Skill Composition, a lesson in the Production Agent Skills Engineering course, teaches that higher-order agent capabilities should be built by composing several narrow, well-scoped skills rather than …
Agentic AI's course on production agent skills engineering warns that skills run with real access to tools that can send emails, modify databases, or deploy code, making security critical. It identifi…
AWS Skill Pack, a course on production agent skills engineering, introduces two new skills: aws-cost-review, which flags likely-wasteful AWS resources such as unattached EBS volumes, idle EC2 instance…
A new LangGraph course lesson, "Banking Skill Pack," teaches how to build two Validator skills for banking compliance — banking-transaction-flag-review and banking-kyc-document-check — that flag trans…
Smart SDLC, an open-source, MIT-licensed framework from superMLdev, ships 30+ skills organized under six AI personas for GitHub Copilot, Claude, Cursor, and other file-reading assistants, with zero ex…
GitHub's official command-line tool, the gh CLI, is the foundation of two new skills in a GitHub Skill Pack: github-pr-description, which generates a structured pull request description from a diff an…
A new Kubernetes Skill Pack from an unnamed author teaches agents to build two read-only skills: k8s-pod-diagnose, which diagnoses pod failures by branching on CrashLoopBackOff, ImagePullBackOff, Pend…
LangGraph Skill Pack introduces two skills for developers building agents with LangGraph: langgraph-scaffold, which generates a StateGraph from a plain-language description, and langgraph-graph-review…
Anthropic's new course, 'From Prototype to Production,' teaches that moving agentic AI skills from personal to production use changes authorship, failure handling, quality measurement, trust, and chan…
A new Python Skill Pack for agentic AI introduces two skills: python-convention-check, a Validator that reviews Python code against project conventions including type hints, docstrings, import orderin…
A new lesson from the Agent Skills Mastery course outlines an eight-stage CI/CD pipeline for agent skills, implemented as GitHub Actions jobs, covering lint, validate, test, evaluate, security scan, p…
Agentic AI's lesson on skill design patterns identifies six recurring shapes—workflow, decision, validator, transformation, lookup, and feedback—that every skill falls into, and teaches engineers to m…
Skill engineering is the discipline of explicitly defining a skill's contract—inputs, outputs, and constraints—and deliberately engineering retry, fallback, and recovery behaviors for failure cases, a…
Capstone: Compose Your Skill Library, a course module from Agentic AI, instructs learners to combine three of eight previously built skill packs into a single higher-order agent, such as an infrastruc…
A new course lesson on skill lifecycle and versioning for agentic AI introduces eight defined stages—draft, test, review, approve, publish, version, deprecate, and archive—and applies semantic version…
A study of public SKILL.md files found that over 99% contain at least one quality issue, or 'skill smell,' according to a lesson in the Agent Skills Mastery course. The lesson identifies ten named ski…
Skill registries extend beyond filesystem-based discovery to support publish, install, search, semantic search, dependency resolution, and trust signals, according to a lesson in the Agent Skills Mast…
A new SQL Skill Pack from an unnamed course teaches building two validator skills: sql-migration-safety-check, which flags destructive migration patterns like dropped columns and unindexed foreign key…
Sysdig's Terraform Skill Pack introduces two skills for agentic AI: terraform-plan-review flags destructive resource replacements in Terraform plans, and terraform-drift-detect surfaces infrastructure…
The page for 'Multi-Agent Skill Systems' was not found, redirecting users to tutorials or the homepage. The site offers skill packs for cost review, IAM least-privilege checks, safe resource changes v…