Live survey304 models · 14 providers · 22,792 auditsAudited grill-with-docs · SAFE →What changedHow we verifyllms.txt

Agent skill · Audited from source

ss-motion

skill · bitjaru/styleseedMIT licenceAudited 31 Oct 2026 · source 44baa08a77f7

★ 994pushed 3 days ago
!CAUTIONGrade B · 81/100 · 24 findings · 44baa08
994repo stars · whole bitjaru/styleseed

Is it safe? With care — CAUTION, grade B (81/100). We read this skill's source at commit 44baa08a77f7 and observed filesystem, network and shell access and no hard-coded secrets. The audit raised 24 findings, 0 critical or high. What it does: Build, improve, or inspect UI with StyleSeed. Preserves project design choices and routes setup, layout, tokens, review, rendered verification, and updates through one entry point.

Ask an AI about this pageGChatGPTCClaudePPerplexityGeGeminiXGrok
More
Cite

Cite this page

ModelsAtlas. “ss-motion (bitjaru/styleseed)”. Retrieved 31 Oct 2026. https://modelsatlas.com/skills/bitjaru/ss-motion

3 skills are called “ss-motion”. You are viewing bitjaru/styleseed.

Trust audit

Audit 0.4.1 · source read 31 Oct 2026

Trust score81/100!CAUTION B
0 critical0 high8 medium10 low6 info

CAUTION means the audit found things worth knowing before you trust this skill. Grade B is shared by 16,667 of 17,602 audited skills.

What the source does

  • FilesystemDeclared6 observations
  • NetworkDeclared7 observations
  • ShellDeclared5 observations
  • DependenciesNot pinnedSome versions float
  • SecretsNone foundNo keys in source

Five audit layers

LayerWhat we checkResultFindings
L0 ProvenanceRepo owner, licence, archive status, activityWARN11
L1 Static sourceSecrets, path traversal, supply chain, hidden codeWARN12
L2 InstructionsPrompt injection, authority framing, hidden directivesPASS1
L3 InventoryThe files and declarations match the sourcePASS0
L4 SandboxRun in isolation and watch behaviourSKIPPED why0

Gates applied: no behavioural pass.

Findings (24)

