Teach agent builder packed frontends
All checks were successful
build / build (push) Successful in 25s
All checks were successful
build / build (push) Successful in 25s
This commit is contained in:
@@ -25,9 +25,13 @@ The single `build(name, prompt)` skill:
|
||||
- `write_agent_skill(...)` — creates valid DeepAgents
|
||||
`skills/<skill-name>/SKILL.md` bundles for generated agents, so rich
|
||||
behavior lives in progressive-disclosure skills instead of fake tools
|
||||
- `init_agent_template(name, description, frontend="react"|"static"|"none")`
|
||||
— starts from the current `a2a-pack` scaffold and can include packed
|
||||
frontend templates under `frontend/` for app-like agents
|
||||
- `test_agent_in_sandbox(name)` — tarballs the workspace project,
|
||||
spins a microVM with the public `a2a-pack` wheel installed, runs
|
||||
`a2a card` to verify the scaffold is valid
|
||||
`a2a card` to verify the scaffold is valid, and prints frontend metadata
|
||||
when a packed app is declared
|
||||
- `cp_deploy_tarball(name, version, public)` — POSTs the tarball
|
||||
to `/v1/agents/from-tarball` on the user's behalf using their
|
||||
forwarded CP JWT
|
||||
|
||||
Reference in New Issue
Block a user