Setup Pre Commit
fossasia/eventyay-interpretation
Set up Husky pre-commit hooks with lint-staged (Prettier), type checking, and tests in the current repo.
Repair and beautify uploaded photos while preserving the original subject, identity, texture, and important details.
Install Rescue Bad Photo
$ npx skills add justlovemaki/LumaRescue --skill rescue-bad-photo -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install justlovemaki/LumaRescue rescue-bad-photo --agent claude-codeProject scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).
Claude Code skills documentation · loads skills from .claude/skills/
Install the "rescue-bad-photo" agent skill from https://github.com/justlovemaki/LumaRescue/tree/main into .claude/skills/rescue-bad-photo/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "rescue-bad-photo", 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.
$ npx skills add justlovemaki/LumaRescue --skill rescue-bad-photo -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install justlovemaki/LumaRescue rescue-bad-photo --agent codexProject scope by default (.agents/skills/); add --scope user for a personal install.
Codex skills documentation · loads skills from .agents/skills/
Install the "rescue-bad-photo" agent skill from https://github.com/justlovemaki/LumaRescue/tree/main into .agents/skills/rescue-bad-photo/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "rescue-bad-photo", 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 justlovemaki/LumaRescue --skill rescue-bad-photo -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install justlovemaki/LumaRescue rescue-bad-photo --agent cursorProject scope by default (.agents/skills/); add --scope user for a personal install.
Cursor skills documentation · loads skills from .cursor/skills/, .agents/skills/, .claude/skills/, .codex/skills/
Install the "rescue-bad-photo" agent skill from https://github.com/justlovemaki/LumaRescue/tree/main into .cursor/skills/rescue-bad-photo/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "rescue-bad-photo", 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.
$ npx skills add justlovemaki/LumaRescue --skill rescue-bad-photo -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install justlovemaki/LumaRescue rescue-bad-photo --agent gemini-cliProject scope by default (.agents/skills/); add --scope user for a personal install.
Gemini CLI skills documentation · loads skills from .gemini/skills/, .agents/skills/
Install the "rescue-bad-photo" agent skill from https://github.com/justlovemaki/LumaRescue/tree/main into .gemini/skills/rescue-bad-photo/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "rescue-bad-photo", 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 justlovemaki/LumaRescue rescue-bad-photoInstalls 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 justlovemaki/LumaRescue --skill rescue-bad-photo -a github-copilotProject install goes to .agents/skills/; add -g for ~/.copilot/skills/.
GitHub Copilot skills documentation · loads skills from .github/skills/, .claude/skills/, .agents/skills/
Install the "rescue-bad-photo" agent skill from https://github.com/justlovemaki/LumaRescue/tree/main into .github/skills/rescue-bad-photo/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "rescue-bad-photo", 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 justlovemaki/LumaRescue --skill rescue-bad-photo -a opencodeOpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.
$ gh skill install justlovemaki/LumaRescue rescue-bad-photo --agent opencodeProject scope by default (.agents/skills/); add --scope user for a personal install.
OpenCode skills documentation · loads skills from .opencode/skills/, .claude/skills/, .agents/skills/
Install the "rescue-bad-photo" agent skill from https://github.com/justlovemaki/LumaRescue/tree/main into .opencode/skills/rescue-bad-photo/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "rescue-bad-photo", 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
rescue-bad-photo- GitHub stars
- 198
- Token cost
- ~6k tokens
- SKILL.md length
- 3,123 words
- Files
- 11 (incl. references)
- Skills in repo
- 1
- Repo updated
- First seen
- Licence
- None found
At a glance
Repair and beautify uploaded photos while preserving the original subject, identity, texture, and important details.
- Works in 7 steps: Classify the image as portrait,… → Apply the matching subject-specific… → Choose an aesthetic direction… → …
- The user asks to save a bad photo
- SKILL.md covers Core Rule, Preservation And Beauty Resolver, Autopilot Default and Beauty Target, plus 11 more sections
- Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md
What it does
Rescue Bad Photo is an agent skill from justlovemaki/LumaRescue. 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…
Its SKILL.md is about 6k tokens, which your agent loads only when the skill is triggered. The skill folder holds 13 other files, including reference files (for example `README.md`, `agents/openai.yaml` and `references/photo-rescue-guide.md`).
It sits in Media & Creative, covering Linting and formatting and Image editing. It works with Prettier. The repository describes itself as: 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。
When your agent uses it
- The user asks to save a bad photo
- Make a photo prettier
- Improve exposure/color/sharpness/noise
- Shape light and shadow
Example prompts
- “/rescue-bad-photo”
Workflow steps
7 steps, taken from the first numbered list in SKILL.md.
- Classify the image as portrait, landscape/travel, architecture/interior, museum/gallery exhibit, product/food, document/artwork…
- Apply the matching subject-specific recipe automatically.
- Choose an aesthetic direction automatically from the image content.
- Perform beauty enhancement, composition/crop evaluation, local cleanup, and final QA by default.
- Produce four labeled outputs by default: programmatic natural, programmatic beauty, AI natural, and AI beauty.
- Use generative editing or regeneration for the AI variants when it materially improves beauty, repair, outpainting, relighting…
- Ask a clarification only when there is a genuine conflict, such as faithful museum documentation versus dramatic poster styling, or when…
What it can do on your machine
Read from SKILL.md and the folder at commit 14cd76c. 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.
