MCP Server Builder
anthropics/skills
Guides the design and implementation of Model Context Protocol servers in TypeScript or Python, from tool naming and error messages to evaluation.
A skill your agent uses when the user invokes /loom to route software delivery, knowledge, or deploy work through the Loom MCP server.
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/claude-code/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/claude-code/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/claude-code/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/claude-code/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/claude-code/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/claude-code/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/claude-code/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/claude-code/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/claude-code/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/claude-code/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/claude-code/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/claude-code/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/claude-code/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/claude-code/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
- ~1.9k tokens
- SKILL.md length
- 1,051 words
- Files
- 1
- Skills in repo
- 17
- Repo updated
- First seen
- Licence
- Apache-2.0
At a glance
A skill your agent uses when the user invokes /loom to route software delivery, knowledge, or deploy work through the Loom MCP server.
- The user invokes /loom to route software delivery
- SKILL.md covers Result Discipline, Request Reading, Writing And Submit and Reference Loading, plus 1 more section
- Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md
- Deploy work through the Loom MCP server
What it does
Loom is an agent skill from valkor-ai/loom. Use when the user invokes /loom to route software delivery, knowledge, or deploy work through the Loom MCP server.
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 Agent Workflows, covering MCP servers. 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
- The user invokes /loom to route software delivery
- Deploy work through the Loom MCP server
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 1.9k tokens when it runs. Until then it costs about 30 tokens; SKILL.md has 1,051 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). 1,051 words, ~1,910 tokens.
Download SKILL.mdSave it as
.claude/skills/loom/SKILL.md (or your agent's skills folder).- name
- loom
- description
- Use when the user invokes /loom to route software delivery, knowledge, or deploy work through the Loom MCP server.
loom
You are the Claude Code adapter for Loom MCP. The /loom command chooses the first Loom MCP tool. After that, the current LoomMcpActionResult is the workflow authority.
Do not replace Loom with Claude Plan Mode. Do not inspect project .loom state to decide the next step. Use Loom MCP tools and resources.
When loom.plan returns a plan-conflict user gate, present its numbered choices and descriptions exactly. Choice 1 calls loom.planConflictResolve with continue_current; choice 2 calls it with start_new. Do not call loom.plan again to resolve the conflict.
Result Discipline
auto_runnable: keep going immediately by executing the returnednext.kind.active_operation: only use the observation tools named by the result.user_gate: whenpreResponseContractis present, execute its steps in order before emitting any user-visible response. This means callingloom.inspectRequest, reading only the groups fromrequestReadPlan.groupswhosewhenToReadapplies before the visible response withloom.readFieldGroup, and, for Brainstorm, completing every requiredknowledge_context_planstep before forming options or confirmation. Groups scheduled after user confirmation remain required before the confirm/submit call. The contract is the MCP-side gate for the response; do not answer frompromptalone, skip directly to generic options, or call/loom continueto bypass it. A phase-continuation Brainstorm gate is an active clarification turn, not an optional/loom continue: do not stop at a progress recap or say "if you want to continue". After the contract steps complete, ask the visible current-block question and wait for the user's answer. For a gate withoutpreResponseContract, present the returned prompt and wait for the accepted user response.repairable_error:stopAllowed=false; first callloom.inspectRequestfor the returnedrequestRefand read every required group inrequestReadPlan.groupswithloom.readFieldGroup, then repair only the returned target and resubmit with the returned tool. The returnedagentInstructionis part of the repair contract.- For a
user_gatewhosegate.kindisvsefm_onboarding, present the returned content and wait for the user's choice:1starts verification and2defers it. Callloom.verifywithdecision=requiredfor1ordecision=deferredfor2. Do not wait for an external V-SEFM result; Loom resumes immediately after recording the choice. done,blocked,failed: report the returned status and stop.
Do not stop at a recap while state=auto_runnable or stopAllowed=false. Treat every auto-runnable result as a required continuation checkpoint. Do not mark a local plan complete, send a final answer, or ask whether to continue while the latest Loom result is auto-runnable. A task is complete only after the requested result artifact is written and the returned MCP submit tool succeeds.
Recovery after tool failure is part of the same Loom action. If a shell, patch, test, or nested MCP call fails, inspect the exact failure and retry the smallest corrective step; do not produce a progress summary or final answer. When MCP is called through a wrapper, parse the nested structured result and its state; the wrapper's success or failure is not the Loom workflow state. Only user_gate, done, blocked, or failed permits a final response.
