Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/guanyang/super-publishernpx agentmods add skills/guanyang/super-publisher/sticker-factoryWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/guanyang/super-publisher/sticker-factory)<a href="https://agentmods.dev/skills/guanyang/super-publisher/sticker-factory"><img src="https://agentmods.dev/badge/skills/guanyang/super-publisher/sticker-factory/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/guanyang/super-publisher/sticker-factory"><img src="https://agentmods.dev/badge/skills/guanyang/super-publisher/sticker-factory.svg" alt="Reviewed on agentmods" width="80" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00065 | $0.01090 |
| Opus 5.5 | $0.00026 | $0.00436 |
| Sonnet 5.5 | $0.00013 | $0.00218 |
| Haiku 4.5 | $0.00006 | $0.00109 |
Grade A, and why
sticker-factory scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 1mo ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 68 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Sticker Factory (Auto-Generator & Packer)
This skill serves as an Automated Production Line that orchestrates the entire lifecycle of sticker creation: from AI generation to WeChat-compliant asset packaging.
Execution Workflow
Step 1: Generate Sticker Grid
Adhere to the Universal Grid Logic defined in skills/grid-sticker-generator/SKILL.md.
-
Prompt Construction:
- Core: User's described character/theme.
- Format Constraints (CRITICAL): Inherit all Visual Design Standards from
grid-sticker-generator(4x4 Grid, No Text, Flat Vector). - Content Logic:
- Default: Load the Office Worker Template (
references/office_worker_template.md) from the generator skill to fill slots with office memes. - Custom: If user specifies a different theme, generate 16 varied actions relevant to that theme satisfying the grid constraints.
- Default: Load the Office Worker Template (
-
Action:
- Call
generate_imagewith the constructed prompt.
- Call
Step 2: Auto-Process with Sticker Maker
Once the image is successfully generated, immediately trigger the packaging robot.
-
Command:
./skills/wechat-sticker-maker/scripts/run.sh "PATH_TO_GENERATED_IMAGE" --output "OUTPUT_DIR" --layout 4x4- PATH_TO_GENERATED_IMAGE: The absolute path returned by the
generate_imagetool. - OUTPUT_DIR: If user specified a custom path, use it. Otherwise, default to
output/stickers_[theme].
- PATH_TO_GENERATED_IMAGE: The absolute path returned by the
-
Metadata Auto-Population (CRITICAL): Before moving to the next step, the Agent must:
- Automatically edit and fill in
info.txtandmeta.txtwith actual names, descriptions, and sticker meaning words, replacing the template placeholders, based on the theme generated. - Copy the original generated grid image into the output folder (e.g. as
source.pngorgrid_image.png).
- Automatically edit and fill in
Step 3: Generate Matching WeChat Sticker Assets
Orchestrate the design of matching promotional materials based on the generated IP character using skills/wechat-sticker-assets-designer/SKILL.md.
What ships with it
1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 1mo ago First seen · 68 lines · 65 tokens per session scan A e6e8b474c3e6
sticker-factory is a skill published in the GitHub repository guanyang/super-publisher (33 stars, last pushed 15d ago), licensed MIT. It adds 65 tokens to every session and 1,090 once invoked, about $0.0003 per session on Opus 5.5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
skillpack-creator
Create a reusable SkillPack from a successful completed task. Use when the user wants to convert a one-off research, coding, analysis, or content workflow into a distributable local SkillPack with skillpack.json, local skills under skills/, starter prompts, start scripts, and an optional zip package.
skill-creator
Create new skills, modify and improve existing skills, and measure skill performance. Use when users want to create a skill from scratch, edit, or optimize an existing skill, run evals to test a skill, benchmark skill performance with variance analysis, or optimize a skill's description for better triggering accuracy.
find-skills
Use when automatically discover, evaluate, and activate community skills when local skills don't cover user needs. Includes credibility scoring and safety checks for complete OpenClaw self-sufficiency.
writing-skills
Use when creating new skills, editing existing skills, or verifying skills work before deployment.
Comprehensive PDF manipulation toolkit for extracting text and tables, creating new PDFs, merging/splitting documents, and handling forms. When GLM needs to fill in a PDF form or programmatically process, generate, or analyze PDF documents at scale.
frontend-design
Transform UI style requirements into production-ready frontend code with systematic design tokens, accessibility compliance, and creative execution. Use when building websites, web applications, React/Vue components, dashboards, landing pages, or any web UI requiring both design consistency and aesthetic quality.