Content
77%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
A comprehensive, highly actionable solo-founder GTM playbook with clear sequenced workflows and concrete reference data. Its main weaknesses are length/framing prose and a monolithic single-file structure with no progressive disclosure into separate reference files.
Suggestions
Trim non-actionable framing prose (the 'You are an expert' persona opening and the 'Taste as Moat' philosophy narrative) to tighten conciseness, keeping the concrete DELEGATE/OWN table.
Split the large reference material — the tool stack table, AI agent team definitions, and revenue-stage playbook — into separate one-level-deep files (e.g. STACK.md, AGENTS.md, STAGES.md) referenced from a lean SKILL.md overview to improve progressive disclosure.
Remove or consolidate the Quick Reference table where it merely restates numbers already present in the body sections to avoid redundant context cost.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | Mostly efficient and table-driven with concrete data, but the ~500-line body carries framing/persona prose ('You are an expert...,' the 'Taste as Moat' philosophy) and a Quick Reference table that restates figures already in the body, so not every token earns its place. | 2 / 3 |
Actionability | Highly concrete, copy-paste-ready guidance for an instruction skill: named tools with monthly costs, per-stage time splits, agent definitions with workflows/time saved, decision tables, sales-velocity targets, a 15-item question bank, and worked Examples. | 3 / 3 |
Workflow Clarity | Processes are clearly sequenced with checkpoints and guardrails: the Before-Starting context checklist, MRR-stage playbook with explicit 'Skip' lists, ordered agent deploy priority, and the QUALIFY→DISCOVER→DEMO→CLOSE→ONBOARD flow with branch logic ('No: politely decline'). | 3 / 3 |
Progressive Disclosure | Well-organized into numbered sections with a Quick Reference and a cross-skill Related Skills table, but everything is inline in a single large file with no bundle references; the content (detailed stack/agent/stage reference) is not split across one-level-deep files, and the <50-line simple-skill exception does not apply. | 2 / 3 |
Total | 10 / 12 Passed |