Get expert-level AI output in 30 seconds. Browse 2,000+ expert-built and security scanned skills -> Browse skills
THE AGENSI STORE
109 skills found
by Timoranjes
Teaches AI coding agents to enforce a strict spec-first workflow: write tests or formal specifications BEFORE implementing any code. Implements a pre-hook that blocks code edits until a test file or s
by Timoranjes
Teaches AI coding agents to proactively manage token budgets across task phases — setting per-task budgets, monitoring consumption in real-time, auto-compressing when approaching limits, and escalatin
The meta-skill for AI agents to self-evolve by logging lessons and updating their own instruction files.
by Timoranjes
Teaches AI coding agents to generate optimized project rule files (.cursorrules, CLAUDE.md, AGENTS.md) that give agents precise context about a project's architecture, conventions, and workflow. Cover
by Timoranjes
Teaches AI coding agents to handle API and tool call failures gracefully using production-grade resilience patterns: exponential backoff with jitter, circuit breakers, timeout management, rate-limit h
by Timoranjes
Teaches AI coding agents to structure and optimize "vibe coding" (AI-assisted iterative development) workflows using a repeatable four-phase framework: Scaffold → Iterate → Validate → Reflect. Covers
A deep reference library of production agent patterns — orchestration, context, tool design, failure and recovery, oversight, and evaluation. Every pattern states when it applies, when it's the wrong answer, what it costs, and the failure it prevents. Seven reference files, not a checklist.
The 60-second audit your AI knowledge system is missing. A structural health auditor for personal knowledge systems that flags maintenance rot and stale documentation.
by Timoranjes
Teaches AI coding agents to perform structured, high-signal code reviews specifically for AI-generated code — catching the failure modes unique to LLM output (confident hallucinations, silent error sw
by Dara Kamyar
Fixes scrambled RTL/LTR rendering when Claude writes Persian text mixed with English words.
Audit LLM spend to find recoverable waste in prompt caching, model routing, and token usage.
by Timoranjes
Teaches AI coding agents to generate a trustworthy onboarding package for an unfamiliar repository: a verified architecture map, dependency and ownership map, risk register, local development checklis
by Shippers
Solo builders trying to run 5-10 Claude Code / Codex agents in parallel keep hitting the same wall: worktrees drift, two