Lofisu Persona
zclllyybb/lofisu-identity-engine
LofiSu的行为人格Skill。基于GitHub公开数据(282次commit/150次README迭代/50+fork/100+contribution) 的Codex深度挖掘分析报告+小红书卖课行为报告的系统蒸馏， 提炼6个核心心智模型、8条决策启发式和完整的表达DNA。
Process screenshot-based UI/UX feedback to fix visual issues — use when users share screenshots of bugs
Install Skill Visual Feedback
$ npx skills add nyldn/claude-octopus --skill skill-visual-feedback -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install nyldn/claude-octopus skill-visual-feedback --agent claude-codeProject scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).
$ git clone --depth 1 https://github.com/nyldn/claude-octopus.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/skill-visual-feedback .claude/skills/skill-visual-feedback && rm -rf skills-srcUse ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.
Claude Code skills documentation · loads skills from .claude/skills/
Install the "skill-visual-feedback" agent skill from https://github.com/nyldn/claude-octopus/tree/main/skills/skill-visual-feedback into .claude/skills/skill-visual-feedback/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "skill-visual-feedback", then confirm the skill loads.Claude Code copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$skill-installer install https://github.com/nyldn/claude-octopus/tree/main/skills/skill-visual-feedbackType this inside Codex. $skill-installer <name> installs a curated skill from openai/skills. The installer writes to $CODEX_HOME/skills (default ~/.codex/skills). Restart Codex if the skill does not show up.
$ npx skills add nyldn/claude-octopus --skill skill-visual-feedback -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install nyldn/claude-octopus skill-visual-feedback --agent codexProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/nyldn/claude-octopus.git skills-src && mkdir -p .agents/skills && cp -r skills-src/skills/skill-visual-feedback .agents/skills/skill-visual-feedback && rm -rf skills-srcUse ~/.agents/skills/ instead of .agents/skills for a personal install.
Codex skills documentation · loads skills from .agents/skills/
Install the "skill-visual-feedback" agent skill from https://github.com/nyldn/claude-octopus/tree/main/skills/skill-visual-feedback into .agents/skills/skill-visual-feedback/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "skill-visual-feedback", then confirm the skill loads.Codex copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add nyldn/claude-octopus --skill skill-visual-feedback -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install nyldn/claude-octopus skill-visual-feedback --agent cursorProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/nyldn/claude-octopus.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/skills/skill-visual-feedback .cursor/skills/skill-visual-feedback && rm -rf skills-srcUse ~/.cursor/skills/ instead of .cursor/skills for a personal install.
Cursor skills documentation · loads skills from .cursor/skills/, .agents/skills/, .claude/skills/, .codex/skills/
Install the "skill-visual-feedback" agent skill from https://github.com/nyldn/claude-octopus/tree/main/skills/skill-visual-feedback into .cursor/skills/skill-visual-feedback/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "skill-visual-feedback", then confirm the skill loads.Cursor copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gemini skills install https://github.com/nyldn/claude-octopus.git --path skills/skill-visual-feedback--scope user (default) or --scope workspace; --path is the subfolder of the repo that holds the skill; --consent skips the security confirmation prompt.
$ npx skills add nyldn/claude-octopus --skill skill-visual-feedback -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install nyldn/claude-octopus skill-visual-feedback --agent gemini-cliProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/nyldn/claude-octopus.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/skills/skill-visual-feedback .gemini/skills/skill-visual-feedback && rm -rf skills-srcUse ~/.gemini/skills/ instead of .gemini/skills for a personal install, then run /skills reload.
Gemini CLI skills documentation · loads skills from .gemini/skills/, .agents/skills/
Install the "skill-visual-feedback" agent skill from https://github.com/nyldn/claude-octopus/tree/main/skills/skill-visual-feedback into .gemini/skills/skill-visual-feedback/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "skill-visual-feedback", then confirm the skill loads.Gemini CLI copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gh skill install nyldn/claude-octopus skill-visual-feedbackInstalls for Copilot at project scope by default; add --scope user for a personal install. Preview a skill first with gh skill preview. Needs GitHub CLI 2.90.0 or later (public preview).
