Skill Crossroads — skills_

Skill Crossroads skills__007
rubric v1.2 · deterministic

overall

Correctness & Structure 57 1 fail

Triggering & Discoverability 85 1 warn

Clarity & Instructions 100 pass

Token & Context Cost 100 pass

Safety & Security 100 pass

Verifiability & Maintainability 53 1 fail

Top fixes — ranked by score impact

✗ STRUCT-05 Supporting-file references resolve

SKILL.md:15references `references/detailed-guide.md` → no such file or directory in the skill

Reference to `references/detailed-guide.md` does not resolve to a file in the skill directory.

references/detailed-guide.md

Fix Add the missing file(s), fix the path, or remove the dead reference.

✗ 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-03 Invocation cues in the description

SKILL.md:1description will match user requests → no explicit cue ('use when …', 'triggers on …', quoted user phrases) found

Pure what-it-does prose — the model has to guess when to invoke it.

Security audit, hardening, threat modeling (STRIDE/PASTA), Red/Blue Team, OWA…

Fix State the trigger explicitly: 'Use when the user says "…", "…", or wants to …'.

⚠ STRUCT-02 Recommended fields present

SKILL.md:1

`description` present, but no `name` field — the skill falls back to its directory name.

Fix Add an explicit `name` field so the skill's identity does not depend on its folder name.

★ scores higher than ≈11% 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/ranbot-ai/awesome-skills/skills/007.svg)](https://skillcrossroads.com/s/ranbot-ai/awesome-skills/skills/007)

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