MEDIUMInventory / provenanceinv.binary · .styleseed/evidence/site-home/baseline-bf07a56/recordings/hero-motion.webm
F-13 Inventory / provenanceCWE-1104Layer L0
hero-motion.webm
Why
a compiled or binary member cannot be reviewed from source
Fix
ship source, or explain the binary in the README
MEDIUMInventory / provenanceinv.binary · .styleseed/evidence/site-home/baseline-bf07a56/recordings/hero-reduced-motion.webm
F-13 Inventory / provenanceCWE-1104Layer L0
hero-reduced-motion.webm
Why
a compiled or binary member cannot be reviewed from source
Fix
ship source, or explain the binary in the README
MEDIUMInventory / provenanceinv.binary · .styleseed/evidence/site-home/final-21937b8/recordings/hero-motion.webm
F-13 Inventory / provenanceCWE-1104Layer L0
hero-motion.webm
Why
a compiled or binary member cannot be reviewed from source
Fix
ship source, or explain the binary in the README
MEDIUMInventory / provenanceinv.binary · .styleseed/evidence/site-home/final-21937b8/recordings/hero-reduced-motion.webm
F-13 Inventory / provenanceCWE-1104Layer L0
hero-reduced-motion.webm
Why
a compiled or binary member cannot be reviewed from source
Fix
ship source, or explain the binary in the README
MEDIUMInventory / provenanceinv.binary · .styleseed/evidence/site-home/plugin-920e1df/recordings/hero-motion.webm
F-13 Inventory / provenanceCWE-1104Layer L0
hero-motion.webm
Why
a compiled or binary member cannot be reviewed from source
Fix
ship source, or explain the binary in the README
MEDIUMNetwork egressnet.raw_ip · demo-pricing/scripts/capture-palettes.mjs:9
F-04 Network egressCWE-200 · CWE-319Layer L1
const baseUrl = process.env.STYLESEED_CAPTURE_URL || "http://127.0.0.1:4177";
Why
No further detail recorded for this rule.
Fix
—
MEDIUMNetwork egressnet.raw_ip · demo-pricing/scripts/test-try.mjs:20
F-04 Network egressCWE-200 · CWE-319Layer L1
const base = `http://127.0.0.1:${port}`;
Why
No further detail recorded for this rule.
Fix
—
LOWFilesystem / pathfs.traversal · demo-pricing/app/architecture/page.tsx:4
F-05 Filesystem / pathCWE-22 · CWE-59Layer L1
import versionInfo from "../../public/version.json";
Why
No further detail recorded for this rule.
Fix
—
LOWFilesystem / pathfs.traversal · demo-pricing/app/evaluate/page.tsx:6
F-05 Filesystem / pathCWE-22 · CWE-59Layer L1
import versionInfo from "../../public/version.json";
Why
No further detail recorded for this rule.
Fix
—
LOWFilesystem / pathfs.traversal · demo-pricing/app/showcase/_renderers/chat.tsx:7
F-05 Filesystem / pathCWE-22 · CWE-59Layer L1
import { MESSAGES } from "../../chat-data";
Why
No further detail recorded for this rule.
Fix
—
LOWFilesystem / pathfs.traversal · demo-pricing/app/showcase/_renderers/pricing.tsx:8
F-05 Filesystem / pathCWE-22 · CWE-59Layer L1
import { TIERS } from "../../pricing/pricing-data";
Why
No further detail recorded for this rule.
Fix
—
LOWFilesystem / pathfs.traversal · demo-pricing/scripts/build-spacing-proof.mjs:5
F-05 Filesystem / pathCWE-22 · CWE-59Layer L1
import { spacingCss } from '../../engine/.claude/skills/styleseed/workflows/ss-resolve/scripts/spacing-contract.mjs';
Why
No further detail recorded for this rule.
Fix
—
LOWNetwork egressnet.raw_ip · docs/NEXT-RUNTIME-IMPLEMENTATION-PLAN.md:1396
F-04 Network egressCWE-200 · CWE-319Layer L1
node demo-pricing/scripts/capture-artifact-evidence.mjs --base-url http://127.0.0.1:3000 --all
Why
No further detail recorded for this rule.
Fix
—
LOWNetwork egressnet.raw_ip · examples/wanted-design-case/README.md:30
F-04 Network egressCWE-200 · CWE-319Layer L1
Open `http://127.0.0.1:43871/?view=list`, `?view=detail`, or `?view=decisions`.
Why
No further detail recorded for this rule.
Fix
—
LOWNetwork egressnet.raw_ip · examples/wanted-design-case/capture.mjs:7
F-04 Network egressCWE-200 · CWE-319Layer L1
const baseURL = process.env.STYLESEED_CASE_URL || 'http://127.0.0.1:43871/';
Why
No further detail recorded for this rule.
Fix
—
LOWSupply chainsupply.unpinned · demo-pricing/package.json
F-08 Supply chainCWE-829 · CWE-1357Layer L1
@radix-ui/react-accordion, @radix-ui/react-avatar, @radix-ui/react-checkbox, @radix-ui/react-dialog, @radix-ui/react-dropdown-menu, @radix-ui/react-label, @radix-ui/react-popover, @radix-ui/react-prog
Why
32 dependency range(s) float
Fix
pin exact versions or ship a lockfile
LOWSupply chainsupply.unpinned · engine/scaffold/package.json
F-08 Supply chainCWE-829 · CWE-1357Layer L1
@radix-ui/react-accordion, @radix-ui/react-alert-dialog, @radix-ui/react-avatar, @radix-ui/react-checkbox, @radix-ui/react-dialog, @radix-ui/react-dropdown-menu, @radix-ui/react-label, @radix-ui/react
Why
32 dependency range(s) float
Fix
pin exact versions or ship a lockfile
INFOInventory / provenanceinv.oversize · .styleseed/evidence/site-docs/baseline-bf07a56/renders/desktop-loaded.png
F-13 Inventory / provenanceCWE-1104Layer L0
.styleseed/evidence/site-docs/baseline-bf07a56/renders/desktop-loaded.png
Why
1477514 bytes not read
Fix
—
INFOInventory / provenanceinv.oversize · .styleseed/evidence/site-docs/baseline-bf07a56/renders/mobile-loaded.png
F-13 Inventory / provenanceCWE-1104Layer L0
.styleseed/evidence/site-docs/baseline-bf07a56/renders/mobile-loaded.png
Why
1076086 bytes not read
Fix
—
INFOInventory / provenanceinv.oversize · .styleseed/evidence/site-docs/final-21937b8/renders/desktop-loaded.png
F-13 Inventory / provenanceCWE-1104Layer L0
.styleseed/evidence/site-docs/final-21937b8/renders/desktop-loaded.png
Why
1477514 bytes not read
Fix
—
INFOInventory / provenanceinv.oversize · .styleseed/evidence/site-docs/final-21937b8/renders/mobile-loaded.png
F-13 Inventory / provenanceCWE-1104Layer L0
.styleseed/evidence/site-docs/final-21937b8/renders/mobile-loaded.png
Why
1076086 bytes not read
Fix
—
INFOInventory / provenanceinv.oversize · .styleseed/evidence/site-docs/plugin-920e1df/renders/desktop-loaded.png
F-13 Inventory / provenanceCWE-1104Layer L0
.styleseed/evidence/site-docs/plugin-920e1df/renders/desktop-loaded.png
Why
1477514 bytes not read
Fix
—
INFOPrompt injectionprompt.credential_read · research/design-judgment/README.md:129
F-01 Prompt injectionCWE-94 · CWE-1427Layer L2
build or launch candidate code, load credentials, or operate a remote service. Use canonical routes
Why
asks the agent to read credentials
Fix
—

