mcollina/snipgrapher
Configures and uses snipgrapher to generate polished code snippet images, including syntax-highlighted PNGs, SVGs, and WebP exports with custom themes, profiles, and styling options. Use when the user wants to create code screenshots, turn code into shareable images, generate pretty code snippets for docs or social posts, produce syntax-highlighted images from source files, or explicitly mentions snipgrapher. Supports single-file renders, batch jobs, watch mode, and reusable named profiles via the snipgrapher CLI or npx.
88
95%
Does it follow best practices?
Impact
79%
1.38xAverage score across 5 eval scenarios
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 covers all key dimensions thoroughly. It provides specific capabilities, comprehensive trigger terms that match natural user language, explicit 'Use when' guidance with multiple scenarios, and a clearly distinctive niche around code-to-image generation via snipgrapher. The description is detailed yet not overly verbose, and uses proper third-person voice throughout.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Lists multiple specific concrete actions: generating syntax-highlighted PNGs/SVGs/WebP exports, custom themes, profiles, styling options, single-file renders, batch jobs, watch mode, and reusable named profiles via CLI or npx. | 3 / 3 |
Completeness | Clearly answers both 'what' (configures and uses snipgrapher to generate code snippet images with various formats and options) and 'when' (explicit 'Use when...' clause listing five distinct trigger scenarios). | 3 / 3 |
Trigger Term Quality | Excellent coverage of natural terms users would say: 'code screenshots', 'turn code into shareable images', 'pretty code snippets', 'syntax-highlighted images', 'docs or social posts', 'snipgrapher', plus format terms like PNG, SVG, WebP. | 3 / 3 |
Distinctiveness Conflict Risk | Highly distinctive niche — code-to-image generation via snipgrapher is a very specific tool and use case. The mention of the specific tool name, output formats, and the particular workflow (code screenshots, shareable images) makes it unlikely to conflict with other skills. | 3 / 3 |
Total | 12 / 12 Passed |
Implementation
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 solid, well-structured skill with strong actionability and clear workflow sequencing including validation. Its main weaknesses are moderate verbosity—the 'When to use' and 'Core principles' sections add little value beyond what Claude can infer—and the inability to verify that referenced rule files actually exist in the bundle. The troubleshooting section is a nice touch but could be more concise.
Suggestions
Remove or significantly trim the 'When to use' section since this information is already captured in the skill's description/frontmatter and Claude doesn't need it repeated.
Condense the 'Core principles' section—these are largely self-evident best practices that Claude would follow naturally; consider removing or folding key points into the rule files.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | Mostly efficient but includes some unnecessary padding. The 'When to use' section repeats what the frontmatter description already covers, and the 'Core principles' section states things Claude would naturally infer (e.g., 'prefer named profiles and explicit output paths'). The troubleshooting section is somewhat verbose for common-sense items. | 2 / 3 |
Actionability | Provides fully executable, copy-paste-ready CLI commands for both quick start and project-based workflows. The commands are specific (npx snipgrapher render, init) with concrete flags and output paths, plus a verification step. | 3 / 3 |
Workflow Clarity | The quick start shows a clear single-step path, the project workflow is sequenced (init → render → verify), and there's an explicit validation checkpoint (ls -lh to confirm output). The troubleshooting section provides a feedback loop for common failure modes with specific remediation steps. | 3 / 3 |
Progressive Disclosure | The skill references two rule files (setup-and-configuration.md, rendering-workflows.md) with clear one-level-deep navigation, which is good structure. However, no bundle files were provided, so we cannot confirm these references actually exist. The inline troubleshooting section could arguably be in a separate file, and the 'Core principles' and 'When to use' sections add bulk that dilutes the overview quality. | 2 / 3 |
Total | 10 / 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 |
|---|---|---|
metadata_version | 'metadata.version' is missing | Warning |
Total | 10 / 11 Passed | |
Reviewed
Table of Contents