$ npx skills add nyldn/claude-octopus --skill skill-visual-feedback -a github-copilotProject install goes to .agents/skills/; add -g for ~/.copilot/skills/.
$ git clone --depth 1 https://github.com/nyldn/claude-octopus.git skills-src && mkdir -p .github/skills && cp -r skills-src/skills/skill-visual-feedback .github/skills/skill-visual-feedback && rm -rf skills-srcUse ~/.copilot/skills/ instead of .github/skills for a personal install. Commit .github/skills so cloud agent and code review can use it.
GitHub Copilot skills documentation · loads skills from .github/skills/, .claude/skills/, .agents/skills/
Install the "skill-visual-feedback" agent skill from https://github.com/nyldn/claude-octopus/tree/main/skills/skill-visual-feedback into .github/skills/skill-visual-feedback/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "skill-visual-feedback", then confirm the skill loads.GitHub Copilot copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add nyldn/claude-octopus --skill skill-visual-feedback -a opencodeOpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.
$ gh skill install nyldn/claude-octopus skill-visual-feedback --agent opencodeProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/nyldn/claude-octopus.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/skills/skill-visual-feedback .opencode/skills/skill-visual-feedback && rm -rf skills-srcUse ~/.config/opencode/skills/ instead of .opencode/skills for a personal install.
OpenCode skills documentation · loads skills from .opencode/skills/, .claude/skills/, .agents/skills/
Install the "skill-visual-feedback" agent skill from https://github.com/nyldn/claude-octopus/tree/main/skills/skill-visual-feedback into .opencode/skills/skill-visual-feedback/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "skill-visual-feedback", then confirm the skill loads.OpenCode copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
Facts
- Skill name
skill-visual-feedback- GitHub stars
- 4.2k
- Used in
- 1 other repo
- Token cost
- ~2.6k tokens
- SKILL.md length
- 577 words
- Files
- 2
- Skills in repo
- 62
- Repo updated
- First seen
- Licence
- MIT
At a glance
Process screenshot-based UI/UX feedback to fix visual issues — use when users share screenshots of bugs
- Works in 8 steps: Visual Analysis → Code Investigation → Root Cause Analysis → …
- Users share screenshots of bugs
- SKILL.md covers Overview, When to Use, The Process and Common Patterns, plus 5 more sections
- Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md
What it does
Skill Visual Feedback is an agent skill from nyldn/claude-octopus. Process screenshot-based UI/UX feedback to fix visual issues — use when users share screenshots of bugs
Its SKILL.md is about 2.6k tokens, which your agent loads only when the skill is triggered. The skill folder holds 2 other files (for example `agents/openai.yaml`).
It sits in Frontend & Design, covering UI design. The repository describes itself as: Run multiple AI models against the same research, design, or coding task. Surface disagreements before you ship. The licence is MIT.
When your agent uses it
- Users share screenshots of bugs
- Tasks that involve UI design
Example prompts
- “/skill-visual-feedback”
Workflow steps
8 steps, taken from the step headings in SKILL.md.
What it can do on your machine
Read from SKILL.md and the folder at commit 4d152db. It shows what the files ask for, not the result of running them.
Tool permissions
Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.
From allowed-tools in the SKILL.md frontmatter.
Runs code
No scripts in the folder and no shell commands in SKILL.md (its code samples are markdown and bash).
From the folder's file list and the shell code blocks in SKILL.md.
Network
No URLs in SKILL.md.
From URLs in SKILL.md, links to its own repository left out.
Credentials
Names no API keys, tokens, secrets or passwords.
From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.
Context cost
Skill Visual Feedback loads about 2.6k tokens when it runs. Until then it costs about 31 tokens; SKILL.md has 577 words of instructions outside code blocks.
Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.
Safety
Auto-check passed
The automated check found no risky patterns in SKILL.md.
Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.
