deployment-guide

Complete deployment guide for Dr. Sophia AI on Railway. Covers environment-aware build system, frontend dist/ compilation, backend auto-deploy, Railway configuration, troubleshooting build/deployment issues. Use when deploying to Railway, building frontend for production, debugging deployment failures, or setting up environment variables.

Quality

77%

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

Fix and improve this skill with Tessl

tessl review fix ./skill-builder-package/examples/deployment-guide/SKILL.md

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.

The body is highly actionable with well-sequenced deployment workflows and verification steps, but it is held back by duplicative sections that waste tokens and—more seriously—by two broken reference-file links that undermine the progressive-disclosure structure.

Suggestions

Create the missing referenced files references/build-troubleshooting.md and references/railway-config.md, or remove the broken links from the 'Detailed Documentation' section.

Remove the redundant 'Keywords' line and 'Overview' paragraph (they restate the frontmatter description) and collapse the 'Quick Reference' build commands that duplicate Step 2.

Add an explicit validate→fix→retry feedback loop inline in the frontend workflow (e.g., 'If CSS is ~9KB, Tailwind failed — re-run npm run build before committing') rather than relying only on the separate failures table.

Dimension	Reasoning	Score
Conciseness	The bulk is actionable commands and checklists, but several sections pad the token budget: a 'Keywords' line that duplicates trigger matching, an 'Overview' that restates the frontmatter description, and a 'Quick Reference' that repeats the build commands already shown in Step 2. Not a 4 because these duplicative sections are noticeable rather than minor.	3 / 5
Actionability	Fully executable, copy-paste-ready guidance throughout — 'cd frontend; npm run build', 'ls -lh dist/assets/*.css', 'git add -A', 'git push origin dev', 'BUILD_ENV=production npm run build', and a curl health check — with concrete verification targets (~60KB CSS, ~450KB JS) covering the common cases.	5 / 5
Workflow Clarity	Frontend (Step 1-4) and backend (Step 1-2) processes are clearly sequenced with an inline 'Verify Build' checkpoint (Step 3) and a post-deploy verification script, plus checklists. Not a 5 because the error-recovery feedback loop lives in a separate 'Common Deployment Failures' table rather than as an explicit validate→fix→retry loop inline in the workflow.	4 / 5
Progressive Disclosure	References are clearly signaled and one level deep, but 2 of the 3 referenced files do not exist in the bundle — 'references/build-troubleshooting.md' and 'references/railway-config.md' are missing — so navigation is broken, and the environment URL table is inlined while also pointing to environment-config.md. Broken reference paths make this fall below the 'references present but not clearly signaled' anchor.	2 / 5
	Total	14 / 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.

A strong, third-person description that clearly states both what the skill does and when to use it, with natural trigger phrases and a distinct project-scoped niche. Minor gains are possible by adding a few more synonyms/tool tokens.

Dimension	Reasoning	Score
Specificity	Lists several concrete capabilities — 'environment-aware build system, frontend dist/ compilation, backend auto-deploy, Railway configuration, troubleshooting build/deployment issues' — with only minor coverage gaps (e.g., env var setup is named but not detailed). Not a 5 because a couple of named areas (Railway configuration) are broad rather than fully concrete actions.	4 / 5
Completeness	Explicitly answers both: 'what' ('Complete deployment guide for Dr. Sophia AI on Railway. Covers environment-aware build system, frontend dist/ compilation, backend auto-deploy...') and 'when' ('Use when deploying to Railway, building frontend for production, debugging deployment failures, or setting up environment variables.') with concrete trigger phrases.	5 / 5
Trigger Term Quality	Natural user phrases are present — 'deploying to Railway', 'building frontend for production', 'debugging deployment failures', 'setting up environment variables' — which a user would actually say. Not a 5 because synonyms and tool-specific tokens (e.g., 'dist folder', 'npm run build', 'Railway build logs') are thinner than the comprehensive anchor.	4 / 5
Distinctiveness Conflict Risk	Scoped to a named project on a named platform ('Dr. Sophia AI on Railway') with Railway-specific triggers, giving it a clear niche and minimal overlap risk with generic skills.	5 / 5
	Total	18 / 20 Passed

Validation

87%

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 — 14 / 16 Passed

Validation for skill structure

Criteria	Description	Result
relative_links	Relative link issues: 2 missing	Warning
referenced_paths_exist	Referenced path issues: 4 missing	Warning

	Total	14 / 16 Passed

Repository: fernandezbaptiste/Skrillz
Path: skill-builder-package/examples/deployment-guide/SKILL.md
Commit: 93ed392

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.