Loading skill
Install any skill in seconds. Free to start, no credit card required.
Get Started Free →fradser/get-context
Execute this when the user requests code context for a repository, library, or any natural-language code/technology question using DeepWiki, Context7, Exa, git clone, and/or web search+fetch.
Passed 7 of 15 test cases with the skill, and 4 of 15 without it.
and 7 more in the full report
6 fixed5 passed either way11 still failing1 broke
Tokens, turns and time describe resource use, not a dollar price.
One of 6 test cases the skill fixed. Same model, same prompt, with and without the skill.
Parse target argument vue@3 with default method settings for context lookup.
| Checked | Without skill | With skill |
|---|---|---|
| Classifies vue@3 as a library target. | Missed | Passed |
| Sets method selection to default value all. | Missed | Passed |
The instructions your model reads when the skill loads.
Launch a code-context:context-researcher agent that executes the full workflow in an isolated context. The input is arbitrary: a natural-language question, a repo slug, a library name, or several of these at once.
$ARGUMENTS into positional targets and the optional --method flag.
--method= accepts a comma-separated list from deepwiki,context7,exa,clone,web,all. Default: all."compare zustand vs jotai state management" is a single natural-language query.facebook/react zustand = two targets.owner/repo) or git URL → repo target (DeepWiki / clone).react, fastapi, next) or with a version hint (react@18) → library target (Context7).package.json, go.mod, pyproject.toml, Cargo.toml) and use detected dependencies as targets.Pass the parsed targets and method list to the agent verbatim — do not pre-resolve them in the main context.
Code context request.
Targets (classify each as repo / library / natural-language query):
<positional targets, one per line; or "auto-detect from local dependency manifests" if empty>
Methods to use (in priority order; "all" = let agent choose per target):
<comma-separated method list, default "all">
Local context already known: <one line on what the cwd already contains, or "none">
Launch code-context:context-researcher using the prompt template above. The agent returns a synthesized summary; the main context stays clean regardless of lookup volume.
test cases passed, vs 4 / 15 without
More skills from the same source and nearby in the registry, with their headline benchmark lift.