Content
72%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 data-rich, highly actionable reference for startup team planning whose main problems are structural: it front-loads ~250 lines of benchmark detail that belongs in bundle files, points to reference directories that do not exist, includes boilerplate filler sections, and lacks any validation checkpoints in its workflow. The domain content itself is specific and immediately usable.
Suggestions
Create the referenced `references/` (and `examples/`) directories with the detailed compensation and equity benchmark tables, and reduce SKILL.md to an overview with clearly signaled one-level-deep links — currently the closing pointer is a dangling reference.
Remove the circular 'Use this skill when / Do not use this skill when' sections and the generic 'Instructions' section, which restate the skill's name without adding information.
Add explicit validation checkpoints to the Quick Start workflow, e.g., 'verify total comp budget stays within 70-100% of revenue for Series A' and 'confirm option pool remains 10-15% after planned allocations'.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The bulk is dense, high-value data Claude does not reliably know (2024 salary ranges, equity percentages, org charts) with almost no conceptual padding, but there are trimmable spots: the circular 'Use this skill when / Do not use this skill when' sections, the generic 'Instructions' section ('Clarify goals, constraints, and required inputs'), and the 'Rule of Thumb' line duplicating the fully-loaded cost formula. This fits anchor 4 (efficient, minor instances that could be trimmed) rather than 5; it is well above anchor 3's 'noticeably unnecessary explanation'. | 4 / 5 |
Actionability | As an instruction-only skill, the guidance is fully concrete and specific: exact dollar ranges per role and level, a worked dilution example ('$15M post-money; 15% pool = $2.25M'), a headcount budget formula with a worked '$1.1M' example, ASCII org charts, and hiring timelines with buffer rules. Specific examples cover the common cases (stage-based planning, comp, equity, budget), matching anchor 5; anchor 4's 'minor gaps' does not apply — a practitioner could execute directly from this. | 5 / 5 |
Workflow Clarity | The 'Quick Start' gives a clear 8-step sequence (identify stage → define roles → prioritize → set comp → plan timeline → calculate budget → design org chart → allocate equity), but there are no validation checkpoints anywhere — the only nod is the generic 'Apply relevant best practices and validate outcomes'. The 'Compensation as % of Revenue' section could serve as a budget sanity check but is never framed as one. This matches anchor 3 ('steps listed but validation gaps; checkpoints missing or implicit') and not anchor 4, which requires most checkpoints present; the operations are advisory, not destructive/batch, so no cap applies. | 3 / 5 |
Progressive Disclosure | Section structure is clear, but roughly 250 lines of benchmark tables (salary ranges, equity ranges, org charts) are inlined in SKILL.md when the rubric expects the file to be an overview pointing to detailed materials — and the closing pointer 'see references/ and examples/' references directories that do not exist in the bundle, so the disclosure path is broken. This matches anchor 3 ('content that should be separate is inline; references present but not clearly signaled') better than anchor 2, whose 'minimal structure' does not hold, and better than anchor 4, which requires references that actually resolve. | 3 / 5 |
Total | 15 / 20 Passed |