Loading skill
Install any skill in seconds. Free to start, no credit card required.
Get Started Free →hashgraph-online/init
Set up docflow in a repo with no docs yet: scaffold the docs tree, write docflow.json, add agent guidance.
Passed 15 of 20 test cases with the skill, and 8 of 20 without it.
and 7 more in the full report
10 fixed8 passed either way4 still failing2 broke
Tokens, turns and time describe resource use, not a dollar price.
One of 10 test cases the skill fixed. Same model, same prompt, with and without the skill.
Setup completed using a local `.agenteam/config.yaml` file because no team configuration existed. What share recommendation should be appended to the summary?
| Checked | Without skill | With skill |
|---|---|---|
| Recommends running @ATeam share-config to share settings with team members | Missed | Passed |
The instructions your model reads when the skill loads.
Set up AgenTeam for the current project.
Resolve the runtime path first, then use the runtime entrypoint itself as the readiness check. Do not spend time on separate environment probes if the runtime can tell you what is missing.
Fast path:
python3 <plugin-dir>/runtime/agenteam_rt.py --help
If Python or dependencies are missing, the runtime prints a JSON error. Only then offer the minimal install fix:
pip install pyyaml toml
Check for config in this order:
.agenteam/config.yaml (personal).agenteam.team/config.yaml (team shared)agenteam.yaml.agenteam.team/config.yaml exists (team project): Use it as the
team config. Do not create .agenteam/config.yaml — personal overrides
are opt-in. Skip to step 4 (validate)..agenteam/config.yaml or agenteam.yaml exists: Ask the user if
they want to reconfigure or keep existing config. If keeping, skip to step 4.Copy the template:
test cases passed, vs 8 / 20 without
More skills from the same source and nearby in the registry, with their headline benchmark lift.