sn-infographic
Generates professional infographics with various layout types and visual styles. Analyzes content, recommends layout and style, and generates publication-ready infographics. Use when user asks to create "infographic", "信息图", "visual summary", or "可视化".
npx skills add OpenSenseNova/SenseNova-Skills --skill sn-infographic --agent claude-code
Same command for any agent — swap --agent for codex, cursor, copilot.
Weekly change comes from our own snapshots, not the repository page — it measures attention, not adoption.
What it does
Generates professional infographics with various layout types and visual styles. Analyzes content, recommends layout and style, and generates publication-ready infographics. Use when user asks to create "infographic", "信息图", "visual summary", or "可视化".
How it works
- Operates as a two-tier architecture: a Main Agent coordinates requests and a Worker Agent executes the generation pipeline. The Worker runs steps to (1) decide whether to rewrite the image prompt (Step 1), (2) expand the prompt if needed (Step 2), and then (3) perform multi-round generation with image generation (sn-image-generate) and review (sn-image-recognize) across rounds, returning a structured JSON result. The workflow references external tools:
sn-image-baseviasn_agent_runner.py, with LLM evaluation throughsn-text-optimizeand image review viasn-image-recognize, all authenticated through default parameters. The engine evaluates prompt quality, can auto-expand prompts, and outputs the best result based on quality ranking. - Input parameters include:
user_prompt(required),max_rounds,output_mode,prompts_expand_mode,aspect_ratio, andimage_size. The Main Agent resolves or infers values; the Worker enforces defaults and inferences when not explicitly provided. The system creates a temporary working directory and a task ID to organize artifacts. - Step 1 always runs to decide whether to rewrite the image prompt. In
automode, it runs an evaluation viasn-text-optimize, parses the evaluation results, and determinesshould_expandbased on required/optional results. If evaluation fails, it defaults to expanding. Ifshould_expandis false, it setsEXPANDED_PROMPTto the original prompt and marksprompts_expand_skipped = true. Inforcemode, expansion is mandatory; indisablemode, it skips expansion and uses the original prompt as the expanded prompt, markingprompts_expand_skipped = true. - Step 2—Content Analysis + Layout & Style selection—uses the results to assemble a system prompt and determine
LAYOUTandSTYLEfor image generation. The worker then proceeds to generate images across rounds, reviewing with a vision model, and ranking outputs to select the best result.
When to use it
Use when the user requests to create or visualize information as an infographic and mentions keywords such as "infographic", "信息图", "visual summary", or "可视化". The skill is designed for content & marketing tasks that require layout recommendation and publication-ready infographic generation, with options to auto-expand prompts and perform multi-round generation.
What it can touch
- Tools:
sn-text-optimize(evaluation/expansion),sn-image-recognize(image review), andsn-image-generate(image creation). All API calls are routed throughsn_agent_runner.pyin thesn-image-baseskill and authenticated with default parameters. The workflow relies on environment variables likeSN_IMAGE_BASE,TASK_ID,TEMP_DIR,USER_PROMPT,MAX_ROUNDS,PROMPTS_EXPAND_MODE,ASPECT_RATIO, andIMAGE_SIZE. - Files/paths mentioned: uses
$SKILL_DIR/references/evaluation-standard.mdfor evaluation prompts and$SN_IMAGE_BASE/scripts/extract_json.pyfor JSON extraction; temporary artifacts stored under/tmp/openclaw/sn-infographic/${TASK_ID}.
Caveats
- License: MIT. The description notes that the Worker returns a JSON string per the Return Contract, and a non-
okstatus indicates an error. The process requires valid API keys in the environment or defaults; missing keys trigger error handling. The Main Agent handles user-visible messaging after Worker returns. The workflow includes multiple rounds and potential fallbacks if evaluation fails.
# sn-infographic Info graphic generation scene skill (tier 1), relying on the `sn-image-generate`, `sn-image-recognize`, and `sn-text-optimize` tools provided by `sn-image-base` (tier 0). Features: - Evaluation of prompt quality (auto mode) - Prompt expansion (force/auto mode) - Multiple rounds of image generation and VLM review - Output the best result based on quality ranking ## Input Specification | Parameter | Type | Default Value | Description | |-----------|------|---------------|-------------| | `user_prompt` | string | **Required** | Original user request. UTF-8 text; may include Markdown, URLs, or structured data. Length bounded only by the underlying LLM context budget. | | `max_rounds` | int | `1` | Maximum number of generation rounds. Valid range: `1`–`8`. When `max_rounds=1`, the Step 3 VLM review and the early-termination check are both skipped. | | `output_mode` | string | `friendly` | `friendly`: one-line content description + rank=1 single image | | | | | `verbose`: full quality ranking + timing stats + all images (ordered by rank) | | `prompts_expand_mode` | string | `auto` | `auto`: evaluate `user_prompt` quality first; enter Step 2 expansion only when it falls s
- Input Specification
- API Configuration
- Architecture: Main Agent + Worker Agent
- Workflow
- Main Agent Workflow
- Worker Agent Workflow
- Call Relationship
- References
mkdir -p "$TEMP_DIR"
echo "$EXPANDED_PROMPT" > "$TEMP_DIR/expanded-prompt.txt"
A failed runner envelope (status != ok) has no .result → return Error Flow.
if [ "$(printf '%s' "$ANALYSIS_ENVELOPE" | jq -r '.status')" != "ok" ]; then
fi
printf '%s' "$ANALYSIS_ENVELOPE" | jq -r '.result' \
cat > "$TEMP_DIR/structured-content.md" << 'EOF'
cat "$SKILL_DIR/references/prompts-expand-system.md"
printf '\n\n---\n\n## Selected Layout: %s\n\n' "$LAYOUT"
cat "$SKILL_DIR/references/layouts/${LAYOUT}.md"What does the sn-infographic skill do?
Generates professional infographics with various layout types and visual styles. Analyzes content, recommends layout and style, and generates publication-ready infographics. Use when user asks to create "infographic", "信息图", "visual summary", or "可视化".
How do I install it?
Run `npx skills add OpenSenseNova/SenseNova-Skills --skill sn-infographic --agent claude-code` — it drops the skill into your project so the agent can pick it up. Swap the --agent value for codex, cursor or copilot if you use one of those.
Where does this skill come from?
From OpenSenseNova/SenseNova-Skills, a repository with 4,855 stars. We read it straight from the repository tree rather than a submitted listing, so what you see here is what is actually published.
Is a popular skill a good skill?
Not necessarily. Stars measure attention, not adoption — a repository can trend for a week and be abandoned. That is why we show the weekly change from our own snapshots next to the total, instead of a single flattering number.