ljg-card

Content caster (铸). Transforms text into PNG through precise HTML typography and, when the mold needs it, generated raster imagery. Four molds: -l (default) long reading card, -f source-faithful full text, -c comic, -w whiteboard. USE WHEN user says '铸', 'cast', '做成图', '做成卡片', '做成海报', '原文排版', '全文卡片', '漫画', or '白板'.

Quality

96%

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

Quality

Content

92%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 a well-structured, highly actionable overview for a complex four-mode skill, with concrete commands, explicit validation/feedback loops, and one-level-deep references that all resolve to real bundle files. The only weakness is moderate verbosity in the Gotchas and per-mode constraint sections that could be offloaded to the mode reference files.

Suggestions

Move some of the -w/-f-specific Gotchas entries into references/mode-whiteboard.md and references/mode-full.md so the SKILL.md overview stays leaner, since those details are only relevant when that mode is selected.

Consolidate the scattered font/color constraint statements for -f (currently split across three sections) into a single block or a reference file to reduce repetition.

Trim the longest Gotchas bullets to their core rule and link to the relevant mode file for rationale, preserving the dense instruction style while lowering token cost.

Dimension	Reasoning	Score
Conciseness	The body is instruction-dense and assumes Claude's competence (no basic-concept padding), but the long Gotchas list and several per-mode constraints could be trimmed or pushed into the mode reference files. It sits noticeably above the midpoint anchor but is not perfectly lean.	4 / 5
Actionability	Copy-paste ready commands (bun assets/capture.ts, bun assets/prepare-whiteboard-source.ts, bun install, bunx playwright install chromium, bun run audit/test/fixtures) and concrete placeholders/data attributes ({{LOGIC_LEDGER_JSON}}, {{SOURCE_LINE}}, data-state="empty", data-source-claim) cover the common cases.	5 / 5
Workflow Clarity	The numbered 共同生产线 (9 steps) provides a clear sequence with explicit validation checkpoints (wait for fonts/images before screenshot, stop on broken image, verify-full-text.ts must fail on edits, overlapping-slice QA, SHA-256 checks) and error-recovery feedback loops (up to 2 targeted regenerations before blocking).	5 / 5
Progressive Disclosure	SKILL.md acts as an overview with a 必读顺序 and a mode 路由 table pointing one level deep to references/mode-.md and assets/_template.html; all referenced paths were verified to exist as real bundle files, and navigation is clearly signaled.	5 / 5
	Total	19 / 20 Passed

Description

100%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 a strong, third-person statement that concretely names the capability, enumerates all four modes, and provides an explicit USE WHEN clause with comprehensive bilingual trigger terms. It cleanly answers both what the skill does and when to invoke it.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions ("Transforms text into PNG through precise HTML typography", "generated raster imagery") and itemizes all four output molds (-l/-f/-c/-w) with their roles, giving comprehensive coverage of what the skill does.	5 / 5
Completeness	It explicitly answers both 'what' (text→PNG via HTML typography + generated imagery, four molds) and 'when' (a concrete USE WHEN clause with explicit trigger phrases).	5 / 5
Trigger Term Quality	The "USE WHEN user says '铸', 'cast', '做成图', '做成卡片', '做成海报', '原文排版', '全文卡片', '漫画', or '白板'" clause covers natural terms across both Chinese and English, including synonyms for each mold.	5 / 5
Distinctiveness Conflict Risk	The content-casting niche and the distinctive trigger terms (铸/cast/做成卡片) make it clearly distinguishable from other skills with minimal overlap risk.	5 / 5
	Total	20 / 20 Passed

Validation

93%

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 — 15 / 16 Passed

Validation for skill structure

Criteria	Description	Result
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	15 / 16 Passed

Repository: lijigang/ljg-skills
Path: skills/ljg-card/SKILL.md
Commit: 44f4105

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.