metis-strategy/metis-whitepaper
Produce Metis Strategy whitepapers — 15–28 page thought leadership PDFs with a specific structure, visual style, and editorial voice. Use this skill whenever a user asks to create, draft, or structure a whitepaper, thought leadership paper, playbook, or long-form research report for Metis Strategy. Also trigger when the user mentions "whitepaper," "white paper," "playbook," "thought leadership piece," "long-form report," or asks to produce a publishable document that looks like existing Metis research. Output is a polished, print-ready PDF generated from HTML via Playwright — matching the look and feel of published Metis whitepapers. Always use this skill for whitepaper requests, even if the user just says "write a whitepaper on X" without further specification.
94
94%
Does it follow best practices?
Impact
Pending
No eval scenarios have been run
Advisory
Suggest reviewing before use
Quality
Discovery
100%Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.
This is an excellent skill description that hits all the marks. It provides specific capabilities, comprehensive trigger terms with natural language variations, explicit 'use when' and 'do not use when' guidance, and clear boundaries that distinguish it from related skills. The negative scope ('Do NOT use this skill for...') with a redirect to the correct alternative skill is particularly well done.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Lists multiple concrete actions and outputs: 'Produce Metis Strategy whitepapers,' 'thought leadership PDFs with a specific structure, visual style, and editorial voice,' 'polished, print-ready PDF generated from HTML via Playwright.' Also specifies what it does NOT do (short reports, proposals, one-pagers, presentations). | 3 / 3 |
Completeness | Clearly answers both 'what' (produce Metis Strategy whitepapers as print-ready PDFs with specific structure/style/voice) and 'when' (explicit 'Use this skill whenever...' clause with detailed trigger scenarios, plus negative boundaries specifying when NOT to use it). | 3 / 3 |
Trigger Term Quality | Excellent coverage of natural trigger terms: 'whitepaper,' 'white paper,' 'playbook,' 'thought leadership piece,' 'long-form report,' 'publishable document,' 'write a whitepaper on X.' These are terms users would naturally say, including common variations like 'whitepaper' vs 'white paper.' | 3 / 3 |
Distinctiveness Conflict Risk | Highly distinctive — scoped to a specific organization (Metis Strategy), a specific document type (whitepapers/long-form thought leadership), and explicitly delineates boundaries by naming the alternative skill (metis-brand-identity) for other document types. Very unlikely to conflict with other skills. | 3 / 3 |
Total | 12 / 12 Passed |
Implementation
85%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This is a highly actionable and well-structured skill for a complex, multi-step document production workflow. Its greatest strengths are the concrete, executable code examples, clear 10-step workflow with validation gates, and appropriate progressive disclosure to reference files. The main weakness is moderate verbosity — some sections explain things Claude already knows (text editor usage, what's safe to edit in HTML) and the overall length could be tightened by ~15-20% without losing information.
Suggestions
Trim the 'Human review (spot edits)' section significantly — Claude knows how text editors work and what HTML tags are. Reduce to just 'The user can edit text content in whitepaper.html directly; CSS classes, SVG coordinates, and the <head> section should not be manually edited.'
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The skill is quite long (~400+ lines) and includes some information Claude could infer (e.g., explaining what Notepad and Ctrl+F do in the human review section, explaining what a PDF is in context). However, much of the length is justified by the highly specific brand rules, asset paths, and CSS constants that Claude genuinely needs. Some sections like the 'What's safe to edit' guidance are unnecessarily verbose. | 2 / 3 |
Actionability | The skill provides fully executable code snippets (bash commands, HTML/CSS templates, SVG examples, Playwright rendering commands), specific file paths, exact CSS values, concrete JSON config formats, and copy-paste ready HTML patterns for callout boxes, metric cards, and citations. Every instruction is concrete and directly usable. | 3 / 3 |
Workflow Clarity | The 10-step workflow is clearly sequenced with explicit validation checkpoints: Step 3 requires user approval before proceeding, Step 8 provides a human review gate before rendering, and Step 10 includes a final verification checklist. The outline-first mandate with explicit 'wait for user approval' is a strong feedback loop for this multi-step process. | 3 / 3 |
Progressive Disclosure | The skill clearly references three external files (content-patterns.md, page-layouts.md, diagram-builders.md) with one-level-deep navigation and clear descriptions of what each contains. The main SKILL.md serves as an effective overview and workflow guide while delegating detailed templates and patterns to reference files. The rendering script is also properly externalized. | 3 / 3 |
Total | 11 / 12 Passed |
Validation
100%Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.
Validation — 11 / 11 Passed
Validation for skill structure
No warnings or errors.
Reviewed
Table of Contents