Content
100%Weight 40%Scale 1-3Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
A high-quality instruction skill: densely directive, concrete in its thresholds and structures, and sequenced as a clear six-phase workflow with verification and error-handling checkpoints. It is self-contained and well-organized with no concept padding or unnecessary file indirection.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | Lean, directive prose with no basic-concept explanations (no 'what a sitemap is' or 'how libraries work' padding). Sentences are behavioral guardrails that earn their place; it assumes Claude's competence rather than over-explaining, matching the score-3 anchor. | 3 / 3 |
Actionability | Concrete, executable guidance throughout: a visited-set/queue frontier with a 40-page cap, specific URL probes (sitemap.xml, llms.txt), prioritization keywords, and exact output requirements (5–8 symbols, 3–6 gotchas, exact setup/run commands). Per the instruction-only carve-out, absence of code is not penalized because the guidance is highly actionable. | 3 / 3 |
Workflow Clarity | A clearly sequenced six-phase process with explicit verification checkpoints: ask for the URL if missing before starting, verify API calls against the docs rather than memory, report pages crawled and any cap-truncation, and flag inferred parts when docs are thin. These feedback loops satisfy the batch-operation validation requirement, so it is not capped at 2. | 3 / 3 |
Progressive Disclosure | No bundle files exist and the body references only external web resources (sitemap.xml, llms.txt), not nested local files. Content is a self-contained workflow broken into well-signaled phase headers with no monolithic wall of text and nothing that should be split out, matching the well-organized-sections standard for a 3. | 3 / 3 |
Total | 12 / 12 Passed |