Agent skill

Cull

This skill should be used when the user wants to view, review, rate, organize, search, or export images / AI-art generations with the Cull app.

MITAuto-check passedMedia & Creative

Install Cull

skills CLI

$ npx skills add glebis/claude-skills --skill cull -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI

$ gh skill install glebis/claude-skills cull --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy

$ git clone --depth 1 https://github.com/glebis/claude-skills.git skills-src && mkdir -p .claude/skills && cp -r skills-src/cull .claude/skills/cull && rm -rf skills-src

Use ~/.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/

Paste into Claude Code

Install the "cull" agent skill from https://github.com/glebis/claude-skills/tree/main/cull into .claude/skills/cull/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "cull", 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

$skill-installer install https://github.com/glebis/claude-skills/tree/main/cull

Type 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.

skills CLI

$ npx skills add glebis/claude-skills --skill cull -a codex

Project install goes to .agents/skills/; add -g for ~/.codex/skills/.

GitHub CLI

$ gh skill install glebis/claude-skills cull --agent codex

Project scope by default (.agents/skills/); add --scope user for a personal install.

Manual copy

$ git clone --depth 1 https://github.com/glebis/claude-skills.git skills-src && mkdir -p .agents/skills && cp -r skills-src/cull .agents/skills/cull && rm -rf skills-src

Use ~/.agents/skills/ instead of .agents/skills for a personal install.

Codex skills documentation · loads skills from .agents/skills/

Paste into Codex

Install the "cull" agent skill from https://github.com/glebis/claude-skills/tree/main/cull into .agents/skills/cull/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "cull", 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.

skills CLI

$ npx skills add glebis/claude-skills --skill cull -a cursor

Project install goes to .agents/skills/; add -g for ~/.cursor/skills/.

GitHub CLI

$ gh skill install glebis/claude-skills cull --agent cursor

Project scope by default (.agents/skills/); add --scope user for a personal install.

Manual copy

$ git clone --depth 1 https://github.com/glebis/claude-skills.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/cull .cursor/skills/cull && rm -rf skills-src

Use ~/.cursor/skills/ instead of .cursor/skills for a personal install.

Cursor skills documentation · loads skills from .cursor/skills/, .agents/skills/, .claude/skills/, .codex/skills/

Paste into Cursor

Install the "cull" agent skill from https://github.com/glebis/claude-skills/tree/main/cull into .cursor/skills/cull/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "cull", 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

$ gemini skills install https://github.com/glebis/claude-skills.git --path cull

--scope user (default) or --scope workspace; --path is the subfolder of the repo that holds the skill; --consent skips the security confirmation prompt.

skills CLI

$ npx skills add glebis/claude-skills --skill cull -a gemini-cli

Project install goes to .agents/skills/; add -g for ~/.gemini/skills/.

GitHub CLI

$ gh skill install glebis/claude-skills cull --agent gemini-cli

Project scope by default (.agents/skills/); add --scope user for a personal install.

Manual copy

$ git clone --depth 1 https://github.com/glebis/claude-skills.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/cull .gemini/skills/cull && rm -rf skills-src

Use ~/.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/

Paste into Gemini CLI

Install the "cull" agent skill from https://github.com/glebis/claude-skills/tree/main/cull into .gemini/skills/cull/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "cull", 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.

GitHub CLI

$ gh skill install glebis/claude-skills cull

Installs 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).

skills CLI

$ npx skills add glebis/claude-skills --skill cull -a github-copilot

Project install goes to .agents/skills/; add -g for ~/.copilot/skills/.

Manual copy

$ git clone --depth 1 https://github.com/glebis/claude-skills.git skills-src && mkdir -p .github/skills && cp -r skills-src/cull .github/skills/cull && rm -rf skills-src

Use ~/.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/

Paste into GitHub Copilot

Install the "cull" agent skill from https://github.com/glebis/claude-skills/tree/main/cull into .github/skills/cull/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "cull", 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.

skills CLI

$ npx skills add glebis/claude-skills --skill cull -a opencode

OpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.

GitHub CLI

$ gh skill install glebis/claude-skills cull --agent opencode

Project scope by default (.agents/skills/); add --scope user for a personal install.

Manual copy

$ git clone --depth 1 https://github.com/glebis/claude-skills.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/cull .opencode/skills/cull && rm -rf skills-src

Use ~/.config/opencode/skills/ instead of .opencode/skills for a personal install.

OpenCode skills documentation · loads skills from .opencode/skills/, .claude/skills/, .agents/skills/

Paste into OpenCode

Install the "cull" agent skill from https://github.com/glebis/claude-skills/tree/main/cull into .opencode/skills/cull/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "cull", 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: cull
GitHub stars: 389
Token cost: ~1.9k tokens
SKILL.md length: 776 words
Files: 1
Skills in repo: 91
Repo updated: Sep 26, 2026
First seen: Oct 7, 2026
Licence: MIT

At a glance

This skill should be used when the user wants to view, review, rate, organize, search, or export images / AI-art generations with the Cull app.

Export images / AI-art generations with the Cull app
SKILL.md covers The one core rule (do not skip), Driving Cull headless (the…, Recipes (CLI-first) and When the MCP is needed…, plus 2 more sections
Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md
Show me these images

What it does

Cull is an agent skill from glebis/claude-skills. This skill should be used when the user wants to view, review, rate, organize, search, or export images / AI-art generations with the Cull app. Trigger on "show me these images", "review this batch", "open these in Cull", "rate / shortlist / collect these", "find similar images", "make a smart collection", "run a quality pass", "export the keepers", "publish this collection". Works via the cull CLI by default (no MCP required); the mcpcull tools are optional for richer interactive control.

Its SKILL.md is about 1.9k tokens, which your agent loads only when the skill is triggered. It is a single SKILL.md file with no bundled scripts.

It sits in Media & Creative, covering Image generation and MCP servers. It works with Model Context Protocol. The repository describes itself as: Collection of Claude Code skills for enhanced AI workflows. The licence is MIT.

When your agent uses it

Export images / AI-art generations with the Cull app
Show me these images
Review this batch
Open these in Cull

Example prompts

“show me these images”
“review this batch”
“open these in Cull”
“/cull”

What it can do on your machine

Read from SKILL.md and the folder at commit 7524dff. 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 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

Cull loads about 1.9k tokens when it runs. Until then it costs about 127 tokens; SKILL.md has 776 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it: ~127
When it runs · the whole SKILL.md, loaded when a task matches: ~1.9k

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 glebis/claude-skills at commit 7524dff, republished under its MIT licence (© glebis). 776 words, ~1,913 tokens.

Download SKILL.mdSave it as .claude/skills/cull/SKILL.md (or your agent's skills folder).

name: cull
description: This skill should be used when the user wants to view, review, rate, organize, search, or export images / AI-art generations with the Cull app. Trigger on "show me these images", "review this batch", "open these in Cull", "rate / shortlist / collect these", "find similar images", "make a smart collection", "run a quality pass", "export the keepers", "publish this collection". Works via the `cull` CLI by default (no MCP required); the `mcp__cull__*` tools are optional for richer interactive control.

Cull

Cull is a local AI-art image-library app: import folders, browse, rate/decide, build collections, run vision/quality analysis, find similar via embeddings, and export/publish.

Cull exposes the same operations four ways: the cull CLI, the cull:// URL scheme, the GUI, and an MCP server — all thin wrappers over one Rust core. Default to the CLI + URL scheme. They need no MCP connection and survive app restarts. Reach for the MCP only when interactive control is needed that the headless surface doesn't implement yet (see "When the MCP is needed").

The one core rule (do not skip)

To show or review images, use Cull — never open <image> or Preview. The user does not want Preview windows. Display by importing into Cull's library and fronting the app on the folder (below). Fronting the app is fine; opening image files with open is not.

Driving Cull headless (the default path)

The binary lives at /Applications/Cull.app/Contents/MacOS/cull. Set it once:

bash

CULL="/Applications/Cull.app/Contents/MacOS/cull"

With no subcommand it launches the GUI; with a subcommand it runs headless and exits, writing to the same library DB the running app reads. Add --json for machine-readable output.

