Agent skill

Skill Router

by juew in juew/Skill-Routing-Kit

A skill your agent uses when the user explicitly asks to diagnose or improve Codex skill/plugin routing, determine which skill or plugin should handle a request, refresh or check a skill registry…

MITAuto-check passedAgent Workflows

Install Skill Router

skills CLI
$ npx skills add juew/Skill-Routing-Kit --skill skill-router -a claude-code

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

GitHub CLI
$ gh skill install juew/Skill-Routing-Kit skill-router --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/juew/Skill-Routing-Kit.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/skill-router .claude/skills/skill-router && 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
skill-router
GitHub stars
120
Used in
1 other repo
Token cost
~803 tokens
SKILL.md length
370 words
Files
2 (incl. references)
Skills in repo
1
Repo updated
First seen
Licence
MIT

At a glance

A skill your agent uses when the user explicitly asks to diagnose or improve Codex skill/plugin routing, determine which skill or plugin should handle a request, refresh or check a skill registry…

  • Works in 6 steps: Classify the user request → Read the registry if available. → Identify recommended skill/plugin… → …
  • The user explicitly asks to diagnose
  • SKILL.md covers Boundaries, When To Use, When Not To Use and Diagnostic Workflow, plus 2 more sections
  • Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md

What it does

Skill Router is an agent skill from juew/Skill-Routing-Kit. Use when the user explicitly asks to diagnose or improve Codex skill/plugin routing, determine which skill or plugin should handle a request, refresh or check a skill registry, investigate why a skill/plugin did not trigger, or review skill descriptions for trigger quality. Do not use for ordinary task execution when a concrete domain skill clearly applies, unless routing is ambiguous or the user asks for routing.

Its SKILL.md is about 800 tokens, which your agent loads only when the skill is triggered. The skill folder holds 2 other files, including reference files (for example `references/capability-card-schema.md`).

It sits in Agent Workflows, covering Skill management. The repository describes itself as: Skill Routing Kit 是一个本地优先的 Codex 插件,用来提升 skill 和插件的命中率,同时避免引入缓慢、强侵入的运行时路由层。 The licence is MIT.

When your agent uses it

  • The user explicitly asks to diagnose
  • Improve Codex skill/plugin routing
  • Determine which skill
  • Plugin should handle a request

Example prompts

  • “/skill-router”

Workflow steps

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

  1. Classify the user request
  2. Read the registry if available.
  3. Identify recommended skill/plugin candidates.
  4. Apply local-first and connector-explicit rules.
  5. Return concise output
  6. If debug mode is requested, include skipped candidates and scoring details.

What it can do on your machine

Read from SKILL.md and the folder at commit 40036f4. 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

Skill Router loads about 803 tokens when it runs, and up to ~1.2k if it reads all its reference files. Until then it costs about 108 tokens; SKILL.md has 370 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~108
When it runs · the whole SKILL.md, loaded when a task matches
~803
With references · SKILL.md plus every file in references/, read only if the agent opens them
~1.2k

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 juew/Skill-Routing-Kit at commit 40036f4, republished under its MIT licence (© juew). 370 words, ~803 tokens.

Download SKILL.mdSave it as .claude/skills/skill-router/SKILL.md (or your agent's skills folder). This skill also uses 1 other file; get the full folder from GitHub.
name
skill-router
description
Use when the user explicitly asks to diagnose or improve Codex skill/plugin routing, determine which skill or plugin should handle a request, refresh or check a skill registry, investigate why a skill/plugin did not trigger, or review skill descriptions for trigger quality. Do not use for ordinary task execution when a concrete domain skill clearly applies, unless routing is ambiguous or the user asks for routing.

Skill Router

Use this skill as a diagnostic and routing-assistance layer. It does not replace Codex native skill discovery, Superpowers process skills, or subagent orchestration. It helps decide which capabilities are relevant, why they are relevant, and when not to use them.

Boundaries

  • Do not execute the user's domain task unless the user asks you to continue after routing.
  • Do not assume external connectors are authenticated or can see data.
  • Do not treat registry cards as the source of truth. Use them as hints with provenance.
  • Do not perform dynamic scanning unless the user asks to refresh or check the registry.
  • Prefer local files, local repositories, browser verification, and build/test commands unless the user explicitly names an external app or the source of truth clearly lives there.

When To Use

Use this skill when the user asks things like:

  • "Which skill should handle this?"
  • "Why did this skill not trigger?"
  • "Refresh the skill registry."
  • "Review this skill description for trigger quality."
  • "List likely skills/plugins for this task."
  • "Help me improve skill/plugin hit rate."

When Not To Use

Do not use this skill for simple tasks with an obvious primary skill:

  • Editing a local PDF: use the PDF skill.
  • Creating a slide deck: use the presentation skill.
  • Debugging a failing test: use systematic debugging first.
  • Implementing a frontend app: use frontend app building/testing skills.

If the task is complex or ambiguous, perform a brief routing check and then continue with the selected primary skill.

Show full SKILL.md (127 more words)Show less

Diagnostic Workflow

  1. Classify the user request:
    • task type: explain, create, edit, debug, analyze, test, review, deploy
    • source: local, web, GitHub, Gmail, Drive, Notion, Slack, Figma, Linear
    • artifact: code, document, spreadsheet, presentation, PDF, image, webpage, report
    • process need: planning, debugging, TDD, verification, review, orchestration
  2. Read the registry if available.
  3. Identify recommended skill/plugin candidates.
  4. Apply local-first and connector-explicit rules.
  5. Return concise output:
    • Recommended skill
    • Helper skills
    • Why
    • Do not use
    • Needs confirmation
  6. If debug mode is requested, include skipped candidates and scoring details.

