commit
01Skill Claude CodeCodex
Stage and commit changes with conventional commit format. Use when the user says /commit or asks to commit.
not rated 20
+3 today A 23 tokens
original MIT
20Stars on the repository
218Mods indexed here, across every type
todayLast push, which is what freshness is scored on
MITLicence, which decides whether bodies are shown
Skill Claude CodeCodex
Research a topic thoroughly using codebase exploration. Use when the user wants deep investigation of a feature, bug, or pattern.
not rated 20
+3 today A 29 tokens
original MIT
deploy
03Skill Claude CodeCodex
Deploy the project to production. Only user-invocable — never auto-trigger.
not rated 20
+3 today A 18 tokens
original MIT
fix-issue
04Skill Claude CodeCodex
Fix a GitHub issue by number. Read the issue, implement the fix, write tests, commit.
not rated 20
+3 today A 25 tokens
original MIT
Skill Claude CodeCodex
Focus: Designing autonomous AI agents capable of reasoning, planning, executing tools, and correcting their own mistakes over long-running tasks. Triggers: ai-agents, agentic-workflows, react, langgraph, autogen, multi-agent, planning.
not rated 20
+3
changed today A 0 tokens
original MIT
ai-agents
06Skill Claude CodeCodex
Focus: Designing, evaluating, and implementing Autonomous AI Agents, ReAct loops, planning, and tool use. Triggers: agent architecture, multi-agent systems, react loop, tool calling, autonomous agent.
not rated 20
+3 today A 0 tokens
original MIT
Skill Claude CodeCodex
Fundamental principles of AI Agent cognitive loops, contrasting ReAct and Plan-and-Solve paradigms.
not rated 20
+3 today A 26 tokens
original MIT
Skill Claude CodeCodex
Theoretical foundations of Working, Semantic, and Episodic memory systems for autonomous agents.
not rated 20
+3 today A 25 tokens
original MIT
Skill Claude CodeCodex
First principles of AI societal structures and multi-agent interaction paradigms.
not rated 20
+3 today A 18 tokens
original MIT
Skill Claude CodeCodex
First principles of tool/environment grounding, structured outputs, and error recovery for AI agents.
not rated 20
+3 today A 24 tokens
original MIT
genai-vision
11Skill Claude CodeCodex
Integrating Stable Diffusion for vision generation and Whisper for audio/multimodal tasks.
not rated 20
+3 today A 23 tokens
original MIT
kv-cache
12Skill Claude CodeCodex
During autoregressive generation, Transformers exhibit quadratic time and linear space complexity with respect to sequence length. To prevent recomputing the Key ($K$) and Value ($V$) tensors for preceding tokens at each generation step, the KV cache is utilized.
not rated 20
+3 today A 0 tokens
original MIT
Skill Claude CodeCodex
Quantization reduces the precision of model weights (and sometimes activations) from 16-bit floating-point (FP16/BF16) to lower bit-widths (e.g., INT4, INT8).
not rated 20
+3 today A 0 tokens
original MIT
Skill Claude CodeCodex
HNSW operates as a multi-layered proximity graph where each layer constitutes a skip-list-esque representation of the vector space. The construction involves stochastic insertion with an exponentially decaying probability of promotion to higher layers.
not rated 20
+3 today A 0 tokens
original MIT
Skill Claude CodeCodex
Best practices for dataset preparation and PEFT/LoRA fine-tuning.
not rated 20
+3 today A 21 tokens
original MIT
Skill Claude CodeCodex
PostgreSQL is an advanced, enterprise-class open-source relational database. Understanding its internals is crucial for high-performance tuning.
not rated 20
+3 today A 0 tokens
original MIT
Skill Claude CodeCodex
As data grows beyond the capacity of a single machine, databases must scale.
not rated 20
+3 today A 0 tokens
original MIT
Skill Claude CodeCodex
DDD is a software engineering approach that centers the design around the business domain, bridging the gap between technical and business teams.
not rated 20
+3 today A 0 tokens
original MIT
Skill Claude CodeCodex
Designing resilient microservices requires managing distributed state, failures, and complex communication networks.
not rated 20
+3 today A 0 tokens
original MIT
Skill Claude CodeCodex
Use when the user asks about strategic roadmapping, technology roadmapping, product roadmap creation, prioritization frameworks (RICE, WSJF, MoSCoW), OKR alignment, stakeholder alignment, timeline planning, or roadmap communication. Do NOT use for: project management task tracking, sprint planning, or technical…
not rated 20
+3 today A 71 tokens
original MIT
Skill Claude CodeCodex
Enforce bulk data import patterns including CSV/Excel parsing, file upload handling, validation pipeline, progress tracking, batch processing, error reporting, rollback on failure, deduplication, and background processing. NOT for real-time data ingestion or streaming pipelines.
not rated 20
+3 today A 55 tokens
original MIT
bun
22Skill Claude CodeCodex
Use this skill when building with Bun runtime — Bun APIs, testing, package management, shell scripting, hot reload, SQLite, file I/O. This skill enforces: built-in APIs over npm equivalents, Bun test runner, bun install speed optimization, Bun.shell for scripts. Do NOT use for: Node.js-specific APIs…
not rated 20
+3 today A 80 tokens
original MIT
Skill Claude CodeCodex
Redis caching patterns including Cache-Aside, Write-Through, and invalidation.
not rated 20
+3 today A 19 tokens
original MIT
deno
24Skill Claude CodeCodex
Use this skill when building with Deno — TypeScript runtime, Deno Deploy, Fresh framework, Deno std library. This skill enforces: permission-based security, URL import system, std lib usage over npm, Fresh island architecture. Do NOT use for: Node.js projects, Bun projects, browser-only TypeScript.
not rated 20
+3 today A 68 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: