New: 98,000+ skills indexed from GitHub repos with 100+ stars · every skill safety-checkedBrowse top skillsTop skills
Esc to closeBrowse all skills
Submit a skillBrowse skills
Submit a skillBrowse skills

Agent skill

Plugin Web UI Extension

by Mesh-LLM in Mesh-LLM/mesh-llm

A skill your agent uses when maintaining the plugin web UI projection contract, docs, exemplar coverage, or recovery flow for mesh-llm plugin web UI work.

Apache-2.0Auto-check passedFrontend & Design

Install Plugin Web UI Extension

skills CLI
$ npx skills add Mesh-LLM/mesh-llm --skill plugin-web-ui-extension -a claude-code

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

GitHub CLI
$ gh skill install Mesh-LLM/mesh-llm plugin-web-ui-extension --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/Mesh-LLM/mesh-llm.git skills-src && mkdir -p .claude/skills && cp -r skills-src/.agents/skills/plugin-web-ui-extension .claude/skills/plugin-web-ui-extension && 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/

Facts

Skill name
plugin-web-ui-extension
GitHub stars
3.5k
Token cost
~2k tokens
SKILL.md length
971 words
Files
1
Skills in repo
25
Repo updated
First seen
Licence
Apache-2.0

At a glance

A skill your agent uses when maintaining the plugin web UI projection contract, docs, exemplar coverage, or recovery flow for mesh-llm plugin web UI work.

  • Works in 5 steps: Name the author-visible behavior and the… → Locate the current manifest, package,… → State whether the change is additive for… → …
  • Maintaining the plugin web UI projection contract
  • SKILL.md covers Baseline Checks, Create A Work Item, Ownership Boundaries and Settings And Manifests, plus 6 more sections
  • Calls cargo and just

What it does

Plugin Web UI Extension is an agent skill from Mesh-LLM/mesh-llm. Use this skill when maintaining the plugin web UI projection contract, docs, exemplar coverage, or recovery flow for mesh-llm plugin web UI work.

Its SKILL.md is about 2k 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 Frontend & Design, covering Frontend development. The repository describes itself as: Distributed AI/LLM for the people. Share compute privately or publicly to power your agents and chat. The licence is Apache-2.0.

When your agent uses it

  • Maintaining the plugin web UI projection contract
  • Exemplar coverage
  • Recovery flow for mesh-llm plugin web UI work

Example prompts

  • “/plugin-web-ui-extension”

Workflow steps

5 steps, taken from the first numbered list in SKILL.md.

  1. Name the author-visible behavior and the exact lifecycle states it changes.
  2. Locate the current manifest, package, config, runtime, API, UI, exemplar, and
  3. State whether the change is additive for older plugins and hosts. Ask for
  4. List the happy path, invalid package path, disabled projection path, stopped
  5. Identify the exact exemplar and documentation updates that make a new author

What it can do on your machine

Read from SKILL.md and the folder at commit 48bf685. 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

    Shell commands in SKILL.md call:

    • cargo
    • just

    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

Plugin Web UI Extension loads about 2k tokens when it runs. Until then it costs about 42 tokens; SKILL.md has 971 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~42
When it runs · the whole SKILL.md, loaded when a task matches
~2k

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 Mesh-LLM/mesh-llm at commit 48bf685, republished under its Apache-2.0 licence (© Mesh-LLM). 971 words, ~2,004 tokens.

Download SKILL.mdSave it as .claude/skills/plugin-web-ui-extension/SKILL.md (or your agent's skills folder).
name
plugin-web-ui-extension
description
Use this skill when maintaining the plugin web UI projection contract, docs, exemplar coverage, or recovery flow for mesh-llm plugin web UI work.
metadata.short-description
Maintain plugin web UI projection

plugin-web-ui-extension

Use this skill for any follow-up on the plugin web UI projection contract, source-owned docs, or maintainer triage.

Baseline Checks

Start by reading the source-owned contract docs and the maintained exemplar:

  • mesh/docs/plugins/README.md
  • mesh/docs/plugins/exemplars/web-ui/README.md
  • mesh/docs/plugins/exemplars/web-ui/manifest.rs
  • mesh/docs/plugins/exemplars/web-ui/plugin.package.json
  • mesh/docs/plugins/exemplars/web-ui/config.toml
  • mesh/docs/plugins/exemplars/web-ui/bundle/register-mesh-plugin-ui.ts
  • mesh/docs/plugins/exemplars/web-ui/lifecycle-states.json

Then confirm the current contract still matches the implementation:

  • manifest web_ui remains additive
  • web_ui_enabled stays separate from plugin process enabled
  • the existing Configuration Plugins tab still owns Integrations projection
  • the static route stays /plugins/$pluginName/$pageId
  • the API stays under /api/plugins/:plugin/web-ui
  • plugin config mutations stay under /api/plugins/:plugin/web-ui/config

Create A Work Item

Before proposing implementation, turn the request into a contract hypothesis:

  1. Name the author-visible behavior and the exact lifecycle states it changes.
  2. Locate the current manifest, package, config, runtime, API, UI, exemplar, and CLI owners; record the observed baseline instead of assuming it.
  3. State whether the change is additive for older plugins and hosts. Ask for explicit approval before any breaking protocol or package change.
  4. List the happy path, invalid package path, disabled projection path, stopped process path, and non-UI continuity proof.
  5. Identify the exact exemplar and documentation updates that make a new author able to reproduce the behavior without reading host source.

The implementation hypothesis is incomplete until it includes rollback, package validation, config persistence, UI unmount behavior, CLI discoverability, and a docs-only reproduction command.

Ownership Boundaries

Keep the projection split clear:

  • plugin process state controls process startup and shutdown
  • web UI state controls only whether the UI projection mounts
  • invalid or missing bundles do not change non-UI capabilities
  • config-section mounting stays on the existing Configuration Plugins surface
  • no new primary app tab is introduced for plugin routes

Settings And Manifests

When editing manifests or persisted settings, keep the source of truth honest:

  • update the manifest docs before describing new fields elsewhere
  • keep bundle paths package-relative and rooted under one bundle directory
  • require one non-empty v1 bundle id and ensure page/config bundle_id references match it
  • keep page route values slug-only; reject path separators, protocols, and traversal-style dot prefixes
  • preserve the exact route and DTO names already used by the backend and UI
  • treat parent_tab = "integrations" as the only config-section tab value, or omit it
  • keep authoring and persistence guidance tied to the host config schema, not direct file writes from the bundle

Runtime Changes

If runtime behavior changes, check the whole lifecycle path:

  • summary state should still surface none, ready, disabled, invalid, and plugin_not_running
  • the toggle endpoint should continue to persist projection only
  • asset serving should stay same-origin and validated
  • route classification should parse /api/plugins/:plugin/web-ui... by exact suffix after the plugin name so stapled HTTP paths under /api/plugins/:plugin/http/... remain plugin HTTP
  • ready mounts should use backend asset_base_url and refuse to import bundle code when it is missing or off-origin
  • bundle imports should stay gated on ready-state projection eligibility
  • mount and unmount logic should remain idempotent
  • host.config.visible.settings should reflect current plugin-owned settings
  • host.config.requestMutation(...) should persist only plugin settings and reject mismatched plugin names, host-owned keys, and invalid values
  • host.notifications.show(...) should surface through the host shell without adding a generic event bus

Exemplar Coverage

The exemplar under docs/plugins/exemplars/web-ui/ is the drift guard.

  • keep the README in sync with the implementation contract
  • keep lifecycle-states.json aligned with the state matrix
  • keep the sample manifest and bundle contract aligned with the typed host API
  • keep the persisted retention_days setting proof wired through host.config.visible and host.config.requestMutation
  • use the exemplar when adding tests, review notes, or recovery guidance
  • keep it buildable as a standalone crate, generate plugin-manifest.json from its runtime manifest, install the local archive with plugins install --archive, and run its browser-importable JavaScript bundle
  • keep bundle/host-contract.d.ts self-contained; public author examples must not import private console source paths
  • initialize an owner identity before testing settings persistence; reserve auth init --no-passphrase for isolated development and document the normal protected/keychain alternative
  • when the exemplar uses just mesh-client with the branch's debug binary, set MESH_LLM_BIN=target/debug/mesh-llm explicitly
  • prove its MCP status tool still responds after web_ui_enabled is toggled off
Show full SKILL.md (320 more words)Show less

Triage And Recovery

When a report says web UI is broken, triage in this order:

  1. Check whether the plugin process is running.
  2. Check whether the projection is disabled or invalid.
  3. Check whether the installed bundle root exists.
  4. Check whether the page or config-section entry script is inside the bundle.
  5. Check whether the config-section parent tab is integrations.
  6. Check /api/plugins/:plugin/web-ui/config for current settings and schema when config sections render stale values or mutation errors.
  7. Reinstall or update the plugin package and reload mesh-llm if metadata needs revalidation.

If the bundle is missing or invalid, fix the package contents first. Do not disable the plugin process unless the non-UI behavior is also broken.

