stabilization-loop
Stabilize the project:
- If there are any local changes, then commit the current code to the local Git repository with commit message "Claude".
- Make sure that the code compiles and the linter checks pass. If not, then fix those and go to step 1.
- Stop the server if it is running.
- Start the server, wait until it is completely up and ready.
- Run the tests.
- If any test fails, then analyze the test errors, try to fix them and go to step 1.
- If the server crashes or logs an error, then analyze the crashes or errors, try to fix them and go to step 1.
- If you have the
consistency-checkskill, then run that on the project as well. - Start the server, wait until it is completely up and ready.
- Run the tests.
- If any test or the server fails, then go to step 6.
- Stop the server.
- Commit the current code.
- Tag the latest commit as "works".
- Provide a concise report.
Remarks:
- CRITICAL: NEVER run more than one instance of the server at the same time.
More from viktor-ferenczi/skills
python-guidelines
Guiding principles for writing clear, concise, human readable and maintainable Python code.
20gcp-batch-inference
Running batch inference on Google Cloud (also known as Vertex AI)
18silent-cli
Environment variables and parameters for running command line programs reliably in non-interactive environments (unattended). Includes silent modes, color/disable TTY, and reduced output options for 155 CLI tools.
12busybox-on-windows
How to use a Win32 build of BusyBox to run many of the standard UNIX command line tools on Windows.
11recursive-language-model
Recursive Language Model workflow for processing documents that exceed context window limits. Uses a persistent Python REPL and subordinate agents to chunk, search, and analyze large context files.
9consistency-check
Checks the internal consistency of a software project, fixes any issues found.
3