Skill Claude Code
Write, compose, integrate, and improve programs that call Jev, TypeSafe's System One judgment model.
not rated 442
+1
changed today A 27 tokens
original MIT
442Stars on the repository
127Mods indexed here, across every type
todayLast push, which is what freshness is scored on
MITLicence, which decides whether bodies are shown
toolkit
50Skill Claude Code
Toolkit management: create and evaluate skills and agents, manage routing tables, generate Claude.md.
not rated 442
+1
changed 20d ago A 21 tokens
original MIT
debugging
51Skill Claude Code
Debugging: guided diagnosis of application bugs, and post-mortem of failed agent sessions.
not rated 442
+1
changed 25d ago A 22 tokens
original MIT
process
52Skill Claude Code
Process: retrospectives, session handoff, pair programming, subagent-driven development, condition-based waiting.
not rated 442
+1
changed yesterday A 23 tokens
original MIT
testing
53Skill Claude Code
Testing: TDD, E2E, preferred patterns, test-value audits, verification, agent testing.
not rated 442
+1
changed yesterday A 23 tokens
original MIT
programming
54Skill Claude Code
Language-specific patterns and tooling: Go, Kotlin, PHP, Swift, TypeScript.
not rated 442
+1
changed 25d ago A 20 tokens
original MIT
research
55Skill Claude Code
Research: structured investigation, fact-checking, explanation traces.
not rated 442
+1
changed yesterday A 14 tokens
original MIT
review
56Skill Claude Code needs its repo
Code review: systematic single-file, parallel multi-reviewer, full-repo audit, PR diff review.
not rated 442
+1
changed yesterday A 23 tokens
original MIT
security
57Skill Claude Code needs its repo
Security: review git changes for vulnerabilities, threat-model a system's attack surface, audit supply-chain risks.
not rated 442
+1
changed 22d ago A 23 tokens
original MIT
jev-design
58Skill Claude Code
Design React interfaces with the full shadcn/ui catalog. The agent writes a brief, Jev picks components and a style recipe from bounded catalogs, then the agent implements, renders, and reviews against concrete checks.
not rated 442
+1
changed today A 46 tokens
original MIT
grill-jev
59Skill Claude Code needs its repo
Broad Jev interrogation: generate up to 50 context-specific questions about a plan, spec, design, code artifact, or any topic — using all primitive shapes and structured forms to surface hidden problems before they ship.
not rated 442
+1
changed today A 48 tokens
original MIT
accounts
60Skill Claude Code needs its repo
Manage multiple Claude Code accounts: add, list, check, launch, and install shell aliases for 10+ isolated CLAUDECONFIGDIR profiles.
not rated 442
+1
changed today B 32 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: