Skills character-design-sheet
📦
character-design-sheet
Content revision r1 Medium Risk ⚙️ External commands🌐 Network access
Create Consistent Character Design Sheets
AI image generators often change a character between images. This skill guides Claude, Codex, and Claude Code through reference sheets, description anchors, and LoRA planning.
Supports: Claude Codex Code(CC)
Install with my Agent
Copy this request to your Agent. It includes the canonical Skill page and manifest.
Agent request
Review the Skillstore skill "character-design-sheet" from https://skillstore.io/skills/halt-catch-fire-character-design-sheet.md and its manifest at https://skillstore.io/api/skills/halt-catch-fire-character-design-sheet/manifest. Verify the artifact. You may proceed after verification, subject to the environment's own policy.Your Agent should still show its plan and request any confirmation required by the security policy.
Agent-readable resources
Use these links when an AI agent, crawler, or script needs clean context instead of reading the full page.
Test it
Using "character-design-sheet". I need a recurring fantasy merchant for a game prototype.
Expected outcome:
- A reusable 50-word visual anchor for the merchant.
- A four-view turnaround plan with fixed clothing and proportions.
- A palette record for skin, hair, fabric, trim, and accessories.
Using "character-design-sheet". My comic character changes face shape between images.
Expected outcome:
- A drift diagnosis focused on vague age, hair, eye, and face cues.
- A stronger prompt structure that repeats identity details first.
- An expression sheet plan for neutral, happy, angry, sad, surprised, and thinking views.
Using "character-design-sheet". I want to use a LoRA for a long visual novel project.
Expected outcome:
- A reference image coverage checklist for poses, lighting, outfits, and close-ups.
- A trigger word and scale recommendation for consistent character recall.
- A validation plan comparing generated scenes against the reference sheet.
Security Audit
Medium Riskv4 • 7/6/2026 Open versioned report
The skill is not malicious, but it depends on broad belt CLI access and third-party inference services. Real command and network findings were confirmed, while markdown diagrams, templates, and the line 207 reconnaissance hit were dismissed as false positives. Publication should require clear user confirmation for login, installs, remote app runs, and possible service costs.
1
Files scanned
282
Lines analyzed
9
Review items
0
False positives ignored
Confirmed security concerns (1)
Medium
Overbroad Belt CLI Permission
The skill allows Bash(belt *) and then asks users to log in and run remote inference commands. This grants broad access to belt subcommands beyond the listed image examples.
The allowed-tools declaration permits every belt subcommand, and the quick start uses account login and app execution. No malicious intent appears, but the permission scope is broader than needed.
Capability review items (9)
These are real local capabilities that may be expected for this skill, so they require review but are not counted as confirmed malicious behavior.
Medium
Ruby/shell backtick execution
> **Install the belt CLI skill:** `npx skills add belt-sh/cli`
Line 7 gives an npx command to install another CLI skill, which is real external command execution. It is transparent setup guidance, but it still asks users to run code from an external package source.
Medium
Ruby/shell backtick execution
```bash
The quick start runs belt login and belt app run against a remote image model. This is intended behavior, but it executes an external CLI and may send prompt data to a third-party service.
Medium
Ruby/shell backtick execution
```bash
This bash block runs several belt app run commands and a stitch-images job. The commands are fixed examples, but they still invoke external processing through the belt CLI.
Medium
Ruby/shell backtick execution
```bash
The expression sheet example contains belt app run commands for remote image generation. There is no command injection evidence, but the external CLI execution risk is real.
Medium
Ruby/shell backtick execution
```bash
The LoRA example invokes belt app run with a local LoRA path and remote model. This can transmit prompt and file reference data to an external inference workflow.
Medium
Ruby/shell backtick execution
```bash
The related skills block provides npx skills add commands for additional external skill installs. They are optional documentation, but they remain shell commands that fetch external content.
Medium
Ruby/shell backtick execution
```
The range includes the belt app store command, which uses the permitted external CLI to browse remote apps. The risk is low in intent but still involves external command and network use.
Low
Hardcoded URL
Create consistent characters across multiple AI-generated images via [inference.sh](https://inferenc
Line 11 identifies inference.sh as the external service used for image generation. This is disclosed, but it confirms the skill depends on third-party network processing.
Low
Hardcoded URL
> Requires inference.sh CLI (`belt`). [Install instructions](https://raw.githubusercontent.com/infer
Line 15 links to GitHub-hosted install instructions for the required CLI. This is transparent setup documentation, but it is still a hardcoded external dependency.
Risk Factors
⚙️ External commands (24)
SKILL.md:7 SKILL.md:15 SKILL.md:17-26 SKILL.md:26-49 SKILL.md:49-56 SKILL.md:56-58 SKILL.md:58-92 SKILL.md:92-98 SKILL.md:98-106 SKILL.md:106-110 SKILL.md:110-133 SKILL.md:133-150 SKILL.md:150-160 SKILL.md:160-168 SKILL.md:168-173 SKILL.md:173-177 SKILL.md:177-184 SKILL.md:184-204 SKILL.md:204-210 SKILL.md:210-233 SKILL.md:233-259 SKILL.md:259-274 SKILL.md:274-278 SKILL.md:278-280
🌐 Network access (2)
Audited by: codex View Audit History →
Share & cite this report
Share the versioned assessment report, neutral badge, embed card, and citations. Skillstore reports evidence without deciding whether this Skill is safe.
