Sprite Gen
aldegad/sprite-gen
Generates images and game sprites through GPT or Grok with guided provider choices, separate saved defaults, automatic cleanup and optional curation.
Mandatory routing skill. An agent skill from valkor-ai/loom.
Install Loom
$ npx skills add valkor-ai/loom --skill loom -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install valkor-ai/loom loom --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/valkor-ai/loom.git skills-src && mkdir -p .claude/skills && cp -r skills-src/plugins/codex/skills/loom .claude/skills/loom && 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 "loom" agent skill from https://github.com/valkor-ai/loom/tree/main/plugins/codex/skills/loom into .claude/skills/loom/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "loom", 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/valkor-ai/loom/tree/main/plugins/codex/skills/loomType 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 valkor-ai/loom --skill loom -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install valkor-ai/loom loom --agent codexProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/valkor-ai/loom.git skills-src && mkdir -p .agents/skills && cp -r skills-src/plugins/codex/skills/loom .agents/skills/loom && rm -rf skills-srcUse ~/.agents/skills/ instead of .agents/skills for a personal install.
Codex skills documentation · loads skills from .agents/skills/
Install the "loom" agent skill from https://github.com/valkor-ai/loom/tree/main/plugins/codex/skills/loom into .agents/skills/loom/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "loom", 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 valkor-ai/loom --skill loom -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install valkor-ai/loom loom --agent cursorProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/valkor-ai/loom.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/plugins/codex/skills/loom .cursor/skills/loom && 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 "loom" agent skill from https://github.com/valkor-ai/loom/tree/main/plugins/codex/skills/loom into .cursor/skills/loom/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "loom", 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/valkor-ai/loom.git --path plugins/codex/skills/loom--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 valkor-ai/loom --skill loom -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install valkor-ai/loom loom --agent gemini-cliProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/valkor-ai/loom.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/plugins/codex/skills/loom .gemini/skills/loom && 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 "loom" agent skill from https://github.com/valkor-ai/loom/tree/main/plugins/codex/skills/loom into .gemini/skills/loom/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "loom", 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 valkor-ai/loom loomInstalls 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 valkor-ai/loom --skill loom -a github-copilotProject install goes to .agents/skills/; add -g for ~/.copilot/skills/.
$ git clone --depth 1 https://github.com/valkor-ai/loom.git skills-src && mkdir -p .github/skills && cp -r skills-src/plugins/codex/skills/loom .github/skills/loom && 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 "loom" agent skill from https://github.com/valkor-ai/loom/tree/main/plugins/codex/skills/loom into .github/skills/loom/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "loom", 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 valkor-ai/loom --skill loom -a opencodeOpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.
$ gh skill install valkor-ai/loom loom --agent opencodeProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/valkor-ai/loom.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/plugins/codex/skills/loom .opencode/skills/loom && 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 "loom" agent skill from https://github.com/valkor-ai/loom/tree/main/plugins/codex/skills/loom into .opencode/skills/loom/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "loom", 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
loom- GitHub stars
- 1.2k
- Token cost
- ~1.4k tokens
- SKILL.md length
- 736 words
- Files
- 1
- Skills in repo
- 17
- Repo updated
- First seen
- Licence
- Apache-2.0
At a glance
Mandatory routing skill. An agent skill from valkor-ai/loom.
- Explicitly invokes @loom
- SKILL.md covers Route, Follow Results, Read, Write, Verify and Reference Loading
- Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md
- Call the matching Loom MCP route before any repository work
What it does
Loom is an agent skill from valkor-ai/loom. Mandatory routing skill. When the user explicitly invokes @loom, call the matching Loom MCP route before any repository work; plain delivery requests must start with loom.plan.
Its SKILL.md is about 1.4k 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 Game Development. It works with Model Context Protocol. The repository describes itself as: Loop engineering for agentic software delivery. The licence is Apache-2.0.
When your agent uses it
- Explicitly invokes @loom
- Call the matching Loom MCP route before any repository work
- Plain delivery requests must start with loom.plan
Example prompts
- “/loom”
What it can do on your machine
Read from SKILL.md and the folder at commit a30a7e6. 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
Loom loads about 1.4k tokens when it runs. Until then it costs about 45 tokens; SKILL.md has 736 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 valkor-ai/loom at commit a30a7e6, republished under its Apache-2.0 licence (© valkor-ai). 736 words, ~1,369 tokens.
Download SKILL.mdSave it as
.claude/skills/loom/SKILL.md (or your agent's skills folder).- name
- loom
- description
- Mandatory routing skill. When the user explicitly invokes @loom, call the matching Loom MCP route before any repository work; plain delivery requests must start with loom.plan.
loom
Use Loom MCP as the workflow authority. Do not inspect .loom directly, invent a workflow in chat, or touch repository files before the route below returns.
