Download skills/sn-image-resume/SKILL.md from the publisher, or copy the path and open the repository. PlugMCP lists the skill and does not host the file.
Where does sn-image-resume live?
The publisher keeps it at https://github.com/OpenSenseNova/SenseNova-Skills.
Which agents can use sn-image-resume?
Claude, Cursor, and Codex can read a SKILL.md you add from the publisher's repository.
|
name: sn-image-resume
description: |
Generates a designed portfolio-resume image from resume content provided in conversation text.
Extracts optional style instructions, converts the resume into a fixed portfolio-resume layout prompt,
and generates the final image through sn-image-base. Use when user asks to create "resume image",
"portfolio resume", "简历图", "简历海报", or "个人简历视觉设计".
metadata:
project: SenseNova-Skills
tier: 1
category: scene
priority: 8
user_visible: true
triggers:
"resume image"
"portfolio resume"
"visual resume"
"resume poster"
"CV image"
"简历图"
"简历海报"
"可视化简历"
"个人简历视觉设计"
"作品集简历"
sn-image-resume
Resume image generation scene skill (tier 1), relying on the sn-text-optimize and sn-image-generate tools provided by (tier 0).
sn-image-base
Features:
Accepts resume content directly from conversational text
Supports optional user-provided style direction
Applies the fixed portfolio-resume layout rules in prompts/resume.md
Generates a tall designed resume image through sn-image-generate
Non-goals
Editing or polishing a plain text resume document without generating an image
Parsing uploaded resume files as the primary input format
Creating a conventional single-column ATS resume
Guaranteeing exact preservation of every long paragraph when the image layout requires compression
Input Specification
Parameter
Type
Default Value
Description
resume_content
string
Required
Resume text provided by the user in conversation, including name, profile, education, experience, skills, projects, contact details, etc.
style
string
Optional
User-specified visual style, tone, color palette, profession aesthetic, or reference mood. May be embedded in resume_content.
aspect_ratio
string
9:16
Output aspect ratio. Allowed values: 2:3, 3:2, 3:4, 4:3, 4:5, 5:4, 1:1, 16:9, 9:16, 21:9, 9:21. Default is 9:16 (vertical) because the template is a tall stacked portfolio-resume page.
image_size
string
2k
Image size preset, 1k or 2k.
output_mode
string
friendly
Output mode: friendly or verbose.
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), so they do not need to be passed explicitly in normal use.
When encountering MissingApiKeyError or needing to specify a model: pass parameters explicitly via CLI. See $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.
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 result, and send final text/image to user
Worker Agent
Execute prompt generation and image generation, then 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 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 low-level API calls execute directly through sn-image-base, without spawning nested subagents
Workflow
Main Agent Workflow
Extract resume_content, optional style, aspect_ratio (default 9:16), image_size (default 2k), and output_mode (default friendly) from the user request
Validate that resume_content is non-empty and contains enough resume information to generate a meaningful page
Validate aspect_ratio against the allowed values: 2:3, 3:2, 3:4, 4:3, 4:5, 5:4, 1:1, 16:9, 9:16, 21:9, 9:21. If the user-provided value is not in this list, inform the user and fall back to the default 9:16
Send uniform preflight message: "Using sn-image-resume skill to generate a resume image, please wait..."
Start Worker Agent, passing in complete parameters and working directory
When Worker Agent returns:
status=ok: send a short summary and the generated image
status=error: report the real error field content to the user
Worker Agent Workflow
Worker Agent receives resume_content, style, aspect_ratio, image_size, output_mode, and the working directory of this skill (SKILL_DIR).
Step 0 — Initialization
Generate task_id using timestamp format YYYYMMDD_HHMMSS
Create temporary directory: /tmp/openclaw/sn-image-resume/<task_id>/ as TEMP_DIR
Use prompts/resume.md as the system prompt and call sn-text-optimize to convert the user resume content into a detailed image generation prompt.
USER_PROMPT=$(cat << EOF
Resume content:
$RESUME_CONTENT
Optional style instruction:
${STYLE:-No explicit style instruction. Infer an appropriate professional visual style from the resume content.}
Task:
Convert the resume content into a complete text-to-image prompt for a tall portfolio-resume image.
Follow the fixed layout, language, content mapping, typography, panel, and style translation rules in the system prompt.
Return only the final image generation prompt. Do not include explanations, markdown fences, or alternative options.
EOF
)
python "$SN_IMAGE_BASE/scripts/sn_agent_runner.py" sn-text-optimize \
--system-prompt-path "$SKILL_DIR/prompts/resume.md" \
--user-prompt "$USER_PROMPT" \
--output-format json
Parse JSON stdout and extract result as generation_prompt. If the process exits non-zero, returns invalid JSON, or result is empty, return status=error with the actual error.
Parse JSON stdout. If generation fails, return status=error with the actual error. The generated image path is $TEMP_DIR/resume.png.
Error Handling Rules
If required resume content is missing, ask the user to provide resume text before starting generation
If sn-text-optimize fails or returns an empty result, stop and report the real error
If sn-image-generate fails, stop and report the real error
Do not silently substitute a generic resume prompt when user content is incomplete or prompt generation fails
Do not invent factual resume details that the user did not provide; only reorganize, condense, and visually map provided information
Return Contract
After Worker Agent completes, its last message must be and only be the following JSON string (bare JSON, no code fences, no preceding or trailing text).
Download skills/sn-image-resume/SKILL.md from the publisher, or copy the path and open the repository. PlugMCP lists the skill and does not host the file.
Where does sn-image-resume live?
The publisher keeps it at https://github.com/OpenSenseNova/SenseNova-Skills.
Which agents can use sn-image-resume?
Claude, Cursor, and Codex can read a SKILL.md you add from the publisher's repository.