SKILL.md
The full file from nyldn/claude-octopus at commit 4d152db, republished under its MIT licence (© nyldn). 577 words, ~2,642 tokens.
Download SKILL.mdSave it as
.claude/skills/skill-visual-feedback/SKILL.md (or your agent's skills folder). This skill also uses 1 other file; get the full folder from GitHub.- name
- skill-visual-feedback
- description
- Process screenshot-based UI/UX feedback to fix visual issues — use when users share screenshots of bugs
- disable-model-invocation
- true
Host: Codex CLI — This skill was designed for Claude Code and adapted for Codex. Cross-reference commands use installed skill names in Codex rather than
/octo:*slash commands. Use the active Codex shell and subagent tools. Do not claim a provider, model, or host subagent is available until the current session exposes it. For host tool equivalents, seeskills/blocks/codex-host-adapter.md.
Visual Feedback Processing
Overview
Systematic approach to processing image-based UI/UX feedback, identifying visual issues, and implementing fixes.
Core principle: Analyze image → Identify issues → Locate code → Fix systematically → Verify visually.
When to Use
Use this skill when user provides:
- Screenshots with UI/UX problems
- "[Image]" prefix with description of visual issues
- Complaints about "messy UI" or "hot mess UX"
- Button styling or layout issues with visual examples
- "This should look like X but shows as Y" with images
Do NOT use for:
- Pure code issues without visual context
- Feature requests without UI mockups
- Performance or functional bugs
- Backend issues
The Process
Phase 1: Visual Analysis
When user provides image feedback:
Step 1: Acknowledge and Examine
I can see the screenshot showing [describe what you observe].
Let me analyze the visual issues:
**Observed Problems:**
1. [Issue 1: e.g., Button styles inconsistent]
2. [Issue 2: e.g., Layout misaligned]
3. [Issue 3: e.g., Colors don't match design system]
**Expected Behavior (from description):**
- [What user said it should be]
**Actual Behavior (from image):**
- [What the image shows]Step 2: Categorize Issues
| Issue Type | Examples |
|---|---|
| Styling | Colors, fonts, spacing, borders |
| Layout | Alignment, positioning, responsive behavior |
| Component | Wrong component used, missing component |
| State | Hover states, active states, disabled states |
| Consistency | Inconsistent patterns across UI |
**Issue Categories:**
- Styling: [list specific styling issues]
- Layout: [list layout issues]
- Component: [list component issues]
- State: [list state-related issues]
- Consistency: [list inconsistency issues]Phase 2: Code Investigation
Step 1: Locate Relevant Components
# Search for component files related to the issue
# Example: For settings page issuesUse Glob to find component files:
**/*settings*.{tsx,jsx,ts,js,vue,svelte}
**/*button*.{tsx,jsx,ts,js,vue,svelte}Use Grep to find specific elements:
# Search for className patterns
pattern: "className.*button|btn-"
# Search for style definitions
pattern: "style={{|styled\.|makeStyles"Step 2: Identify Styling System
**Styling Approach Detected:**
- [ ] CSS Modules
- [ ] Styled Components
- [ ] Tailwind CSS
- [ ] Emotion/styled
- [ ] Plain CSS
- [ ] CSS-in-JS (other)
**Design System:**
- [ ] Custom design system
- [ ] Material-UI
- [ ] Ant Design
- [ ] Chakra UI
- [ ] Other: [name]Step 3: Read Affected Files
Read the component files and associated styles to understand current implementation.