This is the mandatory routing entrypoint. When a user invokes @loom, resolve the Loom route before any repository work. For @loom <request> or @loom plan <request>, call mcp__loom__plan when it is available. If deferred loading hides that tool, make one targeted search for Loom plan software delivery @loom, then call the returned plan tool. Do not search for deploy, inspect, or generic skills, and do not call exec_command, apply_patch, or other repository tools before the plan call returns.
Route
Use the current workspace as projectRoot.
@loom <request>: callloom.planwith{ projectRoot, requestText: "<full request>" }.@loom plan <request>: same call with<request>.@loom continue|resume|proceed|next: callloom.continue.@loom verify,@loom status,@loom knowledge ..., and@loom deploy ...: call the matching Loom tool directly.- If the plan tool is deferred, make one targeted search for
Loom plan software delivery @loom, then call the returned plan tool. Do not do other discovery first. - For a plan-conflict gate, present its choices exactly and resolve it with
loom.planConflictResolve; never callloom.planagain.
Follow Results
auto_runnable: perform the returnednextaction immediately.active_operation: use only the named observation tools.user_gate: followpreResponseContractin order before replying. For Brainstorm, read the applicable groups, run every required knowledge step, present the current question, then wait for the user. A phase continuation is an active clarification, not an optional next step.repairable_error: inspect the request, read every required group, change only the returned target, and use its resubmit tool. Do not ask the user to repeat a confirmation.- V-SEFM onboarding: wait for the user's choice, then call
loom.verifywithdecision=requiredordecision=deferred. done,blocked, orfailed: stop and report it. Do not stop while a result is auto-runnable orstopAllowed=false.
Read, Write, Verify
When a result has requestRef, use loom.inspectRequest and only the declared loom.readFieldGroup groups. requestReadPlan.groups is the only read contract. The request is the source of schemas, read boundaries, and submit parameters; do not request individual fields or infer inputs from old artifacts.
Write only returned writeTargets, then submit with the returned tool. For execution, respect edit boundaries, run the required checks, write the TaskResult, and submit it before saying work is complete. If an operation fails, inspect and repair it in the same Loom action.
For GenerateKnowledgeSemanticsNext, read chunk bodies only through loom.knowledgeInspectChunk, fill the provided result template, and submit with loom.knowledgeSemanticSubmitFile. Continue pack by pack until the build publishes, blocks, or reaches a real user gate.
For RunLoomToolNext, inspect the requestRef, read only the returned readGroups, call the returned Loom MCP tool, then retry the returned retryTool before reporting completion.
Show full SKILL.md (286 more words)Show less
Reference Loading
The current MCP request/result remains the authority. Load no reference by default; load references only when the current action selects a reference profile.
Protocol:
- After reading the current request group, choose references only from the profiles selected by that request.
- Read reference files only from
referenceLoadPlanarrays in the current MCP request/result. - Treat selected group fields as semantic labels for scope and evidence, not as path mappings.
- If a referenced file is not selected by the MCP contract and is not needed by the current action, leave it unread.
- In quality self-checks, report the exact
referencePlanFilesCheckedpaths from the selected load plan; do not paste reference prose or template bodies.
Reference profiles:
- Each
referenceLoadPlanentry containsrefId,path, andreason. Resolvepathunder the installed Loom skill'sreferences/directory. Do not resolve it against the project workspace or source checkout. Before reading, verify the resolved file directly. - Load exactly the listed paths for the current action. Do not derive paths from group names, scan reference directories, or load external language, API, architecture, or UI skills.
- Treat token template paths as merge baselines for project files, not as text to copy into Loom artifacts.
Reference discipline:
- Do not load unselected references to compensate for weak planning; ask Loom to repair the contract only when the selected
referenceLoadPlanis insufficient. - In TaskPlan, Execution, Review, and Repair requests without a selected load plan, use the provided quality refs, requirements, evidence, and review signals without reading raw references.
- Do not paste tech reference text into artifacts, source files, or user-facing UI. Use references to produce concrete decisions, interface contracts, NFRs, risks, and evidence.
Keep user-facing responses compact. Do not paste raw artifacts, request payloads, or logs unless asked.
© valkor-ai, Apache-2.0. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file
Files
Just SKILL.md in plugins/codex/skills/loom of valkor-ai/loom.