Audit 0.4.1 · source sha 44baa08a77f7 · 31 Oct 2026Report an issue or request a re-scan

Provenance

Who published it, and what the verdict is pinned to

  • Publisherbitjaru GitHub userOwner of the repository this skill is read from
  • Source folderbitjaru/styleseedThe exact folder we audited
  • LicenceMITAs the repository states it
  • Commit pinned for this verdict44baa08a77f7A new audit runs when the source changes
  • Repository statusNot archivedLast push 3 days ago
  • Sandboxed runNot runSkills are read, not executed; layer L4 is skipped

What it tells the agent

Full source on GitHub ↗

Its description: Build, improve, or inspect UI with StyleSeed. Preserves project design choices and routes setup, layout, tokens, review, rendered verification, and updates through one entry point.

---
name: styleseed
description: Build, improve, or inspect UI with StyleSeed. Preserves project design choices and routes setup, layout, tokens, review, rendered verification, and updates through one entry point.
---

# StyleSeed

Use the user's goal to choose one first workflow below. This is the only registered core
skill; the 22 workflows and their executable dependencies ship inside this directory.
Read only the selected workflow, then references needed for that task.

## Registry-first artifact boundary

When `.styleseed/project.json` and `.styleseed/artifacts/index.json` exist, resolve the requested
artifact first. Read its `.styleseed/bundles/<artifact-id>.md` and manifest. A partial or invalid
registry is an error; never fall back to the global legacy bundle. Legacy projects may use
`.styleseed/effective-rules.md` only when no registry exists.

Before the first workflow in a project/task session, follow the
[update preflight](workflows/ss-update/references/update-preflight.md).

## Working contract

- Preserve approved project design choices. Support expert judgment; a score is not human acceptance.
- Resolve the current artifact first. For multiple plausible artifacts, ask one bounded clarification question.
- Never fan out to run every workflow. Choose exactly one first workflow; it may call the required gates.
- Honor the user's authorized scope. Audit, score, verify, and status requests do not authorize edits.
  Workflow metadata records the intended tool/scope boundary even though it is not host registration metadata.
- Paths in workflow files are relative to those files. Resolve installed scripts from this skill's
  actual directory, never assume a particular agent folder or download a missing sibling skill.
- In older instructions, `/ss-build`, `$ss-build`, and other `ss-*` names mean the corresponding
  internal workflow. Read `workflows/<name>/WORKFLOW.md`; do not invoke an unregistered skill.
  Users may say `StyleSeed build`, `$styleseed build`, or the old workflow name in natural language.
- Learning is an optional extension, not part of the core install. Only for explicit learning capture,
  use separately installed `ss-learn`; if absent, report that dependency and never auto-install it.

