orlando-japan/claude-code-setting

claude-code-setting

2Stars on the repository
56Mods indexed here, across every type
3mo agoLast push, which is what freshness is scored on
MITLicence, which decides whether bodies are shown

logging-strategy

25

orlando-japan/claude-code-setting

Skill Claude CodeCodex

Log what you'd want during an incident, nothing more. Invoke when adding logging to new code or auditing existing logs for noise.

not rated 2 3mo ago A 29 tokens original MIT

metrics-design

26

orlando-japan/claude-code-setting

Skill Claude CodeCodex

Pick metrics that drive alerts and debugging without drowning in dashboards. Invoke when instrumenting a new service or auditing existing metrics.

not rated 2 3mo ago A 27 tokens original MIT

migration-planning

27

orlando-japan/claude-code-setting

Skill Claude CodeCodex

Plan a safe migration (schema, API, framework, infra) that keeps the system live throughout. Invoke before starting any non-trivial change to a running system.

not rated 2 3mo ago A 37 tokens original MIT

orlando-japan/claude-code-setting

Skill Claude CodeCodex

Find real performance problems with measurement, not guesses. Invoke when something is slow, or you're tempted to "optimize" without data.

not rated 2 3mo ago A 32 tokens original MIT

prompt-caching

30

orlando-japan/claude-code-setting

Skill Claude CodeCodex

Maximize cache hit rate on Claude API calls to cut latency and cost. Invoke when building or optimizing a production Claude-powered feature.

not rated 2 3mo ago A 30 tokens original MIT

prompt-engineering

31

orlando-japan/claude-code-setting

Skill Claude CodeCodex

Write prompts that produce reliable LLM output. Invoke when designing or debugging a prompt in an LLM-powered feature.

not rated 2 3mo ago A 27 tokens original MIT

refactor-surgical

32

orlando-japan/claude-code-setting

Skill Claude CodeCodex

Refactor while preserving observable behavior. Invoke when cleaning up code without wanting to change what it does.

not rated 2 3mo ago A 25 tokens original MIT

release-playbook

33

orlando-japan/claude-code-setting

Skill Claude CodeCodex

Ship a release gradually with rollback ready. Invoke when cutting any production release beyond a trivial patch.

not rated 2 3mo ago A 23 tokens original MIT

root-cause-analysis

34

orlando-japan/claude-code-setting

Skill Claude CodeCodex

Find the real cause of a problem, not just the symptom. Invoke when debugging, after an incident, or when "we fixed it but I don't know why.".

not rated 2 3mo ago A 38 tokens original MIT

runbook-authoring

35

orlando-japan/claude-code-setting

Skill Claude CodeCodex

Write runbooks that a sleepy oncall engineer at 3am can actually follow. Invoke when shipping anything pageable, or when a runbook is stale after a postmortem.

not rated 2 3mo ago A 41 tokens original MIT

security-audit

36

orlando-japan/claude-code-setting

Skill Claude CodeCodex

OWASP-style security audit focused on real exploits, not abstract advice. Invoke before shipping anything that handles user input, secrets, or external I/O.

not rated 2 3mo ago A 34 tokens original MIT

simplicity-first

37

orlando-japan/claude-code-setting

Skill Claude CodeCodex

Solve exactly what was asked with the minimum code. Invoke when tempted to add abstractions, helpers, flags, or handling for hypothetical future cases.

not rated 2 3mo ago A 33 tokens original MIT

spec-writing

38

orlando-japan/claude-code-setting

Skill Claude CodeCodex

Write a spec that a different engineer could implement without asking questions. Invoke when starting a new feature, especially one that will be handed off or implemented later.

not rated 2 3mo ago A 34 tokens original MIT

surgical-changes

39

orlando-japan/claude-code-setting

Skill Claude CodeCodex

Edit only the minimum lines needed. Leave unrelated code alone even if you'd write it differently. Invoke for any bug fix or small feature where scope discipline matters.

not rated 2 3mo ago A 36 tokens original MIT

system-design

40

orlando-japan/claude-code-setting

Skill Claude CodeCodex

Structured approach to designing a non-trivial system. Invoke when scoping a new service, feature, or subsystem before implementation.

not rated 2 3mo ago A 28 tokens original MIT

task-execution

41

orlando-japan/claude-code-setting

Skill Claude CodeCodex

Work through an approved task list without drifting off-scope. Invoke during /spec:apply or any structured implementation where tasks are pre-defined.

not rated 2 3mo ago A 32 tokens original MIT

tdd

42

orlando-japan/claude-code-setting

Skill Claude CodeCodex

Red → green → refactor discipline. Invoke when requirements are clear, the interface is small, or when fixing a bug that needs a reproduction.

not rated 2 3mo ago A 32 tokens original MIT

think-before-coding

43

orlando-japan/claude-code-setting

Skill Claude CodeCodex

Before writing code, surface load-bearing assumptions and verify or ask about each one. Invoke when starting any non-trivial task to avoid building on wrong guesses.

not rated 2 3mo ago A 36 tokens original MIT

tracing-setup

44

orlando-japan/claude-code-setting

Skill Claude CodeCodex

Add distributed tracing to a service so you can follow a request across service boundaries. Invoke when debugging cross-service latency or setting up observability from scratch.

not rated 2 3mo ago A 35 tokens original MIT

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: