plugins/babysitter-github/skills/babysit/SKILL.md
Orchestrate via @babysitter. Use this skill when asked to babysit a run, orchestrate a process or whenever it is called explicitly. (babysit, babysitter, orchestrate, orchestrate a run, workflow, etc.)
npx skillsauth add a5c-ai/babysitter babysitInstall this skill globally with one command. Works with Claude Code, Cursor, and Windsurf.
3 of 9 scanners reported clean
Some scanners were skipped, did not run, or reported a non-clean status. Review each row below.
Orchestrate .a5c/runs/<runId>/ through iterative execution.
Read the SDK version from versions.json to ensure version compatibility:
SDK_VERSION=$(node -e "try{console.log(JSON.parse(require('fs').readFileSync('${PLUGIN_ROOT}/versions.json','utf8')).sdkVersion||'latest')}catch{console.log('latest')}")
sudo npm i -g @a5c-ai/babysitter-sdk@$SDK_VERSION
# sudo is depending on the env and system
then use the CLI alias: CLI="babysitter"
Alternatively, use the CLI alias: CLI="npx -y @a5c-ai/babysitter-sdk@$SDK_VERSION"
make sure you have jq installed and available in the path. if not, install it.
Run the following command to get full orchestration instructions:
babysitter instructions:babysit-skill --harness github-copilot --json
Follow the instructions returned by the command above to orchestrate the run.
IMPORTANT: Unlike Claude Code, GitHub Copilot CLI does NOT have a Stop hook
that can drive the orchestration loop between turns. The sessionEnd hook output
is ignored and cannot block or restart the session.
Therefore, you MUST use in-turn iteration: run the full orchestration loop within a single session turn. The pattern is:
babysitter run:iterate --json -- get pending actionstask:post)babysitter run:iterate --json -- check for more pending actionsAll iteration happens within the same turn -- do NOT rely on hooks to re-enter
the orchestration loop. The agent drives the loop directly by calling
run:iterate repeatedly until completion.
# Initial iterate
RESULT=$(babysitter run:iterate --run-id "$RUN_ID" --json)
STATUS=$(echo "$RESULT" | jq -r '.status')
while [ "$STATUS" != "completed" ] && [ "$STATUS" != "failed" ]; do
# Process pending actions from RESULT
# ... execute tasks, post results ...
# Iterate again
RESULT=$(babysitter run:iterate --run-id "$RUN_ID" --json)
STATUS=$(echo "$RESULT" | jq -r '.status')
done
development
Model documentation skill for generating model cards following Google's model card framework.
development
MLflow integration skill for experiment tracking, model registry, and artifact management. Enables LLMs to log experiments, compare runs, manage model lifecycle, and retrieve artifacts through the MLflow API.
data-ai
LIME-based local explanation skill for individual predictions across tabular, text, and image data.
devops
Kubeflow Pipelines skill for ML workflow orchestration, component management, and Kubernetes-native ML.