## Choose exactly one first workflow

| Request | Read |
|---|---|
| Build or redesign a screen, page, or component | [build](workflows/ss-build/WORKFLOW.md) |
| First setup or missing design lock | [setup](workflows/ss-setup/WORKFLOW.md) |
| Explore creative directions; direction not yet selected | [studio](workflows/ss-studio/WORKFLOW.md) |
| Use screenshot, URL, Figma export, or existing UI as a reference | [reference](workflows/ss-reference/WORKFLOW.md) |
| What is wrong with this screen; UX critique | [audit](workflows/ss-audit/WORKFLOW.md) |
| Review implementation against project design rules | [review](workflows/ss-review/WORKFLOW.md) |
| Score implementation or run code/evidence gates | [score](workflows/ss-score/WORKFLOW.md) |
| Inspect rendered output, screenshot, or spacing in pixels | [verify](workflows/ss-verify/WORKFLOW.md) |
| Change spacing/density or another single design axis | [dial](workflows/ss-dial/WORKFLOW.md) |
| Apply an aesthetic profile | [restyle](workflows/ss-restyle/WORKFLOW.md) |
| Brand color, semantic palette, or design tokens | [tokens](workflows/ss-tokens/WORKFLOW.md) |
| Named animation or motion treatment | [motion](workflows/ss-motion/WORKFLOW.md) |
| Specifically scaffold a page | [page](workflows/ss-page/WORKFLOW.md) |
| Specifically generate a reusable component | [component](workflows/ss-component/WORKFLOW.md) |
| Compose existing primitives into a UI pattern | [pattern](workflows/ss-pattern/WORKFLOW.md) |
| Accessibility audit and requested fixes | [a11y](workflows/ss-a11y/WORKFLOW.md) |
| Quick design lint | [lint](workflows/ss-lint/WORKFLOW.md) |
| Navigation and user flows | [flow](workflows/ss-flow/WORKFLOW.md) |
| UX microcopy | [copy](workflows/ss-copy/WORKFLOW.md) |
| Loading, empty, success, or error states | [feedback](workflows/ss-feedback/WORKFLOW.md) |
| Update installation or consolidate old skill entries | [update](workflows/ss-update/WORKFLOW.md) |
| Compile rules, inspect local install/bundle/evidence health | [resolve](workflows/ss-resolve/WORKFLOW.md) |

For status-only requests use resolve's read-only `scripts/styleseed-doctor.mjs`; do not update,
recompile, or visually inspect instead. For vague requests infer the first step from project state
and the user's goal; ask only when an unresolved choice materially changes the work.

Excerpt, first 4,580 characters of SKILL.md, verbatim from the audited commit. It is text from someone else’s repository, quoted so you can judge it before your agent reads it.

Install

Pinned to the audited commit 44baa08

Download folder ↗
npx skills add bitjaru/styleseed
git clone https://github.com/<your-name>/styleseed.git
npx skills add
claude plugin install styleseed@styleseed
git clone https://github.com/bitjaru/styleseed.git /tmp/styleseed

Commands as the repository documents them: shown, never run by us. Our verdict covers commit 44baa08a77f7 only.

Works in which agents?

What its own text says, not a test

AgentStatusMore
Claude CodeMentioned in its text, not testedSkills for Claude Code · About Claude Code
CodexMentioned in its text, not testedSkills for Codex · About Codex
GitHub CopilotMentioned in its text, not testedSkills for GitHub Copilot · About GitHub Copilot
CursorMentioned in its text, not testedSkills for Cursor · About Cursor
Gemini CLIMentioned in its text, not testedSkills for Gemini CLI · About Gemini CLI
WindsurfMentioned in its text, not testedSkills for Windsurf · About Windsurf
“Mentioned” means the skill’s text names the agent. We have not run it there.

Audit history

Every audit, every source change

  1. !CAUTION B 81 / 100

    first audit · source 44baa08a77f7

README badge

For maintainers · shows the latest audit

ModelsAtlas: CAUTION BMODELSATLASCAUTION · B
[![ModelsAtlas: CAUTION B](https://modelsatlas.com/skills/bitjaru/ss-motion/badge.svg)](https://modelsatlas.com/skills/bitjaru/ss-motion/)

The badge shows our verdict and grade for this skill, and links back to this page. It changes when the audit does.

Add this badge to your README

[![ModelsAtlas: CAUTION B](https://modelsatlas.com/skills/bitjaru/ss-motion/badge.svg)](https://modelsatlas.com/skills/bitjaru/ss-motion/)

Questions about ss-motion

What does the ss-motion skill do?
Open-source design-method engine for Claude Code, Codex & Cursor. One agent skill with 22 internal workflows for fixed design judgment, multiple grammars, semantic palettes, reference compilation, and evidence-verified UI. MIT.
Is ss-motion safe to install?
With care. The audit graded it B (81/100) and found 24 things worth knowing before you trust this skill, listed below with the exact line each was found on.
What can ss-motion access on my machine?
The audit observed that it reaches the network, runs shell commands and reads or writes files. Each of those is consistent with what it says it does. Secrets in the source: none found.
Which assistants does ss-motion work with?
Its documentation mentions claude-code, codex, copilot, cursor, gemini-cli and windsurf. That is what the text claims, not a compatibility test we ran.
How current is this page?
The grade is for one exact copy of the source (44baa08a77f7), read on 2026-10-31. The repository is watched, and a new audit runs when it changes — this is the first audit.

Sources

Spotted something wrong? Report a correction · Methodology

Keep going in your AI

Opens with this page as the source. We add nothing else to the prompt.