Not in the top 1,000 by GitHub stars
justlovemaki/LumaRescue
面向 Codex/豆包桌面版 的 AI 废片拯救技能，通过光影重塑、大师级构图、照片修复与审美增强，将普通照片优化成更惊艳、更耐看的成片。
History
Review weekly changes to SKILL.md before updating. Dates mark the weeks in which we observed each version; checks apply to the recorded commits.
View weekly changes
SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Instructions only → After Instructions only
14cd76cea24e → 14cd76cea24e
Diff text is unavailable under the recorded licenses. Line counts and the GitHub link remain available.
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → 14cd76cea24e
No earlier version was observed for comparison.
Heat
3.7- Star growth, last 7 daysNot available
- Star growth, last 24 hoursNot available
- Rank movement, last 7 daysNot available
- Commits, last 30 daysNot available
- Accounts asking about it through MCP, last 7 daysNot available
- Hot votes this weekNot available
Heat never changes the order by stars, and sponsorship never touches it. How heat works
Stars over time
30-day change not yet available: not enough history.
Individual skills in this repository
How it works
rescue-bad-photo
When your agent uses it
Repair and beautify uploaded photos while preserving the original subject, identity, texture, and important details. Use when the user asks to save a bad photo, make a photo prettier, improve exposure/color/sharpness/noise, shape light and shadow, apply tasteful grading or filters, crop or recompose with master-photographer-level composition, restore damaged or faded photos, colorize black-and-white photos, make landscape photos cinematic or breathtaking, optimize architecture, retouch portraits with natural skin, flattering light, focal-length feel, or background blur, optimize museum/gallery exhibit photos faithfully with exhibit-focused crop/recomposition and background blur, or prepare polished images for sharing or printing. Produces clearly labeled programmatic natural, programmatic beauty, AI natural, and AI beauty variants; beauty variants should usually feel stunning, grand, vibrant, and visibly transformed.
What it loads into context
Frontmatter
178 tokensAlways available to the agent
SKILL.md
4,561 tokensWhen the skill is activated
Reference documents
10,530 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Core Rule
- Preservation And Beauty Resolver
- Autopilot Default
- Beauty Target
- Master Composition Rule
- Beauty Failure Rule
- Variant Output Requirement
- Workflow
- Editing Priorities
- Composition Guidance
- Subject-Specific Logic
- Black-And-White, Faded, Or Damaged Photos
- Epic Landscape Enhancement
- Tool Use
- Output Standard
Files
README.mddoc5,656 bytesSKILL.mdcore24,012 bytesSKILL.mdcore24,012 bytesSKILL.mdcore24,012 bytesagents/openai.yamlasset171 bytesphotos/1.jpgasset182,632 bytesphotos/1_ai_beauty.pngasset2,450,609 bytesphotos/2.jpgasset3,492,097 bytesphotos/2_ai_beauty.pngasset1,763,796 bytesphotos/3.jpgasset5,706,160 bytesphotos/3_ai_beauty.pngasset2,657,787 bytesreferences/photo-rescue-guide.mddoc36,335 bytesreferences/photographic-style-playbook.mddoc9,527 bytes
No excerpt is shown for this license. Read the source on GitHub.
View the complete source on GitHubSkills included
- rescue-bad-photo
Repository facts
- License
- No license detected
- Created
- Jul 7, 2026
- Last pushed
- Jul 7, 2026
- Forks
- 21
- Open issues
- 0
- Project activity
- Slowing
Before you install
Instructions onlyAutomated signals, not a guarantee
Checked Nov 7, 2026
Not fully analyzed: some files were too long, unreadable or missing. This never lowers the level.
Show 2 notes
SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedSKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzed
- No broad tool permissions
- No dangerous shell commands
- No network access
- No hidden or obfuscated text
- No instruction overrides
- No executable scripts
- No access to secrets
- No requests to vote in Hot
How the signals fit together
Facts from a static read of the files at the pinned commit. They describe what the code does, not why.
No combined signals at this commit.
Works with
| Agent | Status | Evidence | Install to |
|---|---|---|---|
| Claude Code | Compatible | Standard SKILL.md SKILL.md | .claude/skills/<skill-name>/ |
| Codex | Compatible | Standard SKILL.md SKILL.md | .agents/skills/<skill-name>/ |
| Cursor | Compatible | Standard SKILL.md SKILL.md | .cursor/skills/<skill-name>/ |
| Gemini CLI | Compatible | Standard SKILL.md SKILL.md | .gemini/skills/<skill-name>/ |
| GitHub Copilot | Compatible | Standard SKILL.md SKILL.md | .github/skills/<skill-name>/ |
| OpenCode | Compatible | Standard SKILL.md SKILL.md | .opencode/skills/<skill-name>/ |
- Native The repository ships a manifest, folder or frontmatter field for this agent.
- Compatible A standard SKILL.md that this agent can read.
- Unknown No evidence either way.
Derived automatically from paths, manifests and frontmatter. Not tested on each agent.
