ideogram-core-workflow-b
Execute Ideogram secondary workflows: edit (Magic Fill), remix, upscale, describe, and reframe. Use when modifying existing images, applying style transfer, upscaling, or building image-to-image pipelines. Trigger with phrases like "ideogram edit image", "ideogram remix", "ideogram upscale", "ideogram inpaint", "ideogram magic fill", "ideogram reframe".
67
82%
Does it follow best practices?
Impact
—
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 a strong skill description that clearly defines its scope as Ideogram's secondary image manipulation workflows, distinct from primary image generation. It provides specific actions, explicit 'Use when' guidance, and well-chosen trigger phrases that cover natural user language. The description is concise, uses third person voice, and would allow Claude to confidently select this skill from a large pool.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Lists multiple specific concrete actions: edit (Magic Fill), remix, upscale, describe, and reframe. Also mentions style transfer and image-to-image pipelines as use cases. | 3 / 3 |
Completeness | Clearly answers both 'what' (edit, remix, upscale, describe, reframe via Ideogram secondary workflows) and 'when' (explicit 'Use when' clause for modifying existing images, style transfer, upscaling, image-to-image pipelines, plus explicit trigger phrases). | 3 / 3 |
Trigger Term Quality | Excellent coverage of natural trigger terms including 'ideogram edit image', 'ideogram remix', 'ideogram upscale', 'ideogram inpaint', 'ideogram magic fill', 'ideogram reframe'. These are terms users would naturally say when requesting these specific operations. | 3 / 3 |
Distinctiveness Conflict Risk | Highly distinctive by specifying 'Ideogram secondary workflows' and distinguishing these from primary generation. The 'ideogram' prefix on all trigger terms and the specific operation names (Magic Fill, remix, reframe) create a clear niche unlikely to conflict with other image skills. | 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 solid, actionable skill with complete executable code for all five Ideogram secondary endpoints. Its main weaknesses are the lack of validation checkpoints (e.g., pre-flight mask dimension checks, response validation beyond HTTP status) and some verbosity from repeating similar patterns across five functions. The error handling table and quick reference are useful additions.
Suggestions
Add validation checkpoints such as verifying mask dimensions match the source image before sending the edit request, and validating downloaded file size/integrity after fetching results.
Consider extracting the repeated fetch-and-download pattern into a shared helper function to reduce redundancy and improve token efficiency.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The skill is mostly efficient with executable code examples, but there's some redundancy across the five functions (repeated fetch/error patterns) and minor unnecessary commentary like 'Low weight = more creative freedom' that Claude could infer. The quick reference table partially duplicates information already shown in the code. | 2 / 3 |
Actionability | Every endpoint has fully executable TypeScript code with proper imports, complete function signatures, typed options, error handling, and concrete usage examples. The code is copy-paste ready with real API endpoints, headers, and form data construction. | 3 / 3 |
Workflow Clarity | The steps are clearly sequenced and each endpoint is well-documented, but there are no validation checkpoints between steps (e.g., verifying mask dimensions match before sending, checking downloaded file integrity, or validating API responses beyond status codes). For operations involving image manipulation and API calls, feedback loops for error recovery are missing. | 2 / 3 |
Progressive Disclosure | The content is well-structured with clear sections, a quick reference table, and links to external API docs. However, at ~150 lines of detailed code, some functions could be referenced from separate files rather than inline. The reference to 'ideogram-install-auth' and 'ideogram-common-errors' shows awareness of skill linking, but no bundle files exist to support progressive disclosure. | 2 / 3 |
Total | 9 / 12 Passed |
Validation
81%Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.
Validation — 9 / 11 Passed
Validation for skill structure
| Criteria | Description | Result |
|---|---|---|
allowed_tools_field | 'allowed-tools' contains unusual tool name(s) | Warning |
frontmatter_unknown_keys | Unknown frontmatter key(s) found; consider removing or moving to metadata | Warning |
Total | 9 / 11 Passed | |
- Commit
a04d1a2
- Reviewed
Table of Contents
Is this your skill?
If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.