Skill Claude Code
Improve prompts using best practices for clarity, specificity, and structure. Use for optimizing AI agent and bot instructions.
not rated 10 8d ago A SkillSpector: pass 27 tokens
original MIT
10Stars on the repository
97Mods indexed here, across every type
8d agoLast push, which is what freshness is scored on
MITLicence, which decides whether bodies are shown
quality-gate
26Skill Claude CodeCodex
Quality gate enforcement — TDD, lint, type-check, test, build checks before any commit or PR.
not rated 10 8d ago A 25 tokens
original MIT
Skill Claude Code
RAG pipeline design — chunking, embeddings, retrieval strategies, evaluation, and demo patterns.
not rated 10 8d ago A SkillSpector: pass 23 tokens
original MIT
Skill Claude Code
Remote sensing pipeline with optical/SAR processing and ML classification. Use for satellite imagery analysis.
not rated 10 8d ago A SkillSpector: warn 23 tokens
original MIT
Skill Claude Code
Security audit with SAST, SCA, containers, SBOM, PII detection. Use for comprehensive security reviews.
not rated 10 8d ago A SkillSpector: warn 29 tokens
original MIT
session-goal
30Skill Claude Code
Pin session objectives to prevent scope creep. Use for alignment across long multi-agent sessions.
not rated 10 8d ago A SkillSpector: pass 21 tokens
original MIT
simplify
31Skill Claude Code
Behavior-preserving code simplification to reduce complexity while keeping outputs, side effects, and APIs unchanged.
not rated 10 8d ago A SkillSpector: pass 23 tokens
original MIT
task-system
32Skill Claude Code
File-backed task management with dependencies and parallel execution. Use for complex work with 3+ interdependent tasks.
not rated 10 8d ago C 25 tokens
original MIT
Skill Claude Code
TDD enforcement with RED→GREEN→REFACTOR cycle and advanced testing patterns. Use for test-driven development across all layers.
not rated 10 8d ago A SkillSpector: pass 32 tokens
original MIT
Skill Claude Code
Advanced testing with E2E, load, mutation, and contract tests. Use for production-ready test coverage beyond unit tests.
not rated 10 8d ago A SkillSpector: warn 29 tokens
original MIT
file-prompts
35Skill Claude Code
Load prompts from external files with path expansion. Use for version-controlled prompts outside config.
not rated 10 8d ago A SkillSpector: pass 21 tokens
original MIT
memory-bank
36Skill Claude Code
Memory bank rules, structure, and optimization — complete guide to Pantheon memory management.
not rated 10 8d ago A SkillSpector: pass 20 tokens
original MIT
Skill Claude Code
Plan feature architecture with component breakdown, data flow, and dependency mapping. Use before implementation to define contracts between layers.
not rated 10 8d ago A SkillSpector: pass 27 tokens
original MIT
Skill Claude Code
Implement SSE, WebSockets, LLM token streaming, and real-time broadcasting in FastAPI.
not rated 10 8d ago A SkillSpector: pass 24 tokens
original MIT
token-audit
39Skill Claude CodeCodex
Audit a repository for token waste — find redundant context files, measure baseline, recommend optimizations.
not rated 10 8d ago A SkillSpector: warn 22 tokens
original MIT
Skill Claude CodeCodex
Automated visual review pipeline — Playwright screenshots, self-analysis, fix loop, escalation. Used by Aphrodite for UI verification.
not rated 10 8d ago A SkillSpector: pass 32 tokens
original MIT
Skill Claude Code
Extract learnings between implementation waves. Use to share conventions and gotchas across phases.
not rated 10 8d ago A SkillSpector: pass 24 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: