Content
77%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This is a strong, highly actionable skill that provides domain-specific frameworks and concrete examples for board/investor communications. Its main weakness is length — at ~200+ lines with multiple inline frameworks, it could benefit from splitting detailed reference material into separate files. The workflow is clear, the examples are excellent, and the guidance is specific enough to produce high-quality outputs.
Suggestions
Move the detailed 11-section framework table, metrics presentation rules, and cadence guidelines into a separate BOARD-UPDATE-REFERENCE.md file, keeping only the workflow and key principles in SKILL.md.
Trim editorial commentary like 'Investors forgive bad quarters. They do not forgive founders who hide problems until they become crises.' — these are persuasive asides that don't change Claude's behavior.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The skill is fairly comprehensive and most content earns its place as domain-specific knowledge Claude wouldn't inherently know (the 11-section framework, bad-news protocol, metrics rules). However, there's some verbosity in explanatory asides ('Boards see 10+ decks per quarter', 'Investors forgive bad quarters. They do not forgive founders who hide problems until they become crises.') and the common mistakes section partially overlaps with guidance already given in other sections. | 2 / 3 |
Actionability | The skill provides highly concrete, actionable guidance: specific section frameworks with owners, exact word/slide counts, a complete example investor email with formatted metrics table, specific bad-news delivery steps, and concrete examples of good vs. bad asks ('any intros would be great' vs. 'intro to VP Ops at Stripe'). The examples are copy-paste ready templates. | 3 / 3 |
Workflow Clarity | The 6-step workflow is clearly sequenced with decision points (format determination based on stage), explicit structure for each section (Headline-Data-Narrative-Ask/Next), and the bad-news protocol provides a clear feedback loop. The four-act narrative structure serves as a validation checkpoint for explaining variances. For a content-generation skill (non-destructive), this level of workflow clarity is excellent. | 3 / 3 |
Progressive Disclosure | The skill is quite long with all content inline — the 11-section framework table, multiple sub-frameworks (bad-news delivery, four-act narrative, metrics rules, cadence guidelines, common mistakes), and two examples all live in one file. The frameworks and detailed tables could be split into referenced files. However, it does use clear headers and tables for organization, and references related skills at the end. | 2 / 3 |
Total | 10 / 12 Passed |