Show / review a batch — the most common task. Import (headless), then front the app on the folder via the URL scheme:

bash

$CULL --json import_folder --folder_path "/abs/path/to/batch"
open -a /Applications/Cull.app "cull://open?path=/abs/path/to/batch&view=grid"   # &view=loupe for single-image detail
open -a Cull                                            # ensure the window is frontmost

Re-running import_folder is safe — already-imported files are skipped.

Implemented CLI subcommands

These are live in the shipped binary (cull --help to confirm). Field names match the MCP tool params.

Command	Purpose
`import_folder --folder_path P` / `import_files --file_paths a,b`	Bring a folder / specific files into the library
`list_folders` / `list_images [--limit N --offset N]` / `list_collections`	Enumerate folders / images / collections
`get_library_stats`	Library-wide counts
`list_export_presets` / `export_images --image_ids … --output_dir … --format …`	List presets / export to disk (also `--collection_id` or `--folder_path`)
`get_embedding_model_download_info` / `download_embedding_model` / `generate_embeddings`	Embedding model prereq + build (async)
`analyze_image_quality` / `get_image_quality` / `get_quality_count`	Run quality analysis / read scores / count by bucket
`call_tool <tool> --params_json '{…}'`	Generic escape hatch — call any MCP-named tool with a JSON object

call_tool accepts MCP-shaped params, so any MCP operation can be tried headless:

bash

$CULL --json call_tool import_folder --params_json '{"folder_path":"/abs/path"}'
$CULL --json call_tool export_images --params_json '{"collection_id":"<id>","output_dir":"/tmp/out","format":"original"}'

URL scheme (GUI actions)

open -a /Applications/Cull.app "cull://<action>?<params>" — paths URL-encoded, multiple paths comma-separated. Always pass -a /Applications/Cull.app: dev builds of Cull also register the cull:// scheme, and a bare open "cull://…" may route to a stale copy (URL silently goes nowhere). GUI actions front the window; if the app isn't running, macOS launches it.

Action	Example
open / navigate	`cull://open?path=/abs/folder&view=grid` (`view=loupe`, `&focus=N`, `&fullscreen=true`)
search	`cull://search?q=sunset`
similar	`cull://similar?path=/abs/ref.jpg&top=5`
rate / accept	`cull://rate?path=/abs/img.jpg&stars=4` · `cull://accept?path=/abs/img.jpg`
collection	`cull://collection/add?name=picks&paths=/abs/a.jpg,/abs/b.jpg`

URL-scheme calls are fire-and-forget (no return value). When a result is needed, use the CLI (--json) or the MCP.

Recipes (CLI-first)

Loupe one image. open -a /Applications/Cull.app "cull://open?path=/abs/img.png&view=loupe".

Export the keepers. list_export_presets → export_images with --collection_id / --folder_path / --image_ids, an --output_dir, and --format.

Quality pass. analyze_image_quality (async — it returns a job; for CLI poll by re-reading) → get_quality_count for the distribution → get_image_quality per image.

Embeddings prerequisite. download_embedding_model (once) → generate_embeddings (async). Only then does similarity work (cull://similar?…, or find_similar over MCP).

Show full SKILL.md (304 more words)Show less

When the MCP is needed (optional)

The headless CLI does not yet implement interactive curation and live navigation — those exist only as mcp__cull__* tools (or manual GUI). Reach for the MCP to:

Navigate / show precisely from the agent: navigate_to_folder, show_image, show_collection (the URL scheme covers the common cases, but these give programmatic control and confirmation).
Curate with round-trips: set_rating, set_decision, create_collection, add_to_collection, create_smart_collection.
Search & vision with results: find_similar, search_by_object, detect_objects / get_detections, analyze_images, get_vision_metadata.
Track async jobs: list_jobs / get_job / cancel_job.
Publish: export_static_publish_package / serve_static_publish_package, clipboard-collection tools.

MCP mechanics. These tools are named mcp__cull__<tool> and in Claude Code are deferred — schemas aren't loaded, so a direct call fails. Load before calling, only what the recipe needs:

ToolSearch "select:mcp__cull__navigate_to_folder,mcp__cull__set_rating"

The MCP drops when Cull restarts. Quitting/relaunching the app kills its MCP server; it must be reconnected by the user via /mcp before any mcp__cull__* call works again. The CLI + URL scheme have no such dependency — prefer them, and fall back to MCP only for the interactive operations above.

