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".

Quality

82%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Failed to scan

The risk profile of this skill

Quality

Content

81%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.

A highly actionable, well-sequenced operational spec with strong validation and error-recovery loops and a sound one-level reference structure. Its main weakness is verbosity — repeated defensive caveats and inlined contract/template detail that could be trimmed or externalized.

Suggestions

Consolidate the repeated jq-null / extract_json.py guard into one stated-once convention referenced thereafter, cutting several restated paragraphs.

Move the full verbose-mode output template and the complete keyword-recognition tables into a reference file, keeping only the friendly-mode summary rule and a pointer inline.

Trim the defensive 'do not over-read the step name' / 'do not map onto subagent-driven-development' prose to a single concise scoping note.

Dimension	Reasoning	Score
Conciseness	The body is operational rather than explanatory of basics, which is good, but it carries noticeable defensive padding — the Step 1 'Scope' warnings, repeated 'do not map onto subagent-driven-development' caveats, and the same jq-null / extract_json.py guard restated at each API boundary could be tightened without losing clarity.	3 / 5
Actionability	Provides copy-paste-ready bash for every scriptable step (sn_agent_runner.py invocations with exact flags, jq pipelines, mkdir, heredoc assembly) plus exact JSON schemas and file paths; the few prose-described steps (VLM response mapping, structured-content generation) are inherently LLM-judgment steps that cannot be fully scripted.	5 / 5
Workflow Clarity	Steps 0–4 are clearly sequenced with explicit validation checkpoints at every API boundary (status == ok checks, extract_json.py exit codes), feedback loops (failed envelope → Error Flow; eval failure → conservative should_expand=true fallback), and an early-termination gate — matching the top anchor for batch operations with error recovery.	5 / 5
Progressive Disclosure	Reference files are real, one level deep, and clearly signaled (analysis-framework, layout-style-selection, layouts/, styles/, etc., all listed in a References section and confirmed to exist), and bulk detail is split out appropriately; however the body itself is long, inlining the full Return Contract, verbose output-format templates, and complete keyword-extraction tables that could partly live in references.	4 / 5
	Total	17 / 20 Passed

Description

83%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.

A strong, third-person description that concretely states what the skill does and gives an explicit 'Use when' clause with bilingual trigger phrases. The main gaps are slightly repetitive action verbs and a few common trigger synonyms omitted from the description itself.

Suggestions

Replace the repeated 'generates infographics' with distinct concrete actions (e.g. 'ranks outputs by VLM-reviewed quality', 'delivers publication-ready single or multi-image results') to broaden specificity.

Add a few high-frequency natural triggers to the description (e.g. 'infographics', 'diagram', 'data visualization') to match the frontmatter trigger list.

Tighten the broad terms ('visual summary', '可视化') or qualify them (e.g. 'visual summary infographic') to reduce overlap with generic visualization skills.

Dimension	Reasoning	Score
Specificity	Names the infographic domain and several concrete actions — 'Generates professional infographics', 'Analyzes content, recommends layout and style', 'generates publication-ready infographics' — but the action list overlaps ('generates infographics' appears twice) rather than being comprehensively distinct, so it sits just below the top anchor.	4 / 5
Completeness	Clearly answers both: the 'what' ('Generates professional infographics... recommends layout and style... generates publication-ready infographics') and an explicit 'when' with concrete trigger phrases ('Use when user asks to create "infographic", "信息图", "visual summary", or "可视化"').	5 / 5
Trigger Term Quality	Includes natural bilingual triggers — 'infographic', '信息图', 'visual summary', '可视化' — giving good keyword coverage, but common variations like 'infographics' (plural), 'diagram', and 'data visualization' that appear in the frontmatter are absent from the description itself.	4 / 5
Distinctiveness Conflict Risk	The infographic/信息图 niche is mostly distinct with specific triggers, but the broader terms 'visual summary' and '可视化' carry minor overlap risk with general data-visualization skills, keeping it just below the minimal-conflict anchor.	4 / 5
	Total	17 / 20 Passed

Validation

68%

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 — 11 / 16 Passed

Validation for skill structure

Criteria	Description	Result
skill_md_line_count	SKILL.md is long (555 lines); consider splitting into references/ and linking	Warning
metadata_version	'metadata.version' is missing	Warning
metadata_field	'metadata' should map string keys to string values	Warning
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning
referenced_paths_exist	Referenced path issues: 1 missing	Warning

	Total	11 / 16 Passed

Repository: OpenSenseNova/SenseNova-Skills
Path: skills/sn-infographic/SKILL.md
Commit: 5b4cb5b

Reviewed: 9 hours 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.