Menu
Scaffold missing files for a Punt Labs project
Install with Codex or Claude Copy this prompt, paste it into Codex, Claude, or another assistant, and let it review the skill page and install it for you.
Based on SOC occupation classification
Execute an automation playbook โ deterministic scripts with LLM error recovery
Check compliance against Punt Labs standards
Scan for personally identifiable information
LLM-powered standards reconciliation for a Punt Labs project
| name | init |
| description | Scaffold missing files for a Punt Labs project |
| disable-model-invocation | true |
Run the deterministic scaffolding tool for a Punt Labs project.
If the user provided a project path as an argument, use it. Otherwise default to ..
First, run detection to see what we're working with:
punt init --language "" <path> 2>&1 || true
If the output shows Language: none, ask the user which language the project uses (python, node, swift), then re-run with the flag:
punt init --language <chosen-language> <path>
If a language was detected, just run:
punt init <path>
Report the output to the user. Explain what files were generated and what manual steps remain.
If the user wants contextual reconciliation (workflow diffing, CLAUDE.md quality review, permission cleanup), suggest the reconcile skill as the next step.