Skill Crossroads — database-design

Skill Crossroads database-design
rubric v1.2 · deterministic

overall

Correctness & Structure 100 pass

Triggering & Discoverability 100 pass

Clarity & Instructions 100 pass

Token & Context Cost 77 3 warn

Safety & Security 64 1 fail

Verifiability & Maintainability 53 1 fail

Top fixes — ranked by score impact

✗ SAFETY-01 No hardcoded secrets

skill.md:622— → matches Connection string with password pattern

Possible hardcoded secret (Connection string with password) — post*****************s@

post*****************s@

Fix Remove the secret from source, rotate it, and reference it via an environment variable instead.

✗ VERIFY-01 Evals or tests present

skill.md:1the skill works → no evals/, tests/, or verification section found

No way to prove the skill does what it claims.

Fix Add an evals/ folder (test prompts + expected outcomes) and a '## Verify' step in the body.

⚠ SAFETY-03 No destructive auto-invocation

skill.md:44auto-invocable (no disable-model-invocation) → performs a destructive action ("DELETE")

Skill appears to "DELETE" but the model can auto-invoke it — a destructive action could fire without the user asking.

DELETE

Fix If this action is destructive/irreversible, set `disable-model-invocation: true` so it only runs when explicitly invoked.

⚠ TOKEN-01 Body under line/token budget

skill.md500-line guidance → 706 lines

SKILL.md is 706 lines — over the ~500-line guidance. ~8,116 tokens (rough est.); ~$0.0243 per load at $3/Mtok reference rate.

Fix Move heavy reference material into supporting files and link to them (progressive disclosure), keeping SKILL.md lean.

⚠ TOKEN-02 Progressive disclosure

skill.mdeverything inlined in SKILL.md → 702 body lines, 0 supporting files

Large SKILL.md (702 lines) with no supporting files — all of it loads every time the skill fires.

Fix Move heavy reference material into supporting files and link to them, so the model loads it only when needed.

⚠ TOKEN-04 Recurring per-invocation cost

skill.mda one-time authoring cost → ~8,116 tokens (rough est.) per invocation

Every invocation carries this: ~8,116 tokens (rough est.) per invocation — ~$24.35 per 1,000 invocations at the $3/Mtok reference rate.

Fix Cut the entry file below ~8k tokens — move reference material into supporting files so every future invocation gets cheaper.

★ scores higher than ≈16% of 208 public skills (deterministic rubric v1.2 sample, 2026-09)

Embed this badge

Always-fresh — it re-scans and updates on its own.

[![Skill Crossroads](https://skillcrossroads.com/api/badge/kid-sid/claude-spellbook/skills/database-design.svg)](https://skillcrossroads.com/s/kid-sid/claude-spellbook/skills/database-design)

Grade your own Claude Code skill — evidence-cited, file-and-line, free. Scan your own skill →