Phase 3: Root Cause Analysis
Step 1: Identify Why Issue Exists
Common root causes:
| Root Cause | Indicators |
|---|---|
| Inconsistent styling | Multiple ways to style same element |
| Missing design tokens | Hard-coded colors/spacing |
| Wrong component variant | Using primary when should use secondary |
| State not handled | Missing hover/active/disabled styles |
| Responsive issues | Fixed widths, missing breakpoints |
| Override conflicts | Specificity wars, !important overuse |
| Deprecated patterns | Old styling approach still in use |
**Root Cause Analysis:**
Issue: [specific visual problem]
Root Cause: [why it's happening]
Evidence: [code snippet or pattern showing the cause]
Impact:
- Affects: [which pages/components]
- Frequency: [how often users see this]
- Scope: [single instance or systemic]Step 2: Scope the Fix
**Fix Scope:**
Option 1: **Targeted Fix** (fix just this instance)
- Files to modify: [list]
- Risk: Low
- Coverage: Fixes reported issue only
Option 2: **Systematic Fix** (fix pattern everywhere)
- Files to modify: [list]
- Risk: Medium
- Coverage: Fixes all instances of this pattern
Option 3: **Design System Fix** (update base component)
- Files to modify: [design system files]
- Risk: Higher (affects many components)
- Coverage: Fixes root cause system-wide
**Recommendation:** [which option and why]Use AskUserQuestion to get user preference on scope.
Phase 4: Implementation
Step 1: Create Fix Plan
For each identified issue:
**Fix Plan:**
Issue: [description]
File: [file path]
Change: [what to change]
Before: [code snippet or description]
After: [code snippet or description]Step 2: Implement Fixes
Apply fixes one at a time, using Edit tool:
Fixing [Issue 1]...
- File: [path]
- Change: [description]
✓ Fixed
Fixing [Issue 2]...
- File: [path]
- Change: [description]
✓ FixedShow full SKILL.md (226 more words)Show less
Step 3: Ensure Consistency
If "everywhere" or "all instances" is mentioned:
# Search for all instances of the pattern
# Example: Find all primary buttonsUse Grep to find all instances, then fix each one:
**Pattern Search:** "button.*primary"
Found in:
1. src/components/Header.tsx:45
2. src/pages/Settings.tsx:123
3. src/pages/Dashboard.tsx:67
Fixing all instances...Fix each file systematically.
Phase 5: Verification
Step 1: Visual Verification Checklist
**Verification Checklist:**
Visual Issues:
- [ ] Button styles consistent
- [ ] Layout aligned properly
- [ ] Colors match design system
- [ ] Spacing is uniform
- [ ] Typography consistent
Responsive:
- [ ] Works on mobile
- [ ] Works on tablet
- [ ] Works on desktop
States:
- [ ] Default state correct
- [ ] Hover state correct
- [ ] Active state correct
- [ ] Disabled state correct
- [ ] Focus state accessible
**How to verify:**
1. Run dev server: `npm run dev`
2. Navigate to [affected page]
3. Check all items above
4. Compare with original screenshotStep 2: Request User Confirmation
✅ **Fixes Applied**
Changes made:
1. [Change 1]
2. [Change 2]
3. [Change 3]
**Please verify:**
- Open [URL or page]
- Check that [specific issue] is now resolved
- Verify no new issues introduced
Let me know if the visual issues are resolved or if further adjustments are needed.Common Patterns
Pattern 1: Button Style Consistency
User: "[Image] these button styles need to be fixed everywhere"
Process:
1. Analyze image - identify button style issues
2. Search for all button components
3. Identify design system button component
4. Update base button component OR
5. Update all instances to use correct variant
6. Verify consistency across appPattern 2: Layout Misalignment
User: "[Image] When logo position is set to Top right, it shows as Middle right"
Process:
1. Analyze image - see position mismatch
2. Find logo positioning code
3. Identify why "Top right" maps to "Middle right"
4. Fix the mapping or positioning logic
5. Test all position options
6. Verify with userPattern 3: Settings UI Issues
User: "[Image] The /settings should be dropdowns not text inputs"
Process:
1. Analyze image - see text inputs instead of dropdowns
2. Navigate to settings component code
3. Identify field definitions
4. Replace input components with select/dropdown
5. Ensure options are populated correctly
6. Verify all settings fieldsPattern 4: General "Hot Mess" Feedback
User: "why is the Display Ad Creator UX still a hot mess?"
Process:
1. Ask for specific issues or screenshot
2. If provided, analyze systematically
3. Create prioritized list of issues
4. Fix highest-impact issues first
5. Verify improvements with userIntegration with Other Skills
With skill-debug
Visual issue that doesn't make sense?
