---

name: sn-infographic description: | 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". metadata: project: SenseNova-Skills tier: 1 category: scene priority: 9 user_visible: true triggers:

• "infographic"
• "information graphic"
• "infographics generation"
• "visual summary"
• "data visualization"
• "visual explanation"
• "diagram"
• "生成信息图"
• "信息图生成"
• "生成 infographic"
• "信息图表"
• "图表生成"
• "数据可视化"
• "图解"

---

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 short | | | | | force: skip evaluation, always execute Step 2 expansion | | | | | disable: skip Step 2, use user_prompt directly as expanded_prompt | | aspect_ratio | string | inferred (16:9) | Set by Main Agent when the user states an explicit supported ratio (e.g. 16:9 / 9:16, optionally via 宽高比 / 画面比例 / aspect ratio); otherwise left unset and the Worker infers it in Step 0 from user_prompt (orientation / scene cues) per references/runtime-parameters.md. | | image_size | string | inferred (2k) | Set by Main Agent when the user states an explicit size (2k / 4k); otherwise the Worker infers it in Step 0 (currently a single option, 2k). 4k is supported when SN_IMAGE_GEN_MODEL=sensenova-u1.5-lite; other models may reject it and the skill surfaces that error. |

Who extracts what: Main Agent parameter extraction resolves max_rounds, output_mode, prompts_expand_mode, and aspect_ratio / image_size (each only when the user gives an explicit value). aspect_ratio and image_size without an explicit value are inferred by the Worker in Step 0.

API Configuration

All API calls in this skill are executed through the sn_agent_runner.py of the sn-image-base skill, with authentication parameters using default values (CLI > environment variables > built-in defaults),无需显式传入。

| Call Type | Tool | Authentication Parameters | Description | |-----------|------|---------------------------|-------------| | LLM | sn-text-optimize (evaluation/expansion) | Default reads SN_TEXT_API_KEY -> SN_CHAT_API_KEY -> SN_API_KEY | Built-in default points to Sensenova internal network service | | VLM | sn-image-recognize (image review) | Default reads SN_VISION_API_KEY -> SN_CHAT_API_KEY -> SN_API_KEY | Built-in default points to Sensenova internal network service | | Image Generation | sn-image-generate | Default reads SN_IMAGE_GEN_API_KEY -> SN_API_KEY; SN_IMAGE_GEN_API_KEY is only needed for image-specific override | Uses image generation configuration of sn-image-base |

When encountering MissingApiKeyError or needing to specify a model: pass explicitly via CLI parameters, parameter reference $SN_IMAGE_BASE/references/api_spec.md.

$SN_IMAGE_BASE path explanation: $SN_IMAGE_BASE is the installation directory of the sn-image-base skill (SKILL.md exists). The agent can locate this path by skill name sn-image-base in the list of installed skills.

Architecture: Main Agent + Worker Agent

This skill uses a two-tier agent architecture:

| Role | Responsibility | |------|----------------| | Main Agent | Receive user request, normalize parameters, send preflight, start Worker, collect results, send text and images to user | | Worker Agent | Execute the generation pipeline (expand → multiple rounds of generation + review → sort), return structured JSON |

Responsibility Boundaries:

• Worker Agent does not send any messages to the user directly, only returns structured JSON
• Main Agent is responsible for sending all user-visible messages
• Worker Agent's last message must be and only be the JSON string defined in the Return Contract
• Worker Agent's internal VLM calls always execute directly, without spawning subagents

Workflow

Main Agent Workflow

1. Parameter extraction from the user request, in three passes:

   1. Inline KV directives — parse tokens of the form key=value where key ∈ {max_rounds, output_mode, prompts_expand_mode, aspect_ratio, image_size}; strip recognized tokens from the user message, and the remainder becomes user_prompt. Example: "生成一张信息图 max_rounds=3 output_mode=verbose" → user_prompt="生成一张信息图", max_rounds=3, output_mode=verbose.

   2. Keyword recognition (case-insensitive, applied to the stripped text) — fill any parameter not yet set by inline KV using the table below:

      | Parameter | Trigger keywords | Resolved value | |-----------|------------------|----------------| | output_mode | verbose, 详细, 详尽, 完整统计 | verbose | | | friendly, 简洁, 精简 | friendly | | max_rounds | N 轮, N rounds, 重试 N 次 (parse N) | N, clamped to [1, 8] | | prompts_expand_mode | 强制扩写, force expand, force expansion | force | | | 不扩写, 跳过扩写, disable expansion, no expand | disable | | aspect_ratio | an explicit supported ratio (16:9 9:16 4:3 3:4 1:1 2:3 3:2 4:5 5:4 21:9 9:21), with or without a 宽高比 / 画面比例 / 比例 / aspect ratio lead-in | that ratio (validated against the supported set in runtime-parameters.md; unsupported value → leave unset for Worker inference) | | image_size | an explicit supported size (2k 4k), with or without an image_size / 分辨率 / 清晰度 / image size lead-in | that size (vague quality words like 高清 / 超清 do not count); unsupported value → leave unset for Worker inference |

   3. Defaults — any parameter still unset falls back to max_rounds=1, output_mode=friendly, prompts_expand_mode=auto. aspect_ratio and image_size have no Main-Agent default: when no explicit value is detected they are left unset for the Worker to infer in Step 0.

