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

76%

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 ./.claude/skills/railway-automation/SKILL.md

The canonical home for this skill is railway-automation in fernandezbaptiste/Skrillz

SKILL.md
Quality
Evals
Security

Quality

Content

67%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-organized, highly actionable overview with concrete Railway CLI guidance, explicit validation/rollback patterns, and clearly signaled one-level-deep references. Main weaknesses are verbosity from repeated near-identical YAML examples and generic best-practice bullets, two dangling template references, and a quick-start snippet that is not runnable as-is.

Suggestions

Trim the repeated `railway/deploy@v1` YAML blocks into one canonical example plus a per-variation note, and cut or move the generic Best Practices bullets (security/monitoring advice Claude already knows) into a reference file.

Fix the dangling references: either add the missing `templates/github-workflow.yml` and `templates/gitlab-ci.yml` files or remove the two 'Template: See ...' pointers and the Templates section.

Make the GitHub Actions quick start a complete, runnable workflow (with `on:` and `jobs:<id>:steps:` context) and replace the `webhookCreate(input: {...})` pseudocode with a concrete GraphQL mutation or a link to where the full mutation is documented.

DimensionReasoningScore

Conciseness

The body is efficient in places (Railway CLI commands Claude would not know), but includes padding Claude already knows — generic best-practice bullets like "Never commit tokens to git", "Run tests before deploy", "Log all deployments" — and repeats near-identical `railway/deploy@v1` YAML blocks six-plus times across sections. Not level 2 because most content is genuinely Railway-specific; not level 4 because the generic bullets and repetitive examples are recurring, not isolated.

3 / 5

Actionability

Mostly executable guidance: concrete commands throughout (`railway up --service api`, `railway status --json | jq -r '.url'`, `./scripts/migrate.sh --from heroku --project myapp`), plus complete troubleshooting and token workflows. Not level 5 because the flagship GitHub Actions quick start is a bare `- uses:` step with no `on:`/`jobs:` wrapper (not runnable as-is), and the webhook API example contains literal pseudocode (`webhookCreate(input: {...})`); not level 3 because pseudocode and fragments are the exception, not the rule.

4 / 5

Workflow Clarity

Numbered setup sequences for both GitHub Actions and GitLab CI, explicit validation patterns (health-check-after-deploy, rollback on `failure()`), a `--dry-run` flag for migration, and a troubleshooting section with diagnosis commands. Not level 5 because the numbered setup steps end without verification checkpoints and migration verification is only named as a script feature, not shown; clearly above level 3, whose defining gap is missing or implicit checkpoints.

4 / 5

Progressive Disclosure

Good structure with clear sections and well-signaled, one-level-deep references ("**Reference**: `references/github-actions.md` for complete guide"), and the three referenced reference files and `scripts/migrate.sh` all exist in the bundle. Not level 5 because `templates/github-workflow.yml` and `templates/gitlab-ci.yml` are referenced twice but do not exist in the bundle (dangling navigation), and substantial content (webhook handler code, three-platform token instructions, best practices) is inlined that belongs in reference files.

4 / 5

Total

15

/

20

Passed

Description

75%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, third-person description with an explicit 'Use when...' clause and concrete, natural trigger terms covering the two major CI platforms and migration. It could reach top marks by enumerating its capabilities in the 'what' half and covering more of its actual scope (scheduled tasks, webhooks, token management).

DimensionReasoningScore

Specificity

The description lists several concrete capabilities — "setting up GitHub Actions, GitLab CI, automated deployments, migration scripts, or programmatic Railway workflows" — going beyond the 1-2 actions of the level-3 anchor. It falls short of level 5 because notable parts of the skill's actual scope (scheduled tasks, webhooks, token management, health-check monitoring) are absent from the description.

4 / 5

Completeness

Both questions are answered: what ("Railway CI/CD integration and automation") and an explicit when ("Use when setting up GitHub Actions, GitLab CI, automated deployments, migration scripts, or programmatic Railway workflows") with concrete trigger phrases. Not level 5 because the 'what' is a high-level domain label while the concrete actions appear only in the 'when' clause; comfortably above level 3, which requires a missing or weakly implied 'when'.

4 / 5

Trigger Term Quality

Natural trigger phrases users would actually say are present: "GitHub Actions", "GitLab CI", "automated deployments", "migration scripts", "programmatic Railway workflows". Not level 5 because common synonyms and variations like "CI/CD pipeline", "continuous integration", "deploy on push", or "Railway CLI" are missing; not level 3 because coverage clearly exceeds a couple of generic keywords.

4 / 5

Distinctiveness Conflict Risk

The Railway brand anchors a clear niche, and the CI-platform triggers are specific. Not level 5 because "automated deployments" and "migration scripts" overlap with closely related sibling skills (the body itself lists railway-deployment and railway-database as related skills); not level 3 because it is far more distinct than a generic 'works with deployment files' description.

4 / 5

Total

16

/

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

.claude/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.