Request Reading
When a result contains requestRef, use loom.inspectRequest and loom.readFieldGroup. requestReadPlan.groups is the only read contract. Do not request individual field paths.
Do not search .loom, do not build custom JSON selectors, and do not infer request schema or submit inputs from old artifacts.
Writing And Submit
Write only to returned writeTargets. Submit only through the returned MCP submit tool using { projectRoot, requestRef, writtenTargetIds? }.
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 task execution, inspect next.requestRef, read the declared groups, implement only the returned task request, respect edit boundaries, write the TaskResult, and submit before reporting completion.
For RunLoomToolNext, inspect the requestRef, read only the returned readGroups, call the returned Loom MCP tool, then retry the returned retryTool before reporting completion.
For deploy repair, respect the returned asset/application boundary and retry through the returned deploy action.
Show full SKILL.md (401 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 any 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. Resolvepathasreferences/<path>relative to the installed Loom skill directory that contains the currently loadedSKILL.md; do not resolve it against the project workspace or the repository'splugins/sharedsource tree. Before reading, verify the resolved file with a direct file check such astest -f; do not use content search to discover whether a path exists. The repository checkout is not the installed reference root, so a missing file there does not prove the selected reference is unavailable. - 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/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 implementation planning; ask Loom to repair the contract only when the selected
referenceLoadPlanis insufficient for the task. - 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 Architecture, TaskPlan, TaskResult, ReviewResult, source files, or user-facing UI. Use references to produce concrete decisions, interface contracts, NFRs, risks, and evidence.
Delivery planning, design, review, repair, and handoff rules are supplied by the current MCP request/result. Do not load separate delivery reference files.
Boundaries
Do not copy field-level contracts, knowledge semantic templates, Brainstorm block schemas, deployment stack rules, or TaskResult schemas into this skill. They belong to the current MCP request/result.
Keep chat output compact; do not paste generated JSON artifacts, full request payloads, full result files, or large logs unless the user explicitly asks.
© 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/claude-code/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 | — | ~1.9k | Automated safety check: Pass | Apache-2.0 | |
| MCP Server Builderanthropics/skills | 180k | 63 repos | ~2.3k | Automated safety check: Pass | Apache-2.0 | |
| MCP Server BuildershareAI-lab/learn-claude-code | 78k | 5 repos | ~1.2k | Automated safety check: Pass | MIT | |
| MCP Integration for Pluginsanthropics/claude-plugins-official | 38k | 11 repos | ~3.1k | Automated safety check: Pass | Apache-2.0 | |
| Crush Configurationcharmbracelet/crush | 29k | — | ~3.7k | Automated safety check: Pass | Custom licence | |
| Context Mode Output Sandboxmksglu/context-mode | 26k | — | ~4.1k | Automated safety check: Pass | Custom licence |
Similar skills
- Official
MCP Server Builder
shareAI-lab/learn-claude-code
Walks through building MCP servers in Python or TypeScript that expose tools, resources and prompts to Claude, with templates, registration and testing.
- Official
MCP Integration for Plugins
anthropics/claude-plugins-official
Explains how to bundle Model Context Protocol servers in a Claude Code plugin, covering config files, stdio, SSE, HTTP and WebSocket server types, and authentication.
Crush Configuration
charmbracelet/crush
Explains how to configure the Crush coding agent with crushrc or crush.json, covering providers, models, LSPs, MCP servers, hooks, permissions and config precedence.
Context Mode Output Sandbox
mksglu/context-mode
Routes large command, file, API and browser output through context-mode tools so only the needed result enters the agent's context, instead of dumping it via Bash.
Warp GUI to Agent CLI Migration
warpdotdev/warp
Migrates the compatible subset of settings and global file-based MCP servers from the Warp desktop app into Warp Agent CLI without exposing credentials or state.
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?
A skill your agent uses when the user invokes /loom to route software delivery, knowledge, or deploy work through the Loom MCP server. Loom is an agent skill from valkor-ai/loom. Use when the user invokes /loom to route software delivery, knowledge, or deploy work through the Loom MCP server.
When should I use Loom?
Loom fits situations like: the user invokes /loom to route software delivery; deploy work through the Loom MCP server.
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/claude-code/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/claude-code/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 1.9k tokens (SKILL.md is roughly 7.6k 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: MCP Server Builder (anthropics/skills, 180k stars), MCP Server Builder (shareAI-lab/learn-claude-code, 78k stars), MCP Integration for Plugins (anthropics/claude-plugins-official, 38k stars) and Crush Configuration (charmbracelet/crush, 29k 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.