Productivity & Workflow Agent Skills for Codex CLI

Governs the complete lifecycle of AI agent instruction assets, prompt templates, and skill registries from creation to retirement.

Create, fix, and validate skills for AI agents.

Creates Claude skills and plugins. Covers greenfield authoring through Socratic discovery, distilling reference material (docs, a tool, an…

Interactive guide for creating new Skills 2.0-compliant skills.

Guides the design, authoring, and debugging of predictable Claude Code skills using proven architectural principles.

Use priority levels when capturing tangents:

Creates, updates, and fixes Agent Skills end-to-end: drafts new skills from a short interview, improves existing ones against Anthropic…

Use when: (1) Your skill repository has grown to 30+ skills and quality is inconsistent, (2) You need to audit skills for stale…

Governs and automates the Claude Code skill lifecycle through standardized generation, multi-tier validation, and library auditing.

Meta-skill for extracting and creating reusable Claude Code skills from past work sessions.

Retrofit the OIAE self-improvement loop to existing skills and analyze feedback to propose evidence-based amendments.

Manages, synchronizes, and bulk-installs Agent Skills across AI coding environments with automated dependency resolution and fallback…

Core operating rules for how Claude should behave when working with this user on code, documentation, and projects across Claude / Claude…

Use as step 3 of AIS FLOWS Skill Library Cleaner to find exact duplicates, near-duplicates, old variants, runtime copies, and overlapping…

Use when a skill is brittle, drifting, repeatedly failing, or needs a Reliable Skill Contract.

Mine selected past agent sessions for repeated corrections, preferences, and workflows, then draft reusable skills.

Watch a video (URL or local path). Downloads with yt-dlp, extracts auto-scaled frames with ffmpeg, pulls the transcript from captions (or…

Reviews, diagnoses, and refactors Claude Code skills with structured workflows, security checks, and confirmation gates.

Convert a personal agent skill into a distributable, open-source-ready skill.

Defines the quantitative skill-optimization model: its run directory and state schema, four evaluation laws, verification-signal policy…

Improves an existing skill by running it as a training loop: evaluates it on real tasks against a mechanical verification signal, proposes…