Discovered skills and agents

gptr_skills() lists the Agent Skills gptr can see: the project's .gptr/skills, .agents/skills and .claude/skills, the user's skill directories, the skills of gptr and of attached packages, and those of enabled plugins. Project skills are listed even when the project is not trusted (their source reads project (untrusted)), but only trusted skills enter the catalog the model sees. gptr_agents() lists agent definition files the same way. Both only read files.

Usage

gptr_skills(scope = c("all", "project", "user", "packages"))

gptr_agents(scope = c("all", "project", "user", "packages"))

Arguments

scope

One of "all", "project", "user" or "packages".

Value

gptr_skills(): a gptr_skills data frame with columns name, description, source, path, tokens (catalog cost) and visible. gptr_agents(): a gptr_agents data frame with columns name, description, model, backend, source and path.

Details

A skill is a directory containing SKILL.md with a YAML description and optional name. Its body is read on demand, or preloaded with peter(skills = "name"). disable-model-invocation: true hides it from automatic catalog selection, while explicit preloading remains available. allowed-tools is metadata, not a permission rule.

See also

gptr_agent, gptr_plugins, gptr_trust; vignette("skills-and-plugins", package = "gptr") for skills, templates and agent files.

Examples

gptr_skills("packages")
#>   name                source   visible  description      path             tokens
#> 1 gptr-orchestration  builtin  FALSE    Write multi-...  /tmp/Rtmpu3C...  50
#> 2 high-performance-r  builtin  TRUE     Fast data wo...  /tmp/Rtmpu3C...  49
#> 3 shiny-bslib         builtin  TRUE     Build Shiny ...  /tmp/Rtmpu3C...  30
#> 
#> # 3 rows
gptr_agents()
#>   name      source   description           model  backend  path
#> 1 explorer  builtin  Explores a projec...  NA     auto     /tmp/Rtmpu3CdAi/re...
#> 2 reviewer  builtin  Reviews R code an...  NA     auto     /tmp/Rtmpu3CdAi/re...
#> 
#> # 2 rows