Content
42%Weight 40%Scale 1-5Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
The domain content — structure percentages, STAR framing, the AMCAS/ERAS character-limit table, and cliché pitfalls — is genuinely useful, but it is buried in generic template padding and undermined by a Quick Start that imports an API which does not exist in the bundle. The shipped `scripts/main.py` exposes a completely different, far shallower interface than the documented one, and the main examples reference is a missing file.
Suggestions
Make the code examples match the bundle: either implement `PersonalStatementWriter` with `write/create_outline/frame_experience/optimize_length/adjust_tone` in `scripts/main.py`, or rewrite the Quick Start around the actual `PersonalStatement.generate()` API.
Delete the template boilerplate sections ('Implementation Details', 'Audit-Ready Commands', 'Output Requirements', 'Input Validation', 'Response Template') and the duplicated description text in 'When to Use'/'Key Features'; keep only the domain-specific material to fix conciseness.
Fix the broken reference: either add `references/personal-statement-examples.md` with the promised example categories or point 'Common Patterns' at the existing `references/guidelines.md`, and give that file real content instead of a two-bullet stub.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | Roughly half the body is generic template filler — 'When to Use' restates the description verbatim twice ('Use this skill when the task needs Use when writing medical school personal statements...'), and 'Implementation Details', 'Audit-Ready Commands', 'Output Requirements', 'Input Validation', and 'Response Template' contain boilerplate that adds nothing specific to this skill. The same py_compile command also appears three times. This matches anchor 2 ('several unnecessary explanations or padded sections') rather than anchor 3's single instance of excess. | 2 / 5 |
Actionability | The body offers concrete-looking guidance (character limit table, STAR method, cliché examples, a runnable py_compile command), but the centerpiece Quick Start and capability snippets call a `PersonalStatementWriter` class with methods like `write()` and `optimize_length()` that do not exist — the actual bundle's `scripts/main.py` defines `PersonalStatement.generate()` with a different signature. Per the rubric's code-example rule these are effectively non-executable against the shipped code, matching anchor 3 ('missing key details / not actually executable') and not anchor 4. | 3 / 5 |
Workflow Clarity | Two competing execution paths are presented — the nonexistent `scripts/personal_statement_writer` API and `scripts/main.py` (whose only invocation shown is a no-argument demo run) — with no reconciliation, and 'See `## Workflow` above for related details' is a circular pointer. A validation step exists (`python -m py_compile scripts/main.py`) but no feedback loop connects the two paths, matching anchor 3 ('sequence present but checkpoints missing or implicit') rather than anchor 4's coherent, mostly-checkpointed sequence. | 3 / 5 |
Progressive Disclosure | The body has section structure and points to `references/`, but the referenced `references/personal-statement-examples.md` ('See references/personal-statement-examples.md for: Medical School (MD/DO) Examples...') does not exist in the bundle — only a two-bullet stub `references/guidelines.md` is present — so the primary reference is broken, and ~90 lines of template boilerplate sit inline in SKILL.md instead of being trimmed or split. This matches anchor 3 ('references present but not clearly signaled; content that should be separate is inline'); it avoids anchor 2 only because headers and a one-level-deep reference intent exist. | 3 / 5 |
Total | 11 / 20 Passed |