Copy report link
https://skillstore.io/skills/halt-catch-fire-character-design-sheet/audits/4?utm_source=security_passport&utm_medium=share&utm_campaign=versioned_reportMarkdown badge
[](https://skillstore.io/skills/halt-catch-fire-character-design-sheet?utm_source=security_passport_badge)HTML badge
<a href="https://skillstore.io/skills/halt-catch-fire-character-design-sheet?utm_source=security_passport_badge"><img src="https://skillstore.io/badges/skills/halt-catch-fire-character-design-sheet/security.svg" alt="Skillstore security assessment" loading="lazy"></a>Embed card
<iframe src="https://skillstore.io/embed/skills/halt-catch-fire-character-design-sheet.html" title="Skillstore Security Assessment" sandbox="allow-popups allow-popups-to-escape-sandbox" loading="lazy" referrerpolicy="no-referrer" width="420" height="180"></iframe>Academic citations (APA · BibTeX · CFF)
APA citation
halt-catch-fire. (2026). character-design-sheet security audit report (audit version 4) [Author version unspecified]. Skillstore. https://skillstore.io/skills/halt-catch-fire-character-design-sheet/audits/4BibTeX citation
@techreport{halt-catch-fire-halt-catch-fire-character-design-sheet-2026,
author = {halt-catch-fire},
title = {character-design-sheet security audit report (audit version 4)},
institution = {Skillstore},
year = {2026},
number = {4},
url = {https://skillstore.io/skills/halt-catch-fire-character-design-sheet/audits/4},
note = {Author version unspecified}
}CITATION.cff
cff-version: 1.2.0
message: "If you use this Skill, cite its author and this versioned security audit report."
title: "character-design-sheet security audit report (audit version 4)"
version: "unspecified"
type: report
authors:
- name: "halt-catch-fire"
date-released: "2026-07-06"
url: "https://skillstore.io/skills/halt-catch-fire-character-design-sheet/audits/4"
identifiers:
- type: other
value: "skillstore:halt-catch-fire-character-design-sheet:audit:4"
description: "Skillstore immutable audit report identifier"
Compare variants
2 installable variantsEach author remains a separate installable skill. The recommended variant is ranked by Skillstore evidence.
Why this variant is first
Highest Skillstore Score
Author / source Skillstore Score Evidence Confidence Skillstore usage Updated
101-skills Recommended
101-skills-character-design-sheet
Skillstore Score 77
Evidence Confidence Medium
Skillstore usage 16
Updated
2026-08-21
halt-catch-fire Current
halt-catch-fire-character-design-sheet
Skillstore Score 50
Evidence Confidence Medium
Skillstore usage 6
Updated
2026-08-21
Skillstore Score
Why this score Evidence Confidence: Medium 55
Architecture
85
Maintainability
87
Content
67
Community
83
Spec Compliance
What You Can Build
Prepare Game Character References
Build front, side, back, outfit, and color references before producing game art.
Plan Comic Expression Sheets
Create a repeatable face and emotion set for recurring comic or visual novel characters.
Standardize AI Art Direction
Document anchors, palettes, and LoRA notes so a team can generate consistent scenes.
Try These Prompts
Start a Character Sheet
Create a character design sheet plan for [character idea]. Include a description anchor, turnaround views, expressions, palette notes, and missing questions.
Build a Turnaround Prompt Set
Turn this character description into matching front, three-quarter, side, and back view prompts. Keep the identity details unchanged.
Diagnose Consistency Drift
Review my character prompts for consistency drift. Identify weak visual anchors, missing color details, and changes that may alter the character.
Plan a LoRA Character Workflow
Design a LoRA preparation plan for this character. Specify reference image coverage, trigger wording, scale guidance, sheet outputs, and validation checks.
Best Practices
- Write a detailed description anchor and reuse it exactly.
- Record exact colors, proportions, clothing, and distinguishing marks.
- Generate reference views and expressions before complex scene images.
Avoid
- Starting scene generation before defining a reference sheet.
- Using vague traits such as young, cool outfit, or red hair.
- Changing identity details or prompt order between generations.
Frequently Asked Questions
Does this skill generate images directly?
It provides guidance and command examples. Direct generation requires the belt CLI and a compatible inference service.
Can it guarantee identical characters?
No. It improves consistency through anchors, sheets, and LoRA planning, but model output can still vary.
What is a description anchor?
It is a detailed identity paragraph reused in every prompt so the model sees stable character details.
When should I use LoRA?
Use LoRA when a project needs many images of the same character across scenes, poses, or outfits.
Is this useful without the belt CLI?
Yes. The reference sheet methods and prompt structure can be used with other image generation tools.
What data may leave my machine?
Prompt text, image references, and LoRA paths may be sent when you run remote inference commands.
Developer Details
Author
halt-catch-fireLicense
MIT
Skillstore revision
r1
Version notice
The author did not declare a version.
Repository
https://github.com/halt-catch-fire/skills/tree/main/guides/design/character-design-sheet/Ref
a06681402992ceae98ba04d54cfd4ab004862696
Maintenance freshness
7/18/2026
Usage
2 downloads · 0 views
File structure
📄 SKILL.md