metis-strategy/metis-html-slides
Generate interactive HTML presentations with sidebar navigation, scrollable sections, and 40+ typography-driven components. Supports Metis branding with auto-embedded logo and client brand extraction from PPTX templates. Output is a self-contained HTML file viewable in any browser.
85
85%
Does it follow best practices?
Impact
Pending
No eval scenarios have been run
Passed
No known issues
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 covers all key dimensions well. It provides specific capabilities, clear trigger terms, explicit 'use when' guidance, and distinguishes itself from related presentation skills (e.g., PPTX-based). The description is detailed yet focused, making it easy for Claude to select this skill appropriately from a large pool.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Lists multiple specific concrete actions: generate HTML presentations as self-contained single files, persistent sidebar navigation, scrollable sections, interactive components, Metis branding, client brand extraction from PPTX templates. | 3 / 3 |
Completeness | Clearly answers both what (generate HTML presentations with sidebar navigation, scrollable sections, interactive components, branding support) and when (explicit 'Use this skill when...' clause plus 'Triggers on...' with specific phrases). | 3 / 3 |
Trigger Term Quality | Includes strong natural trigger terms: 'html slides,' 'html presentation,' 'browser deck,' 'HTML output instead of PPTX,' plus contextual terms like 'internal decks,' 'workshop materials,' 'strategy frameworks,' and 'consulting product.' | 3 / 3 |
Distinctiveness Conflict Risk | Clearly distinguishable from generic presentation skills or PPTX skills by specifying HTML-based, browser-viewable, single-file output. The explicit contrast with PPTX and specific trigger terms like 'browser deck' and 'html slides' minimize conflict risk. | 3 / 3 |
Total | 12 / 12 Passed |
Implementation
64%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 with excellent concrete examples and clear HTML patterns. Its main weakness is that the extensive component reference catalog (Sections 5-10) bloats the main file when it could be split into a separate reference document, and the build workflow lacks explicit error handling/validation feedback loops between phases.
Suggestions
Move the detailed component reference (Sections 5, 6, 8, 10) into a separate file like COMPONENTS.md and link to it from the main skill, keeping only a summary table in SKILL.md
Add explicit validation/error recovery steps in the build workflow — e.g., 'If build_deck.py fails, check that all slides have required data-section-num and data-section-title attributes' and 'Validate HTML structure before building'
Add a brief troubleshooting section covering common failure modes (missing Python path, missing brand assets on G: drive, malformed slide HTML)
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The skill is quite long (~500+ lines) with extensive HTML examples that are necessary for reference but could be more efficiently organized. Some sections like the ASCII diagram and the exhaustive component reference could be moved to a separate file. However, it avoids explaining basic concepts Claude already knows and most content is genuinely instructive. | 2 / 3 |
Actionability | Highly actionable with executable bash commands, complete HTML snippets that are copy-paste ready, specific CSS class names, data attribute requirements, and concrete build commands. Every component has a working HTML example with the exact classes needed. | 3 / 3 |
Workflow Clarity | The four-phase workflow (Plan → Write → Build → QA) is clearly sequenced, and Phase 4 includes a QA checklist. However, there are no explicit validation checkpoints or error recovery steps between phases — e.g., no 'if the build script fails, check X' feedback loop, and no verification that the slides HTML is well-formed before building. | 2 / 3 |
Progressive Disclosure | The skill references `references/patterns.md` for the full pattern guide and mentions external scripts, which is good. However, the massive component reference (Sections 5-6) is inlined rather than split into a separate reference file, making the main skill document very long. The content that should be in a reference file is inline. | 2 / 3 |
Total | 9 / 12 Passed |
Validation
90%Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.
Validation — 10 / 11 Passed
Validation for skill structure
| Criteria | Description | Result |
|---|---|---|
skill_md_line_count | SKILL.md is long (765 lines); consider splitting into references/ and linking | Warning |
Total | 10 / 11 Passed | |
Reviewed
Table of Contents