Agent skills for Codex CLI

Captures learnings, errors, and corrections to enable continuous improvement.

CI-only self-improvement workflow using gh-aw (GitHub Agentic Workflows).

This skill should be used when the harness, scaffold, workflow, or optimizer itself is the optimization target: recursive self-improvement…

Autonomous evolutionary code improvement engine with tournament selection

Streamlines the archiving, versioning, and verification of multi-platform content assets for self-media creators.

Tiers, checkpoints, and off-limits paths for an agent editing the app's own source.

SONA self-optimizing neural architecture with ReasoningBank trajectory learning, EWC++ anti-forgetting, and reinforcement learning…

Identity expression and self-construction.

Use before opening a PR, or whenever asked to self-review a diffusers contribution.

Generate or revise Chinese software self-test reports in genuine DOCX format from Git commits, code diffs, requirements, or described…

Build the thing from scratch — implement the core functionality yourself instead of wrapping an existing library, framework, or service…

Analyzes Amazon product listing date trends and product lifecycle distributions across marketplace categories via SellerSprite API.

Analyzes Amazon ASIN keyword traffic structures, summarizing organic, advertising, and conversion keyword metrics via SellerSprite API.

Compile natural language, a loose composition or pipeline sketch, or an existing program.md into a readable Haskell-esque Sem program that…

Compile and execute natural-language requests, loose semantic pipelines, or existing program.md files as squishy Sem programs.

Checks document semantic content against SCOPE and project goals, coverage gaps, off-topic content, SSOT.

Generates structured English vocabulary tables with IPA phonetics and emojis categorized automatically from Chinese inputs.

Search published venue papers (IEEE, ACM, Springer, etc.) via Semantic Scholar API.

Semantic similarity computation for content relationships and intelligent discovery

Semantic Similarity Index for disease research literature using PubMedBERT embeddings

Generate, inspect, and use node/text embeddings in Semantica — compute Node2Vec embeddings, find similar nodes, score link predictions…