→ Use skill-debug to investigate why visual state is incorrectWith skill-audit
User says "fix these everywhere"?
→ Use skill-audit to find all instances
→ Use skill-visual-feedback to fix each systematicallyWith flow-tangle
Visual feedback requires new component?
→ Use flow-tangle to implement the component
→ Use skill-visual-feedback to verify it matches designBest Practices
1. Always Acknowledge the Visual Evidence
Good:
I can see in the screenshot that the button has inconsistent padding and the wrong color scheme compared to other primary buttons in the interface.Poor:
I'll fix the button.2. Be Specific About Changes
Good:
Changing:
- Button background: #3498db → #2563eb (primary-600)
- Padding: 8px 12px → 12px 16px
- Border radius: 4px → 6pxPoor:
Updating button styles.3. Consider Mobile/Responsive
Always check if the fix works across breakpoints:
**Responsive Verification:**
- Mobile (< 768px): [status]
- Tablet (768px - 1024px): [status]
- Desktop (> 1024px): [status]Red Flags - Don't Do This
| Action | Why It's Wrong |
|---|---|
| Fix without analyzing the image | Might fix wrong thing |
| Change only one instance when user says "everywhere" | Incomplete fix |
| Use !important to force styles | Creates specificity problems |
| Hard-code colors instead of using design tokens | Inconsistent with system |
| Skip verification | User has to report same issue again |
| Make assumptions without asking | Might not match user's vision |
Quick Reference
| User Feedback Pattern | Action Required |
|---|---|
| "[Image] X should be Y" | Analyze image → Find code → Fix → Verify |
| "Button styles everywhere" | Find all instances → Fix systematically |
| "UI is a mess" | Request specifics → Prioritize → Fix incrementally |
| "When X, shows Y instead of Z" | Debug state/logic → Fix mapping → Test all cases |
The Bottom Line
Visual feedback → Image analysis + Systematic fix + Visual verification
Otherwise → Guessing at fixes + Incomplete coverageSee the issue. Understand the root cause. Fix it everywhere. Verify visually.
© nyldn, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file
Files
SKILL.md and 1 other file in skills/skill-visual-feedback of nyldn/claude-octopus.
- SKILL.md
- agents/openai.yaml
Open the folder on GitHubat commit 4d152db
Used in 1 other repository
We found 2 copies of this SKILL.md (exact, near-identical or edited) in other folders, from 1 other GitHub owner. This page covers the copy in nyldn/claude-octopus, which our catalogue first saw on October 7, 2026.
Compare with similar skills
Skill Visual Feedback next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.
| Skill | Stars | Used in | Tokens | Auto-check | Licence | Repo updated |
|---|---|---|---|---|---|---|
| Skill Visual Feedback this skillnyldn/claude-octopus | 4.2k | 1 repos | ~2.6k | Automated safety check: Pass | MIT | |
| Lofisu Personazclllyybb/lofisu-identity-engine | 453 | — | ~2.8k | Automated safety check: Pass | Unlicense | |
| Liteyuki Webui FrontendLiteyukiStudio/LiteyukiBot | 157 | — | ~2.5k | Automated safety check: Pass | Custom licence | |
| Fix PR Design Notesdifferent-ai/openwork | 24k | — | ~824 | Automated safety check: Pass | Custom licence | |
| Refactoring UI Designchaxus/ran | 271 | — | ~1.9k | Automated safety check: Pass | MIT | |
| Live UX PolishEveryInc/compound-engineering-plugin | 25k | — | ~777 | Automated safety check: Pass | MIT |
Similar skills
Liteyuki Webui Frontend
LiteyukiStudio/LiteyukiBot
Build, review, or test LiteyukiBot v7's React/Vite WebUI under webui/ and its packaged static delivery in packages/webui/.
Fix PR Design Notes
different-ai/openwork
Reads the advisory design review attached to a pull request's screenshots, fixes the flagged UI problems in product code, and proves each note is gone.
