genai-io

8 mods across 1 repository, 79 stars between them.

code-review

01

genai-io/san

Skill Claude Code

Review changed code for correctness bugs — logic errors, nil/error handling, concurrency, resource leaks, edge cases, broken invariants. Reports findings first, ordered by severity, then fixes on request. Scoped to correctness, not quality or style cleanups. Use when the user says "code review", "review my changes"…

not rated 79 +20 yesterday A SkillSpector: pass 83 tokens original Apache-2.0

debug

02

genai-io/san

Skill Claude Code

Systematic debugging that finds the root cause before changing any code — collect symptoms, trace the code path, check what changed, reproduce deterministically, form a testable hypothesis, then fix the cause (not the symptom) and prove it with a regression test. Use when the user reports a bug, a crash, a failing…

not rated 79 +20 yesterday A SkillSpector: pass 84 tokens original Apache-2.0

refactor

03

genai-io/san

Skill Claude Code

Restructure existing code without changing its behavior — extract, rename, inline, split, deduplicate, reshape — with tests holding behavior fixed before and after. Scoped to structure only: no new features, no bug fixes, no behavior changes. Use when the user says "refactor", "clean up the structure", "extract this"…

not rated 79 +20 yesterday A SkillSpector: pass 84 tokens original Apache-2.0

simplify

04

genai-io/san

Skill Claude Code

Review changed code for reuse, quality, and efficiency, then clean up what you find — duplicated logic that could reuse an existing helper, hacky or redundant patterns, needless work on hot paths. Quality cleanup only: not bugs (that's code-review) and not behavior-preserving restructuring on request (that's…

not rated 79 +20 yesterday A SkillSpector: pass 94 tokens original Apache-2.0

tdd

05

genai-io/san

Skill Claude Code

Test-driven development — write a failing test that names the behavior, watch it fail, implement the minimum to make it pass, then refactor with tests green. Works for new features, bug fixes, and behavior changes. Use when the user says "tdd", "test-first", "write tests first", or wants a change built test-first.

not rated 79 +20 yesterday A SkillSpector: pass 73 tokens original Apache-2.0

qa

06

genai-io/san

Skill Claude Code needs its repo

Regression test a San feature by name. Looks for a feature doc in docs/reference/ or docs/packages/2-feature/, runs automated Go tests and interactive tmux tests, then produces a pass/fail report. Use this skill when the user says "qa", "regression test", "test feature X", "verify feature", or references a feature…

not rated 79 +20 yesterday A SkillSpector: pass 85 tokens original Apache-2.0

release

07

genai-io/san

Skill Claude Code

Create a new versioned release with changelog. Bumps version in code, updates CHANGELOG.md, commits, tags, and pushes using the repository release flow. GitHub Actions creates the release and uses only the current changelog section as release notes. Use when the user says "release", "cut a release", "bump version"…

not rated 79 +20 yesterday A SkillSpector: warn 75 tokens original Apache-2.0

At most 3 mods per repository are shown here, and a mod shipped inside a plugin is left to that plugin's page — the rest are on their repository pages: