Loading skill
Install any skill in seconds. Free to start, no credit card required.
Get Started Free →stevesolun/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.
Passed 15 of 19 test cases with the skill, and 5 of 19 without it.
and 14 more in the full report
11 fixed6 passed either way5 still failing0 broke
Tokens, turns and time describe resource use, not a dollar price.
One of 10 test cases the skill fixed. Same model, same prompt, with and without the skill.
What is the maximum line limit for a single skill file before the router requires it to be converted into an orchestrator with staged reference files, and how are original source backups named?
| Checked | Without skill | With skill |
|---|---|---|
| Specifies 180 lines as the default threshold for skill splitting | Missed | Passed |
| Identifies .original as the extension used for preserved local backup files | Missed | Passed |
The instructions your model reads when the skill loads.
Scan a repo. Know what the current work needs. Recommend only that. Keep the wiki and graph as the durable catalog behind the decision.
The router manages runtime recommendations for:
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.
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:
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 harness install flow
`-- graph/wiki-graph-runtime.tar.gz # Shipped graph/wiki runtime
test cases passed, vs 5 / 19 without
More skills from the same source and nearby in the registry, with their headline benchmark lift.