Content
46%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 body is well-sectioned with a strong output contract and concrete communication rules, but it has a critical structural flaw: the core principles are delegated to a reference file that is missing from the bundle, leaving the heart of the skill empty. Additionally, large experiment-idea lists restate generic CRO knowledge at the expense of the unique specifics that presumably live in the absent playbook.
Suggestions
Ship the referenced file references/popup-cro-playbook.md (or inline the core principles into SKILL.md) — the "Core Principles" section currently points to a nonexistent file, gutting the skill's core guidance.
Trim the ~80 lines of generic experiment variants (e.g., timing delays, corner positions, button colors) down to the few non-obvious ones and move the exhaustive matrix into the playbook reference; Claude can generate the obvious permutations itself.
Make the workflow explicit: number the steps (read marketing context → assess purpose/state/traffic → propose popups per output format → deliver the five artifacts) and add a checkpoint, e.g., confirm purpose and traffic context before producing copy.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | Bullet lists are terse with no concept over-explanation, but roughly 80 lines of experiment variants ("Test optimal time delay (10s vs. 30s vs. 60s)", "Left corner vs. right corner for slide-ins", "Button color testing for contrast") restate generic CRO knowledge that an expert model already has. Mostly efficient but could be tightened — matches anchor 3, not 4, because the padding is more than minor. | 3 / 5 |
Actionability | The Output Format (Type/Trigger/Targeting/Frequency/Copy/Design notes), Communication rules ("provide headline, subhead, CTA button text, and decline text as a complete set — never partial"), and Task-Specific Questions are concrete for an instruction-only skill. However, the "Core Principles" section is empty except for a pointer to a reference file that does not exist (references/popup-cro-playbook.md), so the core how-to guidance is missing — incomplete with key details absent, matching anchor 3. | 3 / 5 |
Workflow Clarity | A rough sequence exists ("If .claude/product-marketing-context.md exists, read it before asking questions" → "Before providing recommendations, understand..." → Output Format → Output Artifacts), but sections are parallel rather than explicitly sequenced, and there are no validation checkpoints or feedback loops. This matches anchor 3 (sequence present but checkpoints missing or implicit) rather than 4. | 3 / 5 |
Progressive Disclosure | The body's only reference — "→ See references/popup-cro-playbook.md for details" — points to a file that does not exist (no references/, scripts/, or assets/ directories are present), leaving the skill's core principles as a broken pointer. Meanwhile secondary experiment-idea lists are inlined in the body, and no bundle structure exists at all — matching anchor 2 (minimal structure; content that belongs in separate files inlined / references broken) rather than 3, where references would at least exist and be organized. | 2 / 5 |
Total | 11 / 20 Passed |