Output Format

text
Recommended skill:
- ...

Helper skills:
- ...

Why:
- ...

Do not use:
- ...

Needs confirmation:
- ...

Registry Maintenance

Use scripts/build_registry.py only when the user explicitly asks to refresh the registry or when the registry is stale, missing, or inconsistent.

Use scripts/route_request.py --check-registry to inspect registry health.

See references/capability-card-schema.md for card fields and provenance requirements.

© juew, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

SKILL.md and 1 other file (references) in skills/skill-router of juew/Skill-Routing-Kit.

  • SKILL.md
  • references/capability-card-schema.md

Open the folder on GitHubat commit 40036f4

Used in 1 other repository

We found 1 copy of this SKILL.md (exact, near-identical or edited) in other folders, from 1 other GitHub owner. This page covers the copy in juew/Skill-Routing-Kit, which our catalogue first saw on October 7, 2026.

Compare with similar skills

Skill Router 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 Router compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Skill Router this skilljuew/Skill-Routing-Kit1201 repos~803Automated safety check: PassMIT
Skill Downloadernicepkg/ai-workflow285—~1.1kAutomated safety check: PassMIT
Darwin Skill Optimizeralchaincyf/darwin-skill6.2k1 repos~4.7kAutomated safety check: PassMIT
Using Agent Skillsaddyosmani/agent-skills103k4 repos~2.4kAutomated safety check: PassMIT
Ponytail Help CardDietrichGebert/ponytail158k—~728Automated safety check: PassMIT
Skill Creatorzhayujie/CowAgent47k—~4.7kAutomated safety check: NotesMIT

Similar skills

  • Skill Downloader

    nicepkg/ai-workflow

    Download and install Claude Code skills from various sources.

    285 GitHub stars~1.1k tokensUpdated 8 mo ago
    Agent WorkflowsAuto-check passed
  • Darwin Skill Optimizer

    alchaincyf/darwin-skill

    Scores SKILL.md files on a nine-dimension rubric, then improves them in a keep-or-revert loop with independent judge agents, test prompts, git history and human checkpoints.

    6.2k GitHub starsUsed in 1 repo~4.7k tokens
    Agent WorkflowsAuto-check passed
  • Using Agent Skills

    addyosmani/agent-skills

    Meta-skill for choosing which workflow skill fits the task at hand, plus always-on habits: surface assumptions, stop on confusion, push back, keep it simple and stay in scope.

    103k GitHub starsUsed in 4 repos~2.4k tokens
    Agent WorkflowsAuto-check passed
  • Ponytail Help Card

    DietrichGebert/ponytail

    Shows a one-shot quick-reference card for the ponytail skills: intensity levels, the six commands, and how to turn it off, set a default mode and update.

    158k GitHub stars~728 tokensUpdated today
    Agent WorkflowsAuto-check passed
  • Skill Creator

    zhayujie/CowAgent

    Guides creating, installing and updating agent skills in a workspace: SKILL.md frontmatter, bundled scripts and references, with scripts to scaffold, validate and package.

    47k GitHub stars~4.7k tokensUpdated today
    Agent WorkflowsAuto-check: notes
  • Task Observer

    rebelytics/one-skill-to-rule-them-all

    Monitors task execution for skill improvement opportunities.

    3.2k GitHub starsUsed in 1 repo~12k tokens
    Agent WorkflowsAuto-check passed

Questions about Skill Router

What does Skill Router do?

A skill your agent uses when the user explicitly asks to diagnose or improve Codex skill/plugin routing, determine which skill or plugin should handle a request, refresh or check a skill registry…. Skill Router is an agent skill from juew/Skill-Routing-Kit. Use when the user explicitly asks to diagnose or improve Codex skill/plugin routing, determine which skill or plugin should handle a request, refresh or check a skill registry, investigate why a skill/plugin did not trigger, or review skill descriptions for trigger quality.

When should I use Skill Router?

Skill Router fits situations like: the user explicitly asks to diagnose; improve Codex skill/plugin routing; determine which skill; plugin should handle a request.

How do I install Skill Router in Claude Code?

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

How do I install Skill Router in Codex?

Run `npx skills add juew/Skill-Routing-Kit --skill skill-router -a codex`. Or copy the skill folder (skills/skill-router in juew/Skill-Routing-Kit) into .agents/skills/skill-router in your project. Codex loads it when a task matches its description.

Can I use Skill Router 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 juew/Skill-Routing-Kit --skill skill-router -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/skill-router, .gemini/skills/skill-router, .github/skills/skill-router and .opencode/skills/skill-router in your project.

What does Skill Router need to run?

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

Does Skill Router 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 Skill Router 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 Skill Router use?

Skill Router 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 Skill Router use?

About 803 tokens (SKILL.md is roughly 3.2k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full. Its references folder adds about 444 tokens, read only when the agent opens those files.

What are the alternatives to Skill Router?

Skills that share tags, products or a category with Skill Router: Skill Downloader (nicepkg/ai-workflow, 285 stars), Darwin Skill Optimizer (alchaincyf/darwin-skill, 6.2k stars), Using Agent Skills (addyosmani/agent-skills, 103k stars) and Ponytail Help Card (DietrichGebert/ponytail, 158k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Skill Router?

juew (a GitHub user) maintains it in juew/Skill-Routing-Kit, which has 120 GitHub stars. The repository was last updated on June 18, 2026.

Source: juew/Skill-Routing-Kit on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.