Jewgah/claude-code-skills

Battle-tested Claude Code skills: deep multi-agent code review (/review-deep), adversarial plan review (/review-plan), automation scout-and-builder (/loopable), agent-team scaffolder (/init-agents)

2Stars on the repository
26Mods indexed here, across every type
10d agoLast push, which is what freshness is scored on
MITLicence, which decides whether bodies are shown

explain-dev

01

Jewgah/claude-code-skills

Command Claude Code

Write a WhatsApp-ready, non-technical message explaining a development to the client.

not rated 2 10d ago A 16 tokens original MIT

review-plan

02

Jewgah/claude-code-skills

Command Claude Code

Critically review the current plan/approach before implementing — assumptions, gaps, blast radius, deploy safety.

not rated 2 changed 18d ago A 21 tokens original MIT

skill-stats

03

Jewgah/claude-code-skills

Command Claude Code

Leaderboard of your most-used skills from the durable usage log (survives transcript cleanup).

not rated 2 10d ago A 18 tokens original MIT

feature

04

Jewgah/claude-code-skills

Command Claude Code

Run the full feature pipeline — explore → plan → implement → review → test — for the change described in the argument.

not rated 2 10d ago A 24 tokens original MIT

fix

05

Jewgah/claude-code-skills

Command Claude Code

Diagnose and fix a bug — reproduce → locate → root-cause → fix → test.

not rated 2 10d ago A 19 tokens original MIT

review

06

Jewgah/claude-code-skills

Command Claude Code

Review the current diff for bugs, security issues, and regressions.

not rated 2 10d ago A 14 tokens original MIT

triage

07

Jewgah/claude-code-skills

Command Claude Code

Triage a bug report (PDF / markdown / text) — extract the issues, prioritize, then run the fix pipeline per issue.

not rated 2 10d ago A 27 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: