Content
76%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 highly actionable with concrete search queries, a scoring rubric, and complete templates, but the batch workflow lacks explicit validation checkpoints, and the long email/output blocks could be split into reference files for cleaner progressive disclosure.
Suggestions
Add explicit validation steps in the batch workflow — e.g., after Phase 1 research, verify each account's contact email is still valid and confirm at least one change signal before scoring; after Phase 3, confirm sequences are populated for every High Priority account before saving.
Move the full email templates and output-format spec into reference files (e.g., references/email-templates.md and references/output-format.md) and link to them from the body to improve progressive disclosure.
Tighten the opening prose and remove parenthetical restatements to reduce token overhead.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | Dense and actionable with minimal padding, though the opening prose and several parenthetical asides ('Too recent = too soon. Too old = too stale.') could be trimmed. | 4 / 5 |
Actionability | Provides copy-paste-ready search query templates, a concrete scoring formula with numeric anchors, full email templates, and a complete output-format spec covering common cases. | 5 / 5 |
Workflow Clarity | Phases 0–4 are clearly sequenced, but this batch operation across multiple accounts lacks explicit validation/verification checkpoints (e.g., confirm research findings, verify contact emails before sequencing), capping it at 3. | 3 / 5 |
Progressive Disclosure | No bundle files exist; the single document is well-organized with clear section headers, though the lengthy email templates and output format could arguably live in separate reference files. | 4 / 5 |
Total | 16 / 20 Passed |