Common mistakes

Using open / Preview instead of Cull. The cardinal sin — review always happens in Cull (import_folder + cull://open, or the MCP show/navigate tools).
Reaching for the MCP first. Default to the CLI + URL scheme; they're connection-free and restart-proof. MCP is the fallback for interactive curation.
Assuming the MCP survived a Cull restart. It doesn't — the user must /mcp reconnect. Don't restart Cull mid-task if you depend on the MCP.
Calling a deferred MCP tool before loading it. ToolSearch "select:mcp__cull__…" first.
Treating async ops as synchronous. Embeddings, analysis, and large exports are jobs — poll, don't assume completion.
Guessing params. Check cull <command> --help or load the MCP tool and read its schema.

Safety & limits

Destructive ops need explicit intent. delete_collection and prune_audit_log remove data; confirm before running.
Tokens are admin. create_token / rotate_token / revoke_token change access credentials — don't touch unless the user explicitly asks.

Files

Just SKILL.md in cull of glebis/claude-skills.

Open the folder on GitHubat commit 7524dff

Compare with similar skills

Cull 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.

Cull compared with similar skills
Skill	Stars	Used in	Tokens	Auto-check	Licence	Repo updated
Cull this skillglebis/claude-skills	389	—	~1.9k	Automated safety check: Pass	MIT	11 days ago
Setupguaardvark/guaardvark	255	1 repos	~1.2k	Automated safety check: Pass	MIT	today
ComfyComfy-Org/comfy-skills	219	—	~1.4k	Automated safety check: Pass	MIT	today
Gemini SkillWJZ-P/gemini-skill	832	—	~1.1k	Automated safety check: Pass	MIT	19 days ago
Qiaomu Codex Imagegenjoeseesun/qiaomu-codex-imagegen	114	—	~2.3k	Automated safety check: Pass	MIT	4 days ago
Blog ImageAgriciDaniel/claude-blog	2.3k	—	~3.4k	Automated safety check: Pass	MIT	today

Similar skills

Setup
guaardvark/guaardvark
Connect this agent to a running Guaardvark (self-hosted AI studio) and check what it can do right now.
255 GitHub starsUsed in 1 repo~1.2k tokens
AI & LLM EngineeringAuto-check passed
Comfy
Comfy-Org/comfy-skills
Generate images, video, audio, and 3D with Comfy Cloud — search hundreds of models and workflow templates, run custom ComfyUI workflows, and manage generation jobs through the hosted Comfy Cloud MCP…
219 GitHub stars~1.4k tokensUpdated today
Agent WorkflowsAuto-check passed
Gemini Skill
WJZ-P/gemini-skill
通过 Gemini 官网（gemini.google.com）执行生图、对话等操作。用户提到"生图/画图/绘图/nano banana/nanobanana/生成图片"等关键词时触发。操作方式分三级优先级：首选 MCP 工具 → 次选 Skill 脚本 → 最次连接 Skill 浏览器手动操作（需用户授权）。禁止自行启动外部浏览器访问 Gemini。
832 GitHub stars~1.1k tokensUpdated 19 days ago
Agent WorkflowsAuto-check passed
Qiaomu Codex Imagegen
joeseesun/qiaomu-codex-imagegen
Generate or edit images with Codex's built-in image generation from any agent, through an MCP tool or a plain CLI.
114 GitHub stars~2.3k tokensUpdated 4 days ago
Media & CreativeAuto-check passed
Blog Image
AgriciDaniel/claude-blog
AI image generation and editing for blog content powered by Gemini via MCP.
2.3k GitHub stars~3.4k tokensUpdated today
Media & CreativeAuto-check passed
Image Context Runtime
shixinnt/codex-image-context-runtime
A skill your agent uses for image-heavy Codex work when generated or inspected media should stay behind a bounded MCP boundary and the controlling task should receive only durable Job IDs, hashes…
100 GitHub stars~723 tokensUpdated 1 mo ago
Media & CreativeAuto-check passed

