CtrlK
BlogDocsLog inGet started
Tessl Logo

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'.

74

Quality

93%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide
SecuritybySnyk

Low

Low-risk findings worth noting

SKILL.md
Quality
Evals
Security

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 dense, contract-style specification with executable commands, exact typographic specs, a fully sequenced 10-step pipeline with validation checkpoints and feedback loops, and clean one-level-deep references whose files all exist. Its only real weakness is repetition: -f and -w contracts recur across multiple sections where a single canonical statement plus pointers would suffice.

Suggestions

Consolidate the -f rules (no new images, font stack, white-background contract) into one canonical section and reference it from 参数/Gotchas/交付合同 instead of restating them.

Likewise deduplicate the -w ledger and structure rules, which appear in both 共同生产线 and multiple Gotchas entries.

DimensionReasoningScore

Conciseness

Dense, contract-style prose with no concept padding and every sentence carrying a constraint, but key contracts (-f no-new-images, -f fonts/background, -w ledger rules) are restated across 3-4 sections and could be consolidated.

4 / 5

Actionability

Fully executable: concrete commands (bun assets/capture.ts <html> <png> <width> <height> [fullpage], prepare-whiteboard-source.ts, bun install/bunx playwright), exact numeric specs (#FFFFFF, #171717, 40px/1.9, 896px, 1080px), and template placeholder contracts.

5 / 5

Workflow Clarity

A 10-step numbered pipeline with explicit validation checkpoints (stop on any broken image, pre-delivery full-image check, overlapping slice QA, content review) and feedback loops (max two targeted regenerations, then report the blocking reason).

5 / 5

Progressive Disclosure

Clear overview with mode-routing table and mandatory read order pointing one level deep to references/ and assets/; every referenced file (taste.md, image-generation.md, learning-design.md, 4 mode files, 4 templates, capture/prepare-whiteboard-source/verify-full-text scripts) exists in the bundle.

5 / 5

Total

19

/

20

Passed

Description

92%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 exemplary: third-person, concrete about the transformation and the four molds, with an explicit USE WHEN clause and distinctive triggers including the unique brand word '铸'. Only trigger-term breadth (missing a few common synonyms like '长图' or English 'poster') keeps it from a perfect score.

Suggestions

Add common trigger synonyms such as '长图' and English equivalents ('make a poster', 'long-form card') to broaden natural keyword coverage.

DimensionReasoningScore

Specificity

Lists multiple concrete actions — 'Transforms text into PNG through precise HTML typography', generated raster imagery, and four enumerated molds — covering the skill's full scope.

5 / 5

Completeness

Explicitly answers both: what ('Transforms text into PNG through precise HTML typography... Four molds: -l/-f/-c/-w') and when ('USE WHEN user says...').

5 / 5

Trigger Term Quality

Good natural trigger coverage ('做成图', '做成卡片', '做成海报', '漫画', '白板', '铸', 'cast') but a few common variations are missing (e.g. '长图', English 'card'/'poster').

4 / 5

Distinctiveness Conflict Risk

Clear niche (text-to-PNG card casting) with distinct triggers including the unique brand word '铸' and mode flags; minimal overlap with other skills.

5 / 5

Total

19

/

20

Passed

Validation

93%

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

CriteriaDescriptionResult

frontmatter_unknown_keys

Unknown frontmatter key(s) found; consider removing or moving to metadata

Warning

Total

15

/

16

Passed

Repository
lijigang/ljg-skills
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.