Skill Crossroads 0codekit
rubric v1.2 · deterministic
B+ 87.6/100 overall
Correctness & Structure 100 pass
Triggering & Discoverability 88 1 warn
Clarity & Instructions 100 pass
Token & Context Cost 66 1 fail
Safety & Security 100 pass
Verifiability & Maintainability 53 1 fail

Top fixes — ranked by score impact

✗ TOKEN-01 Body under line/token budget
SKILL.md500-line guidance → 1445 lines
SKILL.md is 1445 lines — over the ~500-line guidance. ~10,006 tokens (rough est.); ~$0.0300 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.
✗ 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.
⚠ TRIGGER-02 Description long enough to anchor invocation
SKILL.md:1description will trigger invocation → 96 chars — under the ~100-char reliable-trigger band
Description is thin — likely under-specifies when to invoke.
0codekit integration. Manage Workspaces. Use when the user wants to interact …
Fix Add the concrete use case and user phrasing (e.g. 'Use when the user says …').
⚠ TOKEN-02 Progressive disclosure
SKILL.mdeverything inlined in SKILL.md → 1432 body lines, 0 supporting files
Large SKILL.md (1432 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 → ~10,006 tokens (rough est.) per invocation
Every invocation carries this: ~10,006 tokens (rough est.) per invocation — ~$30.02 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 ≈18% of 208 public skills (deterministic rubric v1.2 sample, 2026-09)

Embed this badge

Skill Crossroads grade B+ Always-fresh — it re-scans and updates on its own. 
[![Skill Crossroads](https://skillcrossroads.com/api/badge/membranedev/application-skills/skills/0codekit.svg)](https://skillcrossroads.com/s/membranedev/application-skills/skills/0codekit)
Grade your own Claude Code skill — evidence-cited, file-and-line, free. Scan your own skill →