A personal collection of reusable AI agent workflows — a briefing for AI agents that encodes a repeatable task pattern.
This repository also configures its own agents. See what agent-playbooks tells them →
Skill Claude CodeCodex
Skill "ai-guided-learning" from athallarizky/agent-playbooks, covering ai-guided learning, trigger, the workflow, step 1: research the technology and step 2: architecture design.
Skill Claude CodeCodex
Skill "git-workflow" from athallarizky/agent-playbooks, covering git workflow, trigger, rules for ai agents, never auto-commit or auto-push and agent-generated directories.
Skill Claude CodeCodex
Skill "linkedin-writing" from athallarizky/agent-playbooks, covering linkedin writing, trigger, voice & tone, language and personality markers.
Skill Claude CodeCodex
Skill "repo-triage" from athallarizky/agent-playbooks, covering repo triage, trigger, goal, scan order and 1. repo metadata & provenance.
Skill Claude CodeCodex
Skill "security-audit" from athallarizky/agent-playbooks, covering security audit, trigger, what to check, secrets & credentials and personal identifiable information (pii).
Skill Claude CodeCodex
Skill "sprint-driven-development" from athallarizky/agent-playbooks, covering sprint-driven development, trigger, the workflow, phase 0 — discovery & exploration and sprint planning — document structure.
Skill Claude CodeCodex
Turn software engineering concepts into small, practical learning projects. Use when a human wants to understand an architecture, pattern, technology, protocol, trade-off, or engineering concept through a hands-on mini project. The skill guides the learner through concept discovery, project design, implementation…
Skill Claude CodeCodex
Activate this playbook when the user says things like.
Skill Claude CodeCodex
Centralized documentation management workflow for linking, writing, curating, and archiving project documentation and architectural findings into the central engineering-handbook repository without machine-specific hardcoded paths.
Skill Claude CodeCodex
Clean up, prettify, format, and remove noise from content pasted or fetched from web clippers/extensions (e.g., webpage-to-md, Definite, MarkDownload, browser copy-paste) without altering or losing core content.
Skill Claude CodeCodex
Explains new programming language concepts, paradigms, and syntax by building direct 1-to-1 mental models and code analogies from the user's familiar programming language (e.g., React/TS to Go, Python to Rust, Java to Kotlin). Use whenever a developer is transitioning to or learning a new language and needs clear…
Skill Claude CodeCodex
Explains technical and architectural concepts by casting the system into a vivid everyday-world story (people, objects, places) where every component has a strict 1-to-1 structural counterpart. Use when the learner understands the words but not the concept — after code samples or cross-language analogies have failed…
Skill Claude CodeCodex
Skill "gh-incident-response" from athallarizky/agent-playbooks, covering github incident response, trigger, phase 0 — ground rules (read before touching anything), phase 1 — detect & scope (read-only) and ioc reference (known campaign; extend as new ones are seen).
Skill Claude CodeCodex
Skill "repo-hygiene" from athallarizky/agent-playbooks, covering repo hygiene, trigger, core principle, data caveats (learned the hard way) and phase 1 — audit (read-only).
Skill Claude CodeCodex
Skill "guardian-protection" from athallarizky/agent-playbooks, covering guardian protection, trigger, the layers (what protects what), guardian operations and rules for the operator.
Skill Claude CodeCodex
Skill "host-watchdog" from athallarizky/agent-playbooks, covering host watchdog, trigger, architecture, install (per machine) and triage when it fires.
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: