and genuinely useful one-level-deep references. The two main defects are a missing templates/ directory leaving two prominent references dangling, and length — several full workflow examples are inlined that the reference files already cover.

Suggestions

Either add the templates/ directory with github-workflow.yml and gitlab-ci.yml, or remove the four references to it and rely on the existing references/ files.

Cut the Scheduled Tasks section to one representative YAML plus a pointer to references/github-actions.md, and collapse the four 'Common Patterns' examples to short snippets — the reference files already contain the full versions.

Replace the GraphQL placeholder 'webhookCreate(input: {...})' with a complete mutation and fix '$YOUR_TOKEN' to '${YOUR_TOKEN}' so every example is copy-paste runnable.

DimensionReasoningScore

Conciseness

The body avoids teaching known concepts and almost everything is commands or config, but ~540 lines include substantial duplication: Quick Start snippets repeated by sections 1–2, three full scheduled-task YAML workflows where one pattern suffices, four full 'Common Patterns' workflows, and generic best-practice bullets ('Run tests before deploy', 'Monitor deployment notifications') Claude already knows. This matches 'mostly efficient but could be tightened' better than the padded anchor 2, since there is no conceptual filler.

3 / 5

Actionability

Nearly everything is copy-paste executable: CLI commands, full YAML workflows, health-check and rollback snippets. Minor gaps keep it from 5: the GraphQL example is a placeholder ('webhookCreate(input: {...})'), and 'export RAILWAY_TOKEN=$YOUR_TOKEN' is not valid shell for the intended substitution.

4 / 5

Workflow Clarity

Setup processes are numbered with a final verification step ('Test with PR or push'), and deploy workflows include explicit validation feedback loops (health check → 'Rollback on failure' via if: failure(); migration supports --dry-run and 'Verification checks'). Not 5 because the migration section delegates to the script's feature list without a sequenced checkpoint workflow of its own.

4 / 5

Progressive Disclosure

Scored against the actual bundle: references/github-actions.md, references/gitlab-ci.md, references/migration-patterns.md, and scripts/migrate.sh all exist, are referenced one level deep with clear signals — good structure. However, the body points to templates/github-workflow.yml and templates/gitlab-ci.yml (twice each, including a dedicated Templates section) and no templates/ directory exists in the bundle, so those navigation paths dead-end; combined with full workflow examples inlined that duplicate the reference files, structure is better than anchor-2's monolith but falls short of the 'minor organization gaps' anchor 4.

3 / 5

Total

14

/

20

Passed

Description

70%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 solid description with an explicit, concrete 'Use when…' trigger clause and a clearly named niche. Its main weakness is the capability half, which relies on generic abstractions ('integration and automation') instead of enumerating what the skill actually does.

Suggestions

Replace the generic 'Railway CI/CD integration and automation' with concrete actions, e.g. 'Set up GitHub Actions and GitLab CI pipelines for Railway deploys, run automated migrations from Heroku/Vercel/Render, and configure webhooks and scheduled tasks.'

Add the migration source platforms (Heroku, Vercel, Render) and terms like 'continuous deployment' to the trigger list so migration and generic CD requests match naturally.

DimensionReasoningScore

Specificity

The 'what' clause is generic — 'Railway CI/CD integration and automation' names the domain but the actions ('integration', 'automation') are abstract nouns rather than concrete verbs like 'set up GitHub Actions workflows' or 'migrate Heroku apps'. Concrete capability detail only appears indirectly through the when-clause's list, so this sits between the 'minimal or generic actions' anchor (2) and 'domain plus 1-2 concrete actions' (3); it earns 3 because the domain is sharply named and the trigger list implies the real capabilities.

3 / 5

Completeness

Both halves are present: 'Railway CI/CD integration and automation' states what it does, and an explicit 'Use when setting up…' clause with concrete triggers states when. Not 5 because the 'what' half is buzzword-level ('integration and automation') where the anchor-5 example lists concrete actions (extract text, fill forms, merge documents); not 3 because the trigger clause is explicit and specific rather than weakly implied.

4 / 5

Trigger Term Quality

'Use when setting up GitHub Actions, GitLab CI, automated deployments, migration scripts, or programmatic Railway workflows' contains natural phrases users would say, matching the 'good keyword coverage; a few natural terms missing' anchor. Not 5 because common variations like 'continuous deployment', 'CI pipeline', 'Heroku/Render migration', or 'deploy from CI' are absent.

4 / 5

Distinctiveness Conflict Risk

The Railway branding plus CI/CD scope carves a clear niche with distinct triggers, matching 'mostly distinct; minor overlap risk'. Not 5 because the when-clause's leading triggers ('setting up GitHub Actions', 'automated deployments') could fire for generic CI/CD or sibling skills (e.g., a railway-deployment skill) before 'Railway' disambiguates.

4 / 5

Total

15

/

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

skill_md_line_count

SKILL.md is long (543 lines); consider splitting into references/ and linking

Warning

Total

15

/

16

Passed

Repository

fernandezbaptiste/Skrillz

Path

skills/railway-automation/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.