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
Rescue Bad Photo loads about 6k tokens when it runs, and up to ~17k if it reads all its reference files. Until then it costs about 237 tokens; SKILL.md has 3,123 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
Without a licence we can't republish the file, so here is its outline and opening line. It has 3,123 words (~6,000 tokens).
“Preserve the subject and factual image content. Improve exposure, color, contrast, composition, clarity, and damage without changing identity, clothing, facial structure, pose, scene meaning, product details, text, logos, artwork, or historically important marks unless the user explicitly asks. Switch optimization…”
- name
- rescue-bad-photo
Files
SKILL.md and 10 other files (references) in the repository root of justlovemaki/LumaRescue.
- SKILL.md
- README.md
- agents/openai.yaml
- photos/1.jpg
- photos/1_ai_beauty.png
- photos/2.jpg
- photos/2_ai_beauty.png
- photos/3.jpg
- photos/3_ai_beauty.png
- references/photo-rescue-guide.md
- references/photographic-style-playbook.md
Open the folder on GitHubat commit 14cd76c
Compare with similar skills
Rescue Bad Photo 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 |
|---|---|---|---|---|---|---|
| Rescue Bad Photo this skilljustlovemaki/LumaRescue | 198 | — | ~6k | Automated safety check: Pass | None | |
| Setup Pre Commitfossasia/eventyay-interpretation | 1.6k | 12 repos | ~565 | Automated safety check: Pass | Apache-2.0 | |
| Formatter Developmentbiomejs/biome | 26k | — | ~2.1k | Automated safety check: Pass | Apache-2.0 | |
| Code Qualityredis/RedisInsight | 8.9k | — | ~1.2k | Automated safety check: Pass | Custom licence | |
| Flowmark Markdown Formatterjlevy/repren | 374 | — | ~631 | Automated safety check: Pass | MIT | |
| Building Glamorous TuisDicklesworthstone/meta_skill | 205 | — | ~3.4k | Automated safety check: Pass | Custom licence |
Similar skills
- Official
Formatter Development
biomejs/biome
A skill your agent uses whenever implementing or debugging Biome formatter behavior, IR composition, node rules, layout selection, source-comment handling, verbatim formatting, idempotency, internal…
- Official
Code Quality
redis/RedisInsight
Code-quality standards for RedisInsight: TypeScript strictness, naming conventions (camelCase, PascalCase, UPPERSNAKECASE), linting rules, no any without reason, no !important in styles, and…
Flowmark Markdown Formatter
jlevy/repren
Formats Markdown with the Flowmark auto-formatter for typographic cleanup and semantic line breaks, and helps adopt it across a repository.
Building Glamorous Tuis
Dicklesworthstone/meta_skill
Build terminal UIs with Charmbracelet (Bubble Tea, Lip Gloss, Gum).
Electron App Source Extractor
JimLiu/baoyu-skills
Unpacks an installed Electron app's asar bundle and restores readable source from its JavaScript source maps when one is available.
Related
Works with
Categories
Questions about Rescue Bad Photo
What does Rescue Bad Photo do?
Repair and beautify uploaded photos while preserving the original subject, identity, texture, and important details. Rescue Bad Photo is an agent skill from justlovemaki/LumaRescue. Repair and beautify uploaded photos while preserving the original subject, identity, texture, and important details.
When should I use Rescue Bad Photo?
Rescue Bad Photo fits situations like: the user asks to save a bad photo; make a photo prettier; improve exposure/color/sharpness/noise; shape light and shadow.
How do I install Rescue Bad Photo in Claude Code?
Run `npx skills add justlovemaki/LumaRescue --skill rescue-bad-photo -a claude-code`. Or copy the skill folder (the justlovemaki/LumaRescue repository) into .claude/skills/rescue-bad-photo in your project. Claude Code loads it when a task matches its description.
How do I install Rescue Bad Photo in Codex?
Run `npx skills add justlovemaki/LumaRescue --skill rescue-bad-photo -a codex`. Or copy the skill folder (the justlovemaki/LumaRescue repository) into .agents/skills/rescue-bad-photo in your project. Codex loads it when a task matches its description.
Can I use Rescue Bad Photo 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 justlovemaki/LumaRescue --skill rescue-bad-photo -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/rescue-bad-photo, .gemini/skills/rescue-bad-photo, .github/skills/rescue-bad-photo and .opencode/skills/rescue-bad-photo in your project.
What does Rescue Bad Photo need to run?
SKILL.md names no scripts, command-line tools or credentials: Rescue Bad Photo is instructions for the agent only.
Does Rescue Bad Photo 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 Rescue Bad Photo 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 Rescue Bad Photo use?
No licence was found for Rescue Bad Photo or its repository. Without one, default copyright applies: ask the author before reusing or redistributing it.
How many tokens does Rescue Bad Photo use?
About 6k tokens (SKILL.md is roughly 24k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full. Its references folder adds about 11k tokens, read only when the agent opens those files.
What are the alternatives to Rescue Bad Photo?
Skills that share tags, products or a category with Rescue Bad Photo: Setup Pre Commit (fossasia/eventyay-interpretation, 1.6k stars), Formatter Development (biomejs/biome, 26k stars), Code Quality (redis/RedisInsight, 8.9k stars) and Flowmark Markdown Formatter (jlevy/repren, 374 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
Who maintains Rescue Bad Photo?
justlovemaki (a GitHub user) maintains it in justlovemaki/LumaRescue, which has 198 GitHub stars. The repository was last updated on July 7, 2026.
Source: justlovemaki/LumaRescue on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.