All authors
Claude Skills by savinofiore
github.com/savinofiore16 skills0 installs14 views
- Code ReviewHybrid Jev + Claude code review. review.py has TypeSafe's Jev judge the diff on closed questions (generic risk and code quality, plus the project's own conventions from .lexi/review.json) and computes the verdict in code (BLOCK, SECURITY REVIEW, CONVENTIONS, QUALITY, NITS, MERGE); Claude takes the handoff, locates fired rules, verifies uncertain checks, delegates triggers and, after a fix, reruns Jev to measure the deltas. lexi's bug and feature flows call it after the last GREEN. Use for "/j...Votes: 0GitHub stars: 4
- Jev Code ReviewHybrid Jev + Pi code review. review.py has TypeSafe's Jev judge the diff on closed questions (generic risk and code quality, plus the project's own conventions from .lexi/review.json) and computes the verdict in code (BLOCK, SECURITY REVIEW, CONVENTIONS, QUALITY, NITS, MERGE); you take the handoff, locate fired rules, verify uncertain checks, delegate triggers and, after a fix, rerun Jev to measure the deltas. lexi's bug and feature flows call it after the last GREEN. Use for "/skill:jev-code...Votes: 0GitHub stars: 4
- Lexi BugFix a bug by rewriting existing tests to RED (prove the bug exists), then fix production code to GREEN. Unit tests only. Use when a bug report names the broken behavior and existing tests need to be rewritten to confirm it.Votes: 0GitHub stars: 4
- Lexi FeatureAnalyze a feature, propose multiple unit tests, confirm them with the user, then execute RED→GREEN cycle. Unit tests only, no widget tests. Use for features with clear scope where you want explicit test proposals before implementation.Votes: 0GitHub stars: 4
- Lexi GrillInterrogate an open scope in rounds until nothing is silently assumed. Each round asks every question whose prerequisites are already settled, with a recommended answer for each. Use before writing tests or code when a task has several defensible designs, unstated intent, or constraints that would only surface after implementation.Votes: 0GitHub stars: 4
- Lexi InitSet up lexi in a project — detect the stack, find the real gate command, choose the testable whitelist, and write .lexi.json plus .lexi/. Run once per project after installing the plugin, and again after updating lexi — on an existing .lexi.json it only asks what the new version added. Use when the user says "lexi init", "set up lexi", or the guard reports it is dormant.Votes: 0GitHub stars: 4
- Lexi LexiTest-first flow for a task, bug or feature, with no spec document. Routes to lexi-feature for clear scope or lexi-grill for open scope, then confirms seams and drives vertical slices red to green. Use whenever a code change is requested in a project with a .lexi.json, or when the lexi guard blocks a write.Votes: 0GitHub stars: 4
- Lexi TddWhat makes a test worth keeping — seams, assertions, mocking, and the anti-patterns that produce tests which pass forever and catch nothing. A reference consulted before and while writing a test, not a procedure. Use when writing or reviewing tests, choosing where to test, or judging whether a test earns its maintenance.Votes: 0GitHub stars: 4
- BugFix a bug by rewriting existing tests to RED (prove the bug exists), then fix production code to GREEN. Unit tests only. Use when a bug report names the broken behavior and existing tests need to be rewritten to confirm it.Votes: 0GitHub stars: 4
- FeatureAnalyze a feature, propose multiple unit tests, confirm them with the user, then execute RED→GREEN cycle. Unit tests only, no widget tests. Use for features with clear scope where you want explicit test proposals before implementation.Votes: 0GitHub stars: 4
- GrillInterrogate an open scope in rounds until nothing is silently assumed. Each round asks every question whose prerequisites are already settled, with a recommended answer for each. Use before writing tests or code when a task has several defensible designs, unstated intent, or constraints that would only surface after implementation.Votes: 0GitHub stars: 4
- InitSet up lexi in a project — detect the stack, find the real gate command, choose the testable whitelist, and write .lexi.json plus .lexi/. Run once per project after installing the plugin, and again after updating lexi — on an existing .lexi.json it only asks what the new version added. Use when the user says "lexi init", "set up lexi", or the guard reports it is dormant.Votes: 0GitHub stars: 4
- LexiTest-first flow for a task, bug or feature, with no spec document. Routes to lexi:feature for clear scope or lexi:grill for open scope, then confirms seams and drives vertical slices red to green. Use whenever a code change is requested in a project with a .lexi.json.Votes: 0GitHub stars: 4
- TddWhat makes a test worth keeping — seams, assertions, mocking, and the anti-patterns that produce tests which pass forever and catch nothing. A reference consulted before and while writing a test, not a procedure. Use when writing or reviewing tests, choosing where to test, or judging whether a test earns its maintenance.Votes: 0GitHub stars: 4
- Code ReviewCode review in this project goes through Jev (jev plugin), replacing Claude Code's built-in review. Use for "/code-review", "review the diff", "can I merge?", "is this code ok?", a PR number, a git ref or a .diff/.patch file.Votes: 0GitHub stars: 4
- ReviewCode review in this project goes through Jev (jev plugin), replacing Claude Code's built-in review. Use for "/review", "review the diff", "can I merge?", "is this code ok?", a PR number, a git ref or a .diff/.patch file.Votes: 0GitHub stars: 4