Open the folder on GitHubat commit a30a7e6
Compare with similar skills
Loom 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 |
|---|---|---|---|---|---|---|
| Loom this skillvalkor-ai/loom | 1.2k | — | ~1.4k | Automated safety check: Pass | Apache-2.0 | |
| Sprite Genaldegad/sprite-gen | 2.6k | — | ~4.8k | Automated safety check: Pass | Apache-2.0 | |
| Blockbench Pluginsjasonjgardner/blockbench-mcp-plugin | 495 | — | ~2.8k | Automated safety check: Pass | GPL-3.0 | |
| Unreal Blueprint Authoringflopperam/unreal-engine-mcp | 1.1k | — | ~1.6k | Automated safety check: Pass | None | |
| Locus Unity BridgeMisaka-Mikoto-Tech/agent-skills | 278 | — | ~4k | Automated safety check: Pass | MIT | |
| Assets Shader List AllIvanMurzak/Unity-MCP | 4.4k | — | ~435 | Automated safety check: Pass | Apache-2.0 |
Similar skills
Blockbench Plugins
jasonjgardner/blockbench-mcp-plugin
Blockbench plugin/extension development for the 3D modeling tool.
Unreal Blueprint Authoring
flopperam/unreal-engine-mcp
Walks an agent through creating and editing Unreal Engine Blueprints with the Flopperam MCP's bp_* tools, from inspection to commit and verification.
Locus Unity Bridge
Misaka-Mikoto-Tech/agent-skills
A skill your agent uses when an agent needs to inspect or control a real Unity Editor through Locus, especially when Unity MCP is unavailable, named-pipe discovery is needed, C must be executed, or…
Assets Shader List All
IvanMurzak/Unity-MCP
List all shaders available in the project assets and packages, sorted by name.
Unreal Material and VFX Workflow
flopperam/unreal-engine-mcp
Walks an Unreal Engine MCP agent through building materials, Niagara particle systems, Chaos destruction, and curve assets with inspect-then-edit steps.
More from valkor-ai/loom
All 17 skills in this repoThreejs Gameplay Systems
valkor-ai/loom
Build and iterate playable Three.js game systems: starter scaffold, architecture, design briefs, core loops, level and encounter design, entities, input, camera, collision and physics, scoring…
Threejs 3D Generator
valkor-ai/loom
Generate, texture, rig, animate, stylize, convert, and download 3D assets for Three.js games via the Tripo API.
Threejs Image Generator
valkor-ai/loom
Generate and edit 2D image assets for Three.js games with Google's Gemini image API: concept sheets, image-to-3D inputs, texture and material references, sky and background plates, decals, logos…
Threejs Game Director
valkor-ai/loom
Entrypoint for building, upgrading, and finishing Three.js browser games.
Threejs Audio Generator
valkor-ai/loom
Generate, convert, clean, and integrate audio for Three.js browser games with ElevenLabs: sound effects, looping ambience, UI sounds, impact/weapon/vehicle audio, creature and boss stingers…
Threejs QA Release
valkor-ai/loom
Verify and release Three.js browser games: playtest QA, automated bot playtests, mobile and responsive checks, production builds, static-hosting base paths, debug gating, bundle review, screenshots…
Related
Works with
Categories
Questions about Loom
What does Loom do?
Mandatory routing skill. An agent skill from valkor-ai/loom. Loom is an agent skill from valkor-ai/loom. Mandatory routing skill.
When should I use Loom?
Loom fits situations like: explicitly invokes @loom; call the matching Loom MCP route before any repository work; plain delivery requests must start with loom.plan.
How do I install Loom in Claude Code?
Run `npx skills add valkor-ai/loom --skill loom -a claude-code`. Or copy the skill folder (plugins/codex/skills/loom in valkor-ai/loom) into .claude/skills/loom in your project. Claude Code loads it when a task matches its description.
How do I install Loom in Codex?
Run `npx skills add valkor-ai/loom --skill loom -a codex`. Or copy the skill folder (plugins/codex/skills/loom in valkor-ai/loom) into .agents/skills/loom in your project. Codex loads it when a task matches its description.
Can I use Loom 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 valkor-ai/loom --skill loom -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/loom, .gemini/skills/loom, .github/skills/loom and .opencode/skills/loom in your project.
What does Loom need to run?
SKILL.md names no scripts, command-line tools or credentials: Loom is instructions for the agent only.
Does Loom 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 Loom 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 Loom use?
Loom is published under the Apache-2.0 licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.
How many tokens does Loom use?
About 1.4k tokens (SKILL.md is roughly 5.5k 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 Loom?
Skills that share tags, products or a category with Loom: Sprite Gen (aldegad/sprite-gen, 2.6k stars), Blockbench Plugins (jasonjgardner/blockbench-mcp-plugin, 495 stars), Unreal Blueprint Authoring (flopperam/unreal-engine-mcp, 1.1k stars) and Locus Unity Bridge (Misaka-Mikoto-Tech/agent-skills, 278 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
Who maintains Loom?
valkor-ai (a GitHub organization) maintains it in valkor-ai/loom, which has 1,211 GitHub stars. The repository holds 17 skills in this directory. The repository was last updated on October 6, 2026.
Source: valkor-ai/loom on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.