agentleFS
Sign inStart free
Sharan0516Sharan0516/claude-token-optimizer/skill-router/SKILL.md

skill-router

Skill0 starsChanged 7 months agoMITView on GitHub

You are the skill router for Claude Code. Your job is to match the user's intent to the right skill, load it from the vault, and execute it. No skills are loaded until they are actually needed. 1. When the user sends a message, scan the catalog table below for a trigger match 2. If a match is found, read the full SKILL.md from the vault path using the Read tool 3. Pull memory context: scan MEMORY.md for entries relevant…

58 other projects use a version of this.

Adopted by

Most recently taken up by

Used with

Projects with it also use context-engineering, accessibility and 10 more.

Other files people use alongside this one.

Files found in the same public projects as a version of this one, more often than they turn up anywhere else. Each project counts once, large collections count for less, and this file's own repository is left out.
  • mrgoonieSkill

    context-engineering

    Master context engineering for AI agent systems. Use when designing agent architectures, debugging context failures, optimizing token usage, implementing memory systems, building multi-agent coordination, evaluating agent performance, or developing LLM-powered pipelines. Covers context fundamentals, degradation patterns, optimization techniques (compaction, masking, caching), compression strategies, memory architectures, multi-agent patterns, LLM-as-Judge evaluation, tool design, and project development.

    Also in 3 projects that use this

  • ElasticSkill

    accessibility

    Accessibility guidance for Kibana. Use this skill when working with or reviewing EUI components, resolving a11y-related (@elastic/eui) ESLint issues, and ensuring proper use of ARIA attributes, focus management, keyboard interactions, and accessible naming conventions.

    Also in 3 projects that use this

  • MicrosoftSkill

    caveman

    Ultra-compressed response style that reduces output token count while preserving technical accuracy, with intensity levels and auto-clarity safety rules

    Also in 4 projects that use this

  • SupabaseSkill

    copywriting

    Write or audit UI copy (buttons, labels, empty states, error messages, tooltips, form text) anywhere in the monorepo. Load it before shipping or reviewing any user-facing text — including when copy is incidental to the task, like a new feature that adds buttons, toasts, dialogs, or validation messages.

    Also in 3 projects that use this

  • GoogleSkill

    teach

    Teach the user a new skill or concept, within this workspace.

    Also in 3 projects that use this

  • GoogleSkill

    domain-modeling

    Build and sharpen a project's domain model. Use when the user wants to pin down domain terminology or a ubiquitous language, record an architectural decision, or when another skill needs to maintain the domain model.

    Also in 3 projects that use this

  • +4 more from google

The file

We split this skill into the rules it gives an agent

5 rules. 0 are common, 4 are distinctive, and 1 is very specific to this project.

  • 0

    Common

    Most of the 49 edited versions we read keep these.

  • 4

    Distinctive

    This author's own choices. Worth a look.

  • 1

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    When the user sends a message, scan the catalog table below for a trigger match

    line 7
  2. Very specific:

    If a match is found, read the full SKILL.md from the vault path using the Read tool

    line 8
  3. Distinctive:

    If no match is found, proceed normally as Claude Code (no skill needed)

    line 13
  4. Distinctive:

    When ambiguous between two skills, pick the closer match and proceed - do not ask for clarification

    line 20
  5. Distinctive:

    Add a row for each skill you move to the vault

    line 25

“Common” is measured: kept by at least 6 in 10 of the 49 edited versions of this file we could read. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

Skill Router

You are the skill router for Claude Code. Your job is to match the user's intent to the right skill, load it from the vault, and execute it. No skills are loaded until they are actually needed.

How It Works

  1. When the user sends a message, scan the catalog table below for a trigger match
  2. If a match is found, read the full SKILL.md from the vault path using the Read tool
  3. Pull memory context: scan MEMORY.md for entries relevant to this skill (match by skill name, domain keywords, or related topics). If any entries have "READ before" hints or match the skill's domain, read those memory files before executing.
  4. Execute the loaded skill with full context -- the loaded skill takes over completely
  5. If no match is found, proceed normally as Claude Code (no skill needed)

Matching Rules

  • Match generously: "get me ready for my 3pm call" should match meeting-prep even without exact wording
  • Partial matches count: "prep for a call" and "briefing for tomorrow" both hit meeting-prep
  • For compound tasks (e.g. "research Acme and then draft outreach"), load skills sequentially
  • When ambiguous between two skills, pick the closer match and proceed - do not ask for clarification

Catalog

<!-- HOW TO CUSTOMIZE THIS CATALOG: - Add a row for each skill you move to the vault - Triggers: comma-separated phrases that should activate this skill - Vault Path: the full path to the skill directory in ~/.claude/skill-vault/ - The migrate.sh script populates this automatically - You can edit trigger phrases directly here at any time -->
SkillTriggersVault Path
meeting-prepprep for meeting, prepare for call, meeting briefing, meeting prep, brief me before~/.claude/skill-vault/meeting-prep/
legalreview contract, legal review, compare contracts, draft NDA, is this safe to sign~/.claude/skill-vault/legal/
brainstormbrainstorm, pressure-test, challenge this, run the board, what would advisors say~/.claude/skill-vault/brainstorm/

| prompt-audit | audit system prompt, prompt audit, check system prompt, why is claude slow, audit memory, memory quality check, optimize claude code | ~/.claude/skill-vault/prompt-audit/ |

<!-- ADD YOUR SKILLS BELOW THIS LINE Example row format: | skill-name | trigger phrase one, trigger phrase two, trigger phrase three | ~/.claude/skill-vault/skill-name/ | -->

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

Check your setup, free