Skill Crossroads — skills__analytics-tracking

Skill Crossroads skills__analytics-tracking
rubric v1.2 · deterministic

overall

Correctness & Structure 33 2 fail

Triggering & Discoverability 33 2 fail

Clarity & Instructions 100 pass

Token & Context Cost 91 1 warn

Safety & Security 100 pass

Verifiability & Maintainability 80 1 warn

Top fixes — ranked by score impact

✗ STRUCT-01 Valid YAML frontmatter

SKILL.md:1— → YAML parser rejected the frontmatter block

Frontmatter failed to parse: All mapping items must start at the same column at line 3, column 1: description: ">" Design, audit, and improve analytics tracking systems that produce reliable, ^

Fix Fix the YAML so it is a valid `key: value` mapping between the opening and closing `---` fences.

✗ STRUCT-02 Recommended fields present

SKILL.md:1

No frontmatter to read fields from (see STRUCT-01).

Fix Add frontmatter with a `description` field.

✗ TRIGGER-02 Description long enough to anchor invocation

SKILL.md:1

No description — nothing for the model to match against.

Fix Add a description that leads with the use case and the phrases a user would say.

✗ TRIGGER-03 Invocation cues in the description

SKILL.md:1

No description — no invocation cues possible.

Fix Add a description with explicit cues: 'Use when …' plus the phrases a user would say.

⚠ TOKEN-02 Progressive disclosure

SKILL.mdeverything inlined in SKILL.md → 404 body lines, 0 supporting files

Large SKILL.md (404 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.

⚠ VERIFY-01 Evals or tests present

SKILL.md:326the skill can be verified → a prose verification step, but no runnable evals/ or tests/

Manual verification only — add eval prompts with expected outcomes to make it checkable.

## Validation

Fix Add an evals/ folder with 2–3 test prompts and the expected assertions.

★ scores higher than ≈3% 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/rootcastleco/rei-skills/skills/analytics-tracking.svg)](https://skillcrossroads.com/s/rootcastleco/rei-skills/skills/analytics-tracking)

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