API And Versioning Alignment

Keep compatibility additive:

  • do not add breaking manifest or route changes without an explicit contract update
  • keep backend and frontend DTO names synchronized
  • keep the route namespace stable under /api/plugins/:plugin/web-ui
  • do not claim sandboxing, remote assets, marketplace discovery, RBAC, or generic settings editing unless the contract has changed and the exemplar has been updated too

Validation And Evidence

Run Cargo commands serially. At minimum validate the author and settings owners:

bash
cargo test -p mesh-llm-plugin --lib
cargo test -p mesh-llm-plugin-manager --lib
cargo test -p mesh-llm-config --lib
cargo test -p mesh-llm-host-runtime --lib

Run the UI typecheck, unit tests, build, the website build when public docs change, and finally just test-all. Confirm just test-all explicitly invokes the plugin, plugin-manager, config, CLI, command, host, and UI test owners; a dependency compiling is not evidence that its unit tests ran.

For release handoff, have one reviewer build a fresh plugin from the published docs without reading crates/** or private UI source. They must install the archive, start it, mount a React-hosted page and Integrations config section, persist a setting, test a non-UI capability with projection disabled, and clean up every process/store/package artifact.

Handoff

When you finish, leave a short note with:

  • what changed
  • which source-owned docs or exemplar files moved
  • which validation checks passed
  • whether any state or recovery path still needs follow-up

© Mesh-LLM, 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 .agents/skills/plugin-web-ui-extension of Mesh-LLM/mesh-llm.

Open the folder on GitHubat commit 48bf685

Compare with similar skills

Plugin Web UI Extension 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.

Plugin Web UI Extension compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Plugin Web UI Extension this skillMesh-LLM/mesh-llm3.5k—~2kAutomated safety check: PassApache-2.0
React Router Developmentremix-run/react-router57k1 repos~1.5kAutomated safety check: PassMIT
React UI State PatternsChrisWiles/claude-code-showcase6.1k8 repos~1.6kAutomated safety check: PassNone
GSAP in Vue, Nuxt and Sveltegreensock/gsap-skills16k4 repos~2.6kAutomated safety check: PassMIT
Svelte Core Best Practicesrilldata/rill2.9k4 repos~1.8kAutomated safety check: PassApache-2.0
Vuetify Playgroundvuetifyjs/vuetify41k—~730Automated safety check: PassCustom licence

Similar skills

  • React Router Development

    remix-run/react-router

    Guides work on React Router apps by first identifying whether the app uses Framework, Data or Declarative mode, then loading the matching reference and the installed package docs.

    57k GitHub starsUsed in 1 repo~1.5k tokens
    Frontend & DesignAuto-check passed

  • React UI State Patterns

    ChrisWiles/claude-code-showcase

    Sets patterns for React interfaces: when to show loading spinners or skeletons, how to surface errors, how to disable buttons during async work and how to handle empty lists.

    6.1k GitHub starsUsed in 8 repos~1.6k tokens
    Frontend & DesignAuto-check passed

  • GSAP in Vue, Nuxt and Svelte

    greensock/gsap-skills

    Shows how to use GSAP in Vue, Nuxt, Svelte and other lifecycle-based frameworks: create after mount, scope selectors to the component, and revert on unmount.

    16k GitHub starsUsed in 4 repos~2.6k tokens
    Frontend & DesignAuto-check passed

  • Svelte Core Best Practices

    rilldata/rill

    Rules for writing idiomatic Svelte 5 code: when to reach for runes like state, derived and effect, and how to handle props, attachments and bindings.

    2.9k GitHub starsUsed in 4 repos~1.8k tokens
    Frontend & DesignAuto-check passed

  • Vuetify Playground

    vuetifyjs/vuetify

    Maintains the Vuetify repo's local Playground.vue so contributors get a realistic reproduction and a short demo they can paste into a pull request description.

    41k GitHub stars~730 tokensUpdated today
    Frontend & DesignAuto-check passed

  • Tabler Astro Dev Server

    tabler/tabler

    Starts the right Tabler dev server, keeps it from clashing with builds and verifies changes in the browser before a page or component is handed back.

