Content
55%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.
A token-efficient, well-sectioned skeleton that documents command syntax and input format clearly, but it delegates all real work to a script that is never explained and whose referenced path does not exist in the bundle. Without an invocation example, output description, or workflow steps, the skill is not currently executable end-to-end.
Suggestions
Fix the referenced paths to bundle-relative locations that actually exist (e.g. scripts/competitive_matrix_builder.py) instead of 'product-team/skills/competitive-teardown/...' paths that are absent from the bundle.
Add an executable invocation example for the script with its arguments (e.g. 'python scripts/competitive_matrix_builder.py competitors.json --weights pricing=2,ux=1.5 --format json') and describe its output format.
Add a minimal workflow sequence: validate the input against the format above, run the builder, then interpret/present the matrix and gap analysis — including what to do on invalid or missing dimensions.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The body is lean with zero padding: every section (Usage, Input Format, Examples, Scripts) carries only operational information and assumes Claude's competence, explaining no background concepts. This matches the 'every token earns its place' anchor; there is nothing to trim. | 5 / 5 |
Actionability | Concrete elements exist (command syntax, a complete input JSON schema, example invocations with options like --weights pricing=2,ux=1.5), but key execution details are missing: the Scripts section lists 'competitive_matrix_builder.py — Matrix builder' with no invocation example, no argument documentation, and no description of the output. This fits the 'some concrete guidance but incomplete, missing key details' anchor rather than the mostly-executable anchor above. | 3 / 5 |
Workflow Clarity | No explicit sequence is given — only an implicit 'prepare competitors.json, run the command' flow. The script's role in the workflow is undefined, there are no steps for interpreting or validating output, and no input validation is described, matching the 'rough sequence present but many gaps; steps poorly defined; validation absent' anchor. The simple-skill exception does not apply because the single action is not unambiguous: how the command maps to script execution is never stated. | 2 / 5 |
Progressive Disclosure | The body references 'product-team/skills/competitive-teardown/scripts/competitive_matrix_builder.py' and 'product-team/skills/competitive-teardown/SKILL.md', but no scripts/, references/, or assets/ directories exist in this bundle — both referenced paths are broken and use repo-style paths rather than bundle-relative ones. Scored against the actual bundle structure, the references are unusable and effectively buried, matching the 'references are buried' anchor; the in-body sections alone are too thin to carry the skill. | 2 / 5 |
Total | 12 / 20 Passed |