Agent skill · Design & Presentation

skill-router

Repo-aware recommendation manager for ctx. Scans the active repository, identifies stack and workflow signals, recommends a capped set of skills, agents, and MCP servers, and unloads helpers that no longer match the current work after user confirmation. Harnesses are recommended by the custom-model onboarding flow or loop adapters and then attach to the same recommendation layer.

stevesolungithub.com/stevesolunGitHub ↗
claude-codeships scriptsMIT
Install
npx skills add stevesolun/ctx --skill docs --agent claude-code

Same command for any agent — swap --agent for codex, cursor, copilot.

Facts
Files in the skill folder: 42
SKILL.md size: 9 KB
Bundled scripts: yes
Path: docs/SKILL.md
Open the folder on GitHub →
Where it comes from
Stars: 569
Language: Python

Weekly change comes from our own snapshots, not the repository page — it measures attention, not adoption.

From the SKILL.md

# Skill Router Scan a repo. Know what the current work needs. Recommend only that. Keep the wiki and graph as the durable catalog behind the decision. ## Scope The router manages runtime recommendations for: - skills - agents - MCP servers Harnesses are separate catalog entities. They are recommended when a user wants to run ctx with a non-Claude-Code host, local model, API model, or external loop adapter. Once attached, the harness calls the same skills/agents/MCP recommendation engine. ## Problem Every loaded helper costs tokens, attention, and operational surface area. Most sessions need a small top-scored bundle from the shipped graph, not every entity ctx knows about. Loading too much: - wastes context on irrelevant instructions, - causes misfires when a helper matches the wrong task, - slows the agent loop, and - creates conflicting instructions. ## Architecture ```text ctx/ |-- src/scan_repo.py # Repo scanner -> stack profile |-- src/ctx/core/resolve/resolve_skills.py # Profile -> load/unload manifest |-- src/ctx/core/resolve/recommendations.py # Shared scoring/ranking engine |-- src/ctx/adapters/ # Host adapters + generic tools |-- src/harness_install.py # Custom-model harn

What's inside
Steps it walks through
  1. Scope
  2. Problem
  3. Architecture
  4. Startup Flow
  5. Scanner
  6. Detection Categories
  7. Scanning Rules
  8. Resolver
  9. Ranking Signals
  10. Wiki And Graph Contract
  11. Entity Sources
  12. Micro-Skill Gate
  13. Core Operations
  14. Full Scan
Ships with 24 files
  • assets/javascripts/catalog.js
  • assets/javascripts/repo-stats-refresh.js
  • backup-hook-install.md
  • catalog.md
  • dashboard.md
  • enterprise-readiness-review.md
  • entity-onboarding.md
  • harness/attaching-to-hosts.md
  • harness/clean-host-contract.md
  • harness/loopflow-adapter-demo.md
  • huggingface-publish.md
  • index.md
  • knowledge-graph.md
  • marketplace-registry.md
  • memory-anchor.md
  • plans/ctx-agent-reviewer-workbench.md
  • qa/dashboard-user-story-status.csv
  • qa/feature-user-story-status.csv
  • services/macos/com.claude.backup.watchdog.plist
  • services/systemd/claude-backup-watchdog.service
  • skill-lifecycle-and-dashboard.md
  • skill-quality-install.md
  • skill-router/index.md
  • skill-stack-matrix.md
first 24 of 42
More from ctx
All skills →
About this skill
What does the skill-router skill do?

Repo-aware recommendation manager for ctx. Scans the active repository, identifies stack and workflow signals, recommends a capped set of skills, agents, and MCP servers, and unloads helpers that no longer match the current work after user confirmation. Harnesses are recommended by the custom-model onboarding flow or loop adapters and then attach to the same recommendation layer.

How do I install it?

Run `npx skills add stevesolun/ctx --skill docs --agent claude-code` — it drops the skill into your project so the agent can pick it up. Swap the --agent value for codex, cursor or copilot if you use one of those.

Where does this skill come from?

From stevesolun/ctx, a repository with 569 stars. We read it straight from the repository tree rather than a submitted listing, so what you see here is what is actually published.

Is a popular skill a good skill?

Not necessarily. Stars measure attention, not adoption — a repository can trend for a week and be abandoned. That is why we show the weekly change from our own snapshots next to the total, instead of a single flattering number.

Keep going