stefan-jansen

Skill Claude CodeCodex

Docker image optimization patterns including multi-stage builds, layer caching, security hardening, and size reduction techniques. Use when building Docker images, optimizing container size, improving build performance, or implementing Docker security best practices. Reduces image sizes by 70-90% and build times by…

85 1mo ago B 65 tokens original MIT

sql-optimization

Skill Claude CodeCodex

SQL query optimization patterns including EXPLAIN plan analysis, index strategies, query rewriting, and N+1 query prevention. Use when optimizing slow database queries, analyzing query performance, designing indexes, or debugging database bottlenecks. Works with PostgreSQL, MySQL, SQLite, and other SQL databases.…

85 1mo ago A 78 tokens original MIT

huggingface-transformers

Skill Claude CodeCodex

Hugging Face Transformers best practices including model loading, tokenization, fine-tuning workflows, and inference optimization. Use when working with transformer models, fine-tuning LLMs, implementing NLP tasks, or optimizing transformer inference.

85 1mo ago A 52 tokens original MIT

llm-evaluation

Skill Claude CodeCodex

LLM evaluation and testing patterns including prompt testing, hallucination detection, benchmark creation, and quality metrics. Use when testing LLM applications, validating prompt quality, implementing systematic evaluation, or measuring LLM performance.

85 1mo ago A 47 tokens original MIT

rag-implementation

Skill Claude CodeCodex

Comprehensive guide to implementing RAG systems including vector database selection, chunking strategies, embedding models, and retrieval optimization. Use when building RAG systems, implementing semantic search, optimizing retrieval quality, or debugging RAG performance issues.

85 1mo ago A 50 tokens original MIT

coding-agent-toolkit

Settings file Claude Code

Agent settings configuring $comment, enabledPlugins, autoMemoryDirectory.

22 17d ago B tokens not measured original MIT

coding-agent-toolkit AGENTS.md

Instructions file CodexOpenCode

Instructions for stefan-jansen/coding-agent-toolkit, covering coding-agent-toolkit, purpose, cross-host primitive, step chain and three surfaces, one source.

22 17d ago A 1,341 tokens original MIT

coding-agent-toolkit CLAUDE.md

Instructions file

Instructions for stefan-jansen/coding-agent-toolkit, a project described as: Cross-agent workflow toolkit (Claude Code + Codex) — align/plan/ship/handoff verbs with shared .workspace/ as the host-swap primitive.

22 17d ago A 5 tokens copy · 100% MIT

align

Skill Claude CodeCodex

This skill should be used at the START of any non-trivial work unit, when the user asks to "align", "spec this out", "define the work", or before planning/implementing. Forcefully interrogates the user (or seeds the spec from a brief/RFC if invoked as /align @brief.md) to produce a complete spec.md (WHAT/WHY…

22 17d ago A 95 tokens original MIT

continue

Skill Claude CodeCodex

This skill should be used when the user says "continue from ", asks to "resume from the last handoff", "pick up where we left off", or runs /continue. Reads a transition file written by /handoff, runs its verification snapshot, reports drift, and surfaces the suggested next steps WITHOUT auto-executing. Host-neutral.

22 17d ago B 74 tokens original MIT

delegate

Skill Claude CodeCodex

This skill should be used when the user asks to "message another session", "ask the other agent", "delegate to a peer session", "coordinate with the session in my other pane/worktree", "tell the session ...", "check on the migration/test run in the other terminal", "see what the session is doing", "inspect/peek at…

22 17d ago A 150 tokens original MIT

handoff

Skill Claude CodeCodex

This skill should be used when the user asks to "write a handoff", "produce a transition", "record where we are for the next session", "write a digest before /clear", or runs /handoff. Writes a durable transition file at .workspace/transitions/YYYY-MM-DD/HHMMSS.md that any future session on either host (Claude or…

22 17d ago A 91 tokens original MIT

next-issue

Skill Claude CodeCodex

This skill should be used after /plan-issues has materialized issues on GitHub and the user asks to "implement the next issue", "pick up the next ticket", "do the next one", or runs /next-issue. Picks the lowest-numbered open issue in the active milestone, branches if needed, implements per the issue body, runs tests…

22 17d ago A 83 tokens original MIT

plan-issues

Skill Claude CodeCodex

This skill should be used after a plan.md exists in an active work unit, when the user asks to "create the issues", "open the GitHub issues from the plan", "materialize issues", or runs /plan-issues. Parses plan.md, creates the milestone, and opens one GitHub issue per Issue N — heading. Default is dry-run; pass…

22 17d ago A 96 tokens original MIT

ship

Skill Claude CodeCodex

This skill should be used after all issues in a milestone have commits on the milestone's PR branch and the user asks to "ship the milestone", "merge the PR", "close out the milestone", or runs /ship. Verifies every milestone issue has a closing-footer commit on the PR branch, marks the PR ready if draft…

22 17d ago A 105 tokens original MIT

local marketplace

Plugin Claude Code

Plugin marketplace for coding-agent-toolkit - modular development, workflow, memory, and code-quality plugins for Claude Code.

5 +1 3d ago A tokens not measured

codex

Plugin Claude Code

Use Codex from Claude Code to review code or delegate tasks.

5 +1 3d ago A tokens not measured

codex-rescue

Agent

Proactively use when Claude Code is stuck, wants a second implementation or diagnosis pass, needs a deeper root-cause investigation, or should hand a substantial coding task to Codex through the shared runtime.

5 +1 3d ago A 44 tokens

adversarial-review

Command

Run a Codex review that challenges the implementation approach and design choices.

5 +1 3d ago A 13 tokens

cancel