code-writer
Skill1 starsChanged 59 days agoApache-2.0View on GitHub
Delegate boilerplate code generation to a cheaper Claude model via shuntkit. Use for tests, config, docstrings, type stubs, or any generation where >80% is predictable from a reference file.
2 other projects use a version of this, 1 of them edited.
Adopted by
Most recently taken up by
- SalehB1/shunt-anywhereedited, first seen Sep 9, 2026
- orange4664/research-skillstheir own version, first seen Mar 31, 2026
Other versions2 projects use a version of this.
Word for word · 0
None found.
Edited · 1
- SalehB1/shunt-anywhere★ 451% same
Wrote their own version · 1
- orange4664/research-skills★ 41same name
How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.
In this repositoryOne other file it gives its agents.
- bulk-readerSkill
The file
Files
# Generate and write directly to the target file
PYTHONPATH="${CLAUDE_PLUGIN_ROOT}/src" python3 -m shuntkit write --spec "<what to generate>" \
--reference <file-whose-style-to-match> \
--context <source-file-the-output-is-about> [<more>] \
--target <output-path>
# Output to stdout instead (omit --target)
PYTHONPATH="${CLAUDE_PLUGIN_ROOT}/src" python3 -m shuntkit write --spec "<what to generate>" --reference <ref> --context <src>--reference is required: it is the file whose conventions (imports, naming,
test style) the output must match.
--context is the code the output is about, for example the module under
test. Without it the worker only sees a style example and will invent names,
signatures and expected values. Always pass it when the output must be correct
against existing code.
Each call is independent. To build on what was just generated, pass that file
as the --reference for the next call.
Review the output and make surgical edits for the small share that needs frontier-model judgment.
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.