Refactoring UI Design
chaxus/ran
A skill your agent uses when designing, reviewing, or improving web UI visual quality, especially when a developer-built interface feels cluttered, flat, generic, poorly spaced, weakly hierarchical…
Live UX Polish
EveryInc/compound-engineering-plugin
Collects your feedback on a running feature, typed or spoken and drawn in the browser, and turns it into focused UX fixes saved as local commits.
SVG Precision Skill
dkyazzentwatwa/chatgpt-skills
Generate deterministic SVGs from structured specs with validation and rendering.
More from nyldn/claude-octopus
All 62 skills in this repoOctopus Quick
nyldn/claude-octopus
Quick execution for ad-hoc tasks without full workflow overhead — use for small, self-contained requests
Octopus Research
nyldn/claude-octopus
Thorough research across multiple sources — use for complex topics needing broad synthesis
Octopus Security Audit
nyldn/claude-octopus
OWASP compliance, vulnerability scanning, and adversarial red team testing — use for security reviews
Skill Audit
nyldn/claude-octopus
Audit codebases for quality, consistency, and broken patterns — use for pre-release or tech debt review
Skill Content Pipeline
nyldn/claude-octopus
Extract patterns and anatomy from URLs — use to reverse-engineer content strategies from live pages
Skill Context Detection
nyldn/claude-octopus
Auto-detect work context (Dev vs Knowledge) — use to tailor workflows based on current task type
Related
Categories
Questions about Skill Visual Feedback
What does Skill Visual Feedback do?
Process screenshot-based UI/UX feedback to fix visual issues — use when users share screenshots of bugs. Skill Visual Feedback is an agent skill from nyldn/claude-octopus.
When should I use Skill Visual Feedback?
Skill Visual Feedback fits situations like: users share screenshots of bugs; tasks that involve UI design.
How do I install Skill Visual Feedback in Claude Code?
Run `npx skills add nyldn/claude-octopus --skill skill-visual-feedback -a claude-code`. Or copy the skill folder (skills/skill-visual-feedback in nyldn/claude-octopus) into .claude/skills/skill-visual-feedback in your project. Claude Code loads it when a task matches its description.
How do I install Skill Visual Feedback in Codex?
Run `npx skills add nyldn/claude-octopus --skill skill-visual-feedback -a codex`. Or copy the skill folder (skills/skill-visual-feedback in nyldn/claude-octopus) into .agents/skills/skill-visual-feedback in your project. Codex loads it when a task matches its description.
Can I use Skill Visual Feedback in Cursor, Gemini CLI or GitHub Copilot?
Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add nyldn/claude-octopus --skill skill-visual-feedback -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/skill-visual-feedback, .gemini/skills/skill-visual-feedback, .github/skills/skill-visual-feedback and .opencode/skills/skill-visual-feedback in your project.
What does Skill Visual Feedback need to run?
SKILL.md names no scripts, command-line tools or credentials: Skill Visual Feedback is instructions for the agent only.
Does Skill Visual Feedback access the network?
SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.
Is Skill Visual Feedback safe to install?
Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.
What licence does Skill Visual Feedback use?
Skill Visual Feedback is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.
How many tokens does Skill Visual Feedback use?
About 2.6k tokens (SKILL.md is roughly 11k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.
What are the alternatives to Skill Visual Feedback?
Skills that share tags, products or a category with Skill Visual Feedback: Lofisu Persona (zclllyybb/lofisu-identity-engine, 453 stars), Liteyuki Webui Frontend (LiteyukiStudio/LiteyukiBot, 157 stars), Fix PR Design Notes (different-ai/openwork, 24k stars) and Refactoring UI Design (chaxus/ran, 271 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
Who maintains Skill Visual Feedback?
nyldn (a GitHub user) maintains it in nyldn/claude-octopus, which has 4,182 GitHub stars. The repository holds 62 skills in this directory. The repository was last updated on October 7, 2026.
Source: nyldn/claude-octopus on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.