ai-card-generator

Generate AI Cards — HTML visual pages (single-file or folder-based multi-file) for scheduled automated reports. Use when: user wants to create a recurring visual card, hotspot tracker, daily digest, analytics panel, inspiration page, or any HTML-based automated visualization that updates on schedule. Trigger signals: AI card, inspiration card, generated card, visual report, hotspot tracker, daily digest, dashboard card, scheduled visualization, and equivalent requests in any user language. Skip when: the task is about creating social media posts (use self-media-composer), or simple file generation without recurring schedule.

Quality

76%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Low

Low-risk findings worth noting

Fix and improve this skill with Tessl

tessl review fix ./backend/super-magic/agents/skills/ai-card-generator/SKILL.md

Quality

Content

57%Weight 40%Scale 1-5

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

The body is highly actionable with concrete config, template, and scheduling code, and its workflows are well sequenced. Its main weaknesses are duplicated content that belongs in the existing reference file (hurting both conciseness and progressive disclosure) and the absence of validation checkpoints in the destructive archive/overwrite workflow.

Suggestions

Replace the inlined directory tree, responsive iframe modes, data-section marking, and source/iframe patterns in the body with brief pointers to references/card-spec.md to remove duplication and improve progressive disclosure.

Add an explicit validation checkpoint in the Scheduled Execution Workflow (e.g., verify `magic.project.js` parses and the data fetch succeeded before archiving/overwriting `latest/`), with a fix-and-retry loop, to lift workflow_clarity above the destructive-operation cap of 3.

Link references/card-spec.md explicitly from a short 'Reference' section so the existing bundle file is discoverable rather than orphaned.

Dimension	Reasoning	Score
Conciseness	The body is mostly efficient and skill-specific, but several blocks duplicate material also present in references/card-spec.md (directory tree, responsive iframe modes, data-section marking, source/iframe patterns) and could be tightened by pointing to the reference instead of restating.	3 / 5
Actionability	Quotes concrete executable blocks: the full `window.magicProjectConfig` JS, the `notification` shape, the template HTML skeleton, the sandboxed iframe pattern, and a real `scheduled_task_create` Python snippet via `tool.call`; mostly copy-paste ready with only minor gaps around runtime verification.	4 / 5
Workflow Clarity	Creation (Steps 0–3) and Scheduled Execution (9 numbered steps) are clearly sequenced, but a destructive/batch operation — archiving then overwriting `latest/` — has no explicit validation checkpoint, capping this dimension at 3 per the rubric's destructive-operation rule.	3 / 5
Progressive Disclosure	A reference file (references/card-spec.md) exists, but the body never links to it and instead inlines the same directory layout, responsive modes, and source patterns; references are present but not clearly signaled and content that should be separate stays inline.	3 / 5
	Total	13 / 20 Passed

Description

95%Weight 40%Scale 1-5

Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.

The description is third-person, concrete, and explicitly covers what, when, and when-not-to-use with a rich set of natural trigger terms. Its only minor gap is that the action side is dominated by a single "generate" verb while the output-type list does most of the specificity work.

Dimension	Reasoning	Score
Specificity	Quotes "Generate AI Cards — HTML visual pages (single-file or folder-based multi-file) for scheduled automated reports" plus a list of concrete card types; it names several specific outputs but the primary verb is a single generate action, leaving minor coverage gaps relative to the comprehensive 5 anchor.	4 / 5
Completeness	Quotes a clear what ("Generate AI Cards — HTML visual pages...") and an explicit when ("Use when: user wants to create a recurring visual card...") plus trigger signals and a "Skip when" boundary, explicitly answering both what and when with concrete trigger phrases.	5 / 5
Trigger Term Quality	Quotes "AI card, inspiration card, generated card, visual report, hotspot tracker, daily digest, dashboard card, scheduled visualization, and equivalent requests in any user language" — comprehensive natural-term coverage including synonyms and multi-language allowance.	5 / 5
Distinctiveness Conflict Risk	Quotes a clear niche (scheduled HTML AI cards) with an explicit conflict-avoidance clause "Skip when: the task is about creating social media posts (use self-media-composer)", giving minimal overlap risk with other skills.	5 / 5
	Total	19 / 20 Passed

Validation

100%

Warnings & errors only

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository: dtyq/magic
Path: backend/super-magic/agents/skills/ai-card-generator/SKILL.md
Commit: f9973c5

Reviewed: 2 days ago

Table of Contents

Discovery Implementation Validation

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.