Loading skill
Install any skill in seconds. Free to start, no credit card required.
Get Started Free →agentlas-ai/team-builder-packaging
Use when generating or auditing a multi-role agent team package with orchestrator, PM Soul, Memory Curator, Policy Gate, workers, eval, QA, handoffs, and runtime adapters.
Passed 23 of 23 test cases with the skill, and 5 of 23 without it.
and 30 more in the full report
18 fixed5 passed either way0 still failing0 broke
Tokens, turns and time describe resource use, not a dollar price.
One of 18 test cases the skill fixed. Same model, same prompt, with and without the skill.
What exact script must be run to validate an Agentlas team package prior to reporting completion, and what argument does it take?
| Checked | Without skill | With skill |
|---|---|---|
| The validation script path is scripts/verify-team-package.sh. | Missed | Passed |
| The validation script accepts package-root as its argument. | Missed | Passed |
The instructions your model reads when the skill loads.
Start with the orchestrator/HQ.
Run contracts/builder-interview-research-gate.md before writing the roster:
ask an 8-12 question first batch, research official sources, similar agent
repositories or comparables, academic/professional theory, and plugin docs,
compare tool/plugin choices, and write the domain-expert synthesis plus
prompt-performance contract.
Add PM Soul or project owner.
Add Memory Curator and Memory Ticket handoff.
Add Policy Gate, eval judge, and QA/evidence gate.
Add workers only for real domain ownership proved by interview or research.
Add docs/builder-interview.md, docs/research-sources.md,
docs/tool-selection.md, docs/domain-expert-synthesis.md,
docs/prompt-performance-contract.md, and
.agentlas/capability-eval-plan.json unless explicitly creating a minimal
private scaffold.
Encode handoff and return contracts.
Emit one orchestrator/HQ global command in .agentlas/global-commands.json
and runtime command files. Do not expose worker commands unless requested.
9b. Declare the execution graph in manifest.json. This is what the Hub runtime
reads to build the team; a package that omits it is published, charged for as
a team, and can never be called:
{
"entrypoints": { "orchestrator": "agents/00-orchestrator/agent.md" },
"roster": ["agents/10-<role>/agent.md", "agents/20-<role>/agent.md"]
}
Write both keys explicitly. The runtime also accepts older spellings
(entrypoint, orchestrator, entry; workers, members, team) and can
derive the roster from agents/<name>/agent.md, but relying on that leaves
the team's shape implicit and it drifts. Note that entry in agentlas.json
is the PACKAGE entrypoint, not the team manager — never reuse it for that.
Emit runtime adapters and package verification.
Run scripts/verify-team-package.sh <package-root> before reporting
test cases passed, vs 5 / 23 without
Published skills whose descriptions closely match this one, with their headline benchmark lift.
More skills from the same source and nearby in the registry, with their headline benchmark lift.