Content
75%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 well-structured, task-focused analysis skill: the 7-step method, exact output template, and best practices give Claude concrete, executable guidance without over-explaining known concepts, and the two-approach triangulation provides real workflow checkpoints. Remaining improvements are modest: trimming the persona/Purpose padding, adding a worked example or named data sources, and specifying what to do when top-down and bottom-up estimates diverge.
Suggestions
Remove the 'You are a strategic market analyst...' persona line and the Purpose section (it restates the frontmatter description) to tighten conciseness.
Add a brief worked mini-example of the triangulation (e.g., a 3-line top-down vs. bottom-up TAM reconciliation) or name specific data sources (Statista, IBISWorld, SEC/annual reports) to make estimates fully concrete.
Add explicit divergence handling to the analysis steps: when top-down and bottom-up estimates differ materially, re-check market boundaries and scoping assumptions before reconciling.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The body is lean and task-focused (numbered analysis steps, an output template, a summary table) with no explanation of concepts Claude already knows, but contains minor trimmable padding: the 'You are a strategic market analyst specializing in market sizing...' persona line, the Purpose section that restates the frontmatter description, and the '(Think Step by Step)' parenthetical. Not 5 because of these minor over-explanations; not 3 because there is no substantive concept over-explanation or padded prose. | 4 / 5 |
Actionability | For an instruction-only analysis skill the guidance is concrete and executable: 7 numbered analysis steps ('Top-Down Estimation: Start from total industry size and narrow to the relevant slice', 'Bottom-Up Estimation: Build from unit economics (customers × price × frequency) to cross-validate'), an exact output structure including a Market Summary Table, per-assumption confidence levels, and explicit tool direction ('Use web search to find current market data'). Not 5 because it lacks a worked mini-example or named data sources (e.g., Statista, IBISWorld, annual reports) that would make estimates concrete; not 3 because nothing is vague or pseudocode-like — every step specifies what to produce. | 4 / 5 |
Workflow Clarity | The 7-step sequence is clearly ordered and embeds explicit checkpoints: bottom-up 'to cross-validate' the top-down estimate, 'Reconciliation of the two approaches' in the output, and assumption mapping with confidence levels and 'How to validate the most uncertain assumptions'. Not 5 because there is no explicit recovery guidance for when the two approaches materially diverge (the key failure mode of this workflow). No destructive/batch cap applies — this is a read/analyze task. | 4 / 5 |
Progressive Disclosure | No bundle files exist (references/, scripts/, assets/ are absent), and the ~85-line body is appropriately self-contained: well-labeled sections (Purpose, Instructions, Output Structure, Best Practices) with a clearly signaled, one-level-deep 'Further Reading' list of external links. Not 5 because the Further Reading links are loosely related to the skill's core job (user interviews, Crossing the Chasm) rather than targeted market-sizing references, leaving minor organization gaps. | 4 / 5 |
Total | 16 / 20 Passed |