More from glebis/claude-skills

All 91 skills in this repo

PII Annotation and Agreement Scorer
glebis/claude-skills
Runs a human-first workflow for labeling PII spans in a transcript, then scores inter-annotator agreement and drafts an adjudicated gold set.
389 GitHub stars~1.3k tokensUpdated 11 days ago
Auto-check passed
Non-Destructive Chrome Automation
glebis/claude-skills
Automates a dedicated, logged-in Chrome instance per profile without ever closing the user's own open tabs or browser windows.
389 GitHub stars~973 tokensUpdated 11 days ago
Auto-check passed
Deep Research
glebis/claude-skills
This skill should be used when conducting comprehensive research on any topic using the OpenAI Deep Research API.
389 GitHub stars~2.6k tokensUpdated 11 days ago
Auto-check: notes
Elimination Research
glebis/claude-skills
This skill should be used for elimination-style research where the user wants to choose from a shortlist of products, tools, services, vendors, or other options using explicit criteria, numeric…
389 GitHub stars~1.6k tokensUpdated 11 days ago
Auto-check passed
Narrated HTML Presentations
glebis/claude-skills
Generates a self-contained HTML presentation with article and slides modes, ElevenLabs voiceover narration and optional GPT Image 2 illustrations.
389 GitHub stars~2.3k tokensUpdated 11 days ago
Auto-check: notes
Synthetic Coaching Session Generator
glebis/claude-skills
Writes fictional but realistic coaching or therapy session transcripts for evals, demos and few-shot examples, in several modalities and export formats.
389 GitHub stars~2.9k tokensUpdated 11 days ago
Auto-check passed

Works with

Model Context Protocol

Questions about Cull

What does Cull do?

This skill should be used when the user wants to view, review, rate, organize, search, or export images / AI-art generations with the Cull app. Cull is an agent skill from glebis/claude-skills. This skill should be used when the user wants to view, review, rate, organize, search, or export images / AI-art generations with the Cull app.

When should I use Cull?

Cull fits situations like: export images / AI-art generations with the Cull app; show me these images; review this batch; open these in Cull.

How do I install Cull in Claude Code?

Run `npx skills add glebis/claude-skills --skill cull -a claude-code`. Or copy the skill folder (cull in glebis/claude-skills) into .claude/skills/cull in your project. Claude Code loads it when a task matches its description.

How do I install Cull in Codex?

Run `npx skills add glebis/claude-skills --skill cull -a codex`. Or copy the skill folder (cull in glebis/claude-skills) into .agents/skills/cull in your project. Codex loads it when a task matches its description.

Can I use Cull 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 glebis/claude-skills --skill cull -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/cull, .gemini/skills/cull, .github/skills/cull and .opencode/skills/cull in your project.

What does Cull need to run?

SKILL.md names no scripts, command-line tools or credentials: Cull is instructions for the agent only.

Does Cull 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 Cull 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 Cull use?

Cull 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 Cull use?

About 1.9k tokens (SKILL.md is roughly 7.7k 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 Cull?

Skills that share tags, products or a category with Cull: Setup (guaardvark/guaardvark, 255 stars), Comfy (Comfy-Org/comfy-skills, 219 stars), Gemini Skill (WJZ-P/gemini-skill, 832 stars) and Qiaomu Codex Imagegen (joeseesun/qiaomu-codex-imagegen, 114 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Cull?

glebis (a GitHub user) maintains it in glebis/claude-skills, which has 389 GitHub stars. The repository holds 91 skills in this directory. The repository was last updated on September 26, 2026.

Source: glebis/claude-skills on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.

Install Cull

Facts

At a glance

What it does

When your agent uses it

Example prompts

What it can do on your machine

Tool permissions

Runs code

Network

Credentials

Context cost

Safety

SKILL.md

Cull

The one core rule (do not skip)

Driving Cull headless (the default path)

Implemented CLI subcommands

URL scheme (GUI actions)

Recipes (CLI-first)

When the MCP is needed (optional)

Common mistakes

Safety & limits

Files

Compare with similar skills

Similar skills

More from glebis/claude-skills

Related

Questions about Cull