    42k GitHub stars~1.2k tokensUpdated today
    Frontend & DesignAuto-check passed

More from Mesh-LLM/mesh-llm

All 25 skills in this repo

  • Release Validation

    Mesh-LLM/mesh-llm

    A skill your agent uses when validating a MeshLLM release candidate or current HEAD against the last GitHub release, assembling the canonical feature/fix/modification inventory, testing locally…

    3.5k GitHub stars~2.6k tokensUpdated today
    Auto-check passed

  • Benchmark Tune

    Mesh-LLM/mesh-llm

    A skill your agent uses when running, debugging, interpreting, or documenting mesh-llm benchmark tune model-serving throughput trials, including choosing…

    3.5k GitHub stars~1.6k tokensUpdated today
    Auto-check passed

  • Config Settings Management

    Mesh-LLM/mesh-llm

    A skill your agent uses when adding, renaming, removing, validating, or exposing mesh-llm config settings, including built-in settings, plugin config schemas, owner-control apply behavior, CLI…

    3.5k GitHub stars~1.4k tokensUpdated today
    Auto-check passed

  • Connect Agents

    Mesh-LLM/mesh-llm

    A skill your agent uses when connecting agent tools or OpenAI clients to mesh-llm — launching or configuring Goose, Claude Code, OpenCode, Pi, curl, or any OpenAI-compatible client against a local…

    3.5k GitHub stars~1.2k tokensUpdated today
    Auto-check passed

  • Hf Bf16 Gguf Conversion Jobs

    Mesh-LLM/mesh-llm

    A skill your agent uses when converting Hugging Face SafeTensors checkpoints into split BF16 GGUF model repos with skippy-quantize on Hugging Face Jobs or a local machine, then publishing the…

    3.5k GitHub stars~1.1k tokensUpdated today
    Auto-check passed

  • Hf Gguf Quant Jobs

    Mesh-LLM/mesh-llm

    A skill your agent uses when creating, monitoring, validating, or documenting low-memory Hugging Face Jobs or local runs that quantize split BF16/FP16 GGUF model repos into custom quant GGUF repos…

    3.5k GitHub stars~1.9k tokensUpdated today
    Auto-check passed

Categories

Questions about Plugin Web UI Extension

What does Plugin Web UI Extension do?

A skill your agent uses when maintaining the plugin web UI projection contract, docs, exemplar coverage, or recovery flow for mesh-llm plugin web UI work. Plugin Web UI Extension is an agent skill from Mesh-LLM/mesh-llm. Use this skill when maintaining the plugin web UI projection contract, docs, exemplar coverage, or recovery flow for mesh-llm plugin web UI work.

When should I use Plugin Web UI Extension?

Plugin Web UI Extension fits situations like: maintaining the plugin web UI projection contract; exemplar coverage; recovery flow for mesh-llm plugin web UI work.

How do I install Plugin Web UI Extension in Claude Code?

Run `npx skills add Mesh-LLM/mesh-llm --skill plugin-web-ui-extension -a claude-code`. Or copy the skill folder (.agents/skills/plugin-web-ui-extension in Mesh-LLM/mesh-llm) into .claude/skills/plugin-web-ui-extension in your project. Claude Code loads it when a task matches its description.

How do I install Plugin Web UI Extension in Codex?

Run `npx skills add Mesh-LLM/mesh-llm --skill plugin-web-ui-extension -a codex`. Or copy the skill folder (.agents/skills/plugin-web-ui-extension in Mesh-LLM/mesh-llm) into .agents/skills/plugin-web-ui-extension in your project. Codex loads it when a task matches its description.

Can I use Plugin Web UI Extension 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 Mesh-LLM/mesh-llm --skill plugin-web-ui-extension -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/plugin-web-ui-extension, .gemini/skills/plugin-web-ui-extension, .github/skills/plugin-web-ui-extension and .opencode/skills/plugin-web-ui-extension in your project.

What does Plugin Web UI Extension need to run?

Going by SKILL.md and its folder, Plugin Web UI Extension needs the command-line tools its instructions call (cargo and just).

Does Plugin Web UI Extension 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 Plugin Web UI Extension 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 Plugin Web UI Extension use?

Plugin Web UI Extension 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 Plugin Web UI Extension use?

About 2k tokens (SKILL.md is roughly 8k 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 Plugin Web UI Extension?

Skills that share tags, products or a category with Plugin Web UI Extension: React Router Development (remix-run/react-router, 57k stars), React UI State Patterns (ChrisWiles/claude-code-showcase, 6.1k stars), GSAP in Vue, Nuxt and Svelte (greensock/gsap-skills, 16k stars) and Svelte Core Best Practices (rilldata/rill, 2.9k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Plugin Web UI Extension?

Mesh-LLM (a GitHub organization) maintains it in Mesh-LLM/mesh-llm, which has 3,485 GitHub stars. The repository holds 25 skills in this directory. The repository was last updated on October 8, 2026.

Source: Mesh-LLM/mesh-llm on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.