Documentation
¶
Overview ¶
Package skills exposes an Agent Skills github.com/Tangerg/scope/skills.ResourceSource as three model-callable tools for progressive disclosure:
- list_skills: every skill's name and description
- load_skill: one skill's instruction body, by exact name
- read_skill_resource: one bundled file under a skill
Bundled scripts are never executed here; the model runs them with its own shell or file tools.
Index ¶
Constants ¶
View Source
const (
DefaultMaxOutputBytes = int64(256 * 1024)
)
Variables ¶
View Source
var ErrNilSource = errors.New("skills: source must not be nil")
Functions ¶
func NewTools ¶
func NewTools(source skillsrc.ResourceSource, config Config) ([]toolcontract.Tool, error)
Types ¶
type Config ¶
type Config struct {
MaxOutputBytes int64
}
Config bounds model-visible content independently of repository storage limits.
type LoadSkillRequest ¶
type LoadSkillRequest struct {
Name string `` /* 136-byte string literal not displayed */
}
LoadSkillRequest uses an exact name; it does not search or broaden the selection.
type ReadSkillResourceRequest ¶
type ReadSkillResourceRequest struct {
Name string `` /* 129-byte string literal not displayed */
Path string `` /* 159-byte string literal not displayed */
}
Resource reads remain confined to the named skill.
Source Files
Click to show internal directories.
Click to hide internal directories.