   Precedence: inline KV > keyword recognition > default. Values from inline KV are validated against the Input Specification (out-of-range max_rounds clamped to [1, 8]; unrecognized enum values fall back to default and Main Agent should log the mismatch).

2. Send uniform preflight message: "Using sn-infographic skill to generate infographic, please wait..."

3. Start Worker Agent (Sub-Agent), passing in complete parameters and working directory

4. When Worker Agent returns status=ok and need_main_agent_send=true:

   • max_rounds = 1: Generate the Text Summary (see Output Format → friendly mode for length/language rules) from expanded_prompt in the returned JSON (always present for status=ok, see Return Contract), send it, then send the rank=1 single image
   • max_rounds > 1, friendly mode: Generate the Text Summary based on the rank=1 round's result and violations, send it, then send the rank=1 single image
   • max_rounds > 1, verbose mode: Render the verbose template (see Output Format → verbose mode for substitution rules) and send it, then send all images in rank order

5. If Worker Agent returns status=error, report the real error field content to the user

Worker Agent Workflow

Worker Agent receives user_prompt, max_rounds, prompts_expand_mode, an optional aspect_ratio and image_size (each set only when the user gave an explicit value), and the working directory of this skill (SKILL_DIR). (output_mode stays on the Main Agent side — Worker has no branch that depends on it.)

Worker Environment

Variables referenced as $NAME in the bash snippets below. Worker must bind each before the step that consumes it.

| Variable | Source | Used by | |----------|--------|---------| | USER_PROMPT | Main Agent input — original user request | Step 1 evaluation; Step 2.0 content analysis | | MAX_ROUNDS | Main Agent input (default 1) | Step 3 loop bound; early-termination gate | | PROMPTS_EXPAND_MODE | Main Agent input (default auto) | branches Step 1 | | SKILL_DIR | Agent runtime resolves the current skill's install path (e.g. ~/.openclaw/skills/sn-infographic, ~/.hermes/skills/sn-infographic) | reads references/* | | SN_IMAGE_BASE | Agent runtime resolves by skill name sn-image-base in the installed-skill registry | runs scripts/sn_agent_runner.py | | TASK_ID | Step 0 (date +%Y%m%d_%H%M%S) | uniqueness token | | TEMP_DIR | Step 0 (/tmp/openclaw/sn-infographic/${TASK_ID}) | scratch dir for all intermediate artifacts | | IMAGE_SIZE | Main Agent input when the user stated an explicit size, else Step 0 inference from USER_PROMPT (single option, 2k) | sn-image-generate --image-size | | ASPECT_RATIO | Main Agent input when the user stated an explicit ratio, else Step 0 inference from USER_PROMPT (default 16:9) | sn-image-generate --aspect-ratio | | EXPANDED_PROMPT | Step 1 (copy of USER_PROMPT when Step 2 is skipped) or Step 2.3 (expanded result) | sn-image-generate --prompt | | LAYOUT, STYLE | Step 2.1 selection result (with fallback to hub-spoke / corporate-memphis) | Step 2.3 system-prompt assembly | | ROUND | Step 3 loop counter (for ROUND in $(seq 1 "$MAX_ROUNDS")) | per-round file naming (round_${ROUND}.png) |

Naming: $SKILL_DIR for own files; $SN_<SKILL_NAME> (e.g. $SN_IMAGE_BASE) for cross-skill references.

JSON parsing: every sn_agent_runner.py ... -o json call prints a JSON envelope on stdout ({"status", "result", "model", ...}; diagnostics go to stderr). A failed call sets status to a non-ok value (e.g. failed) and omits result, so always confirm .status == ok on the envelope before reading .result — otherwise a missing .result surfaces as the literal null, which is itself valid JSON and slips past both jq -r and extract_json.py (no error raised). The LLM's own JSON (evaluation / analysis steps) lives inside the result string and may carry stray prose or ```json fences. Before any jq, pipe the runner output through $SN_IMAGE_BASE/scripts/extract_json.py (reads stdin, prints the recovered JSON, exits non-zero when none is found); for steps that parse the inner LLM/VLM JSON, pipe .result through it as well. A non-ok status or a non-zero extract_json.py exit means the response is unusable → return the Error Flow JSON.

Step 0 — Initialization

1. Generate task_id (timestamp, format YYYYMMDD_HHMMSS) and create the uniform temporary directory /tmp/openclaw/sn-infographic/<task_id>/ as TEMP_DIR. TEMP_DIR must exist before any subsequent step writes to it:

   TASK_ID=$(date +%Y%m%d_%H%M%S)
   TEMP_DIR="/tmp/open