agentic-engineeringclaude-code · codex · cursor
Context engineering: set up agent context for quality output
Optimizes agent context setup.
@addyosmani · MIT · Verified Oct 17, 2026
Evidence not reviewed
Skills
Instruction files agents can follow.
Each skill is a public SKILL.md, copied with its author, source, and license. A workflow can name the skills it uses, and a stack is one workflow plus those skills.
- skills
- 84
- skills
- research-backed
- 1
- research-backed
- categories
- 19
- categories
10 skills
- agentic-engineeringclaude-code · codex · cursor
Incremental implementation: thin, verifiable slices
Delivers changes incrementally in thin, verifiable slices.
@addyosmani · MIT · Verified Oct 17, 2026
Evidence not reviewed - agentic-engineeringclaude-code · codex · cursor
Source-driven development: ground decisions in official docs
Grounds every implementation decision in official documentation.
@addyosmani · MIT · Verified Oct 17, 2026
Evidence not reviewed - agentic-engineeringclaude-code · codex · cursor
Agent harness construction: action spaces, tools, observations
Design and optimize AI agent action spaces, tool definitions, and observation formatting for higher completion rates.
@affaan-m · MIT · Verified Oct 17, 2026
Evidence not reviewed - agentic-engineeringclaude-code · codex · cursor
Agentic engineering: eval-first, decomposed, cost-aware execution
Operate as an agentic engineer using eval-first execution, decomposition, and cost-aware model routing.
@affaan-m · MIT · Verified Oct 17, 2026
Evidence not reviewed - agentic-engineeringclaude-code
Autonomous loops: patterns for unattended Claude Code pipelines
Patterns and architectures for autonomous Claude Code loops — from simple sequential pipelines to RFC-driven multi-agent DAG systems.
@affaan-m · MIT · Verified Oct 17, 2026
Evidence not reviewed - agentic-engineeringclaude-code · codex
Context budget: check live context use in Codex or Claude Code
Routes live context checks to the native Codex or Claude Code meter without scanning files, and performs a bounded static component audit only when explicitl…
@affaan-m · MIT · Verified Oct 17, 2026
Evidence not reviewed - agentic-engineeringclaude-code · codex · cursor
Caveman: short-output skill that cuts agent tokens
>
@TheHappyGe · Apache-2.0 · Verified Oct 16, 2026
Evidence not reviewed - agentic-engineeringclaude-code
gstack: Garry Tan's Claude Code skill set
Router for the gstack skill suite.
@oliviscusAI · Verified Oct 16, 2026
Evidence not reviewed - agentic-engineeringclaude-code · codex · cursor
Superpowers: plan, test, and review skills framework
You MUST use this before any creative work - creating features, building components, adding functionality, modifying behavior, or planning anything new, in s…
@xppt8a · Verified Oct 16, 2026
Evidence not reviewed