codex grade coding
by Roy Yuen
Turn your AI agent into a senior engineer with strict task classification and verification-driven coding protocols.
New: UPI payments are live. Buyers in India can now pay for skills with UPI in INR -> Browse skills
THE AGENSI STORE
39 skills found
by Roy Yuen
Turn your AI agent into a senior engineer with strict task classification and verification-driven coding protocols.
by Kevin Cline
Transform your agent into a Senior Engineer that analyzes architecture and reuses code before writing a single line.
by LocoLoboZ
Expert technical configuration and data mapping for Make.com modules, IML expressions, and automation logic.
Lint an OpenAPI spec and diff two versions to catch breaking API changes before they reach consumers. Within a spec it flags missing operationId, success responses with no schema, untyped parameters, operations with no security requirement, and unbounded arrays/strings. Across two versions it flags removed paths and operations, removed response codes, a parameter becoming required, narrowed parameter types, removed enum values, and removed response fields. Analyzes JSON specs (convert YAML to JSON first).
Produces a Socratic code review — the questions a senior reviewer would ask — covering correctness, edge cases, concurrency, API design, and test adequacy. Use when the user says "review my code", "review this PR", "review this diff", "critique my implementation", or "find problems in my code". Do not use for planning an implementation before writing code.
Audits the gap between a documented design system and the shipped product — variant inventory, token coverage, hardcoded-value mapping, Figma-to-code parity — from shared components or screenshots. Use when the user says audit our design system, find component drift, why do we have twelve button variants, or clean up the component library. Do not use when the user wants to design a new component from scratch.
Produces a codebase architecture assessment — dependency map, module boundary analysis, and a safe refactoring sequence. Use when the user says "review our codebase architecture", "reduce coupling in this module", "find circular dependencies", or "refactor this god object". Do not use when the user wants a migration plan to a different system, not restructuring the current codebase — that's code-migration-planner.
Designs, builds, and debugs multi-agent systems using proven orchestration patterns — task decomposition, Claude Code worktree orchestration, YAML agent config, and production monitoring. Use when the user says design a multi-agent system, set up Claude Code worktrees, or write a YAML agent config. Do not use when they just need to decide if one task warrants multiple agents, not build the full architecture.
by Nex AI
Organize self-hosted services into a structured agency operating system with port mapping and retainer models.
Produces a scored WCAG 2.1 AA accessibility audit of a WordPress theme or page, plus code fix patches per finding. Use when the user says "check WCAG compliance on my WordPress site", "audit WordPress accessibility", "fix accessibility violations in my theme", "European Accessibility Act check", or "is my WP site accessible". Do not use for a Figma design, not a live site — use design:accessibility-review instead.
Produces a pre-merge checklist derived from your diff — test coverage, migrations, docs, feature flags, and leftover debug code. Use when the user says "is this branch ready to merge", "pre-merge checklist", "what am I missing before I ship this", or "branch cleanup checklist". Do not use when the user wants a full code review of logic and design, not a merge-readiness checklist.
by SkillForge
Force your AI agent to apply senior-level architectural judgment and design notes before writing any code.
by Shandra
Creates phased modernization plans for transforming monolithic applications into modular monoliths, service-oriented systems, or microservice-ready architectures without risky rewrites.
Design and write the eval suite for your LLM-powered feature — the metrics that match your failure modes, a golden dataset plan with starter cases, anchored rubrics, LLM-as-judge prompts with the known bias mitigations, and pass/fail gates wired for CI.
Fills 10 motion-graphic animation templates — progress bar, checklist reveal, before/after, testimonial fade, and logo animation — with paste-ready prompts for any brand in AI motion tools. Use when the user says motion graphic prompt, animate my brand colors, or wants kinetic headline prompts for AI video tools. Do not use when they want frame-by-frame animation code, not paste-ready AI prompts.
by Timoranjes
Transform your AI agent from a code generator into a senior architect that enforces clean design and SOLID principles.
by Boubacar B
Claude can write frontend code. What it needs is a design system vocabulary to write CONSISTENT frontend code. This skill gives it that vocabulary, so every button, form, and layout follows the same rules across your entire app.
Design the right team of specialized AI subagents for your project and get the definition files written properly — precise delegation triggers, focused system prompts, least-privilege tools, and the right model tier for each job. Includes a template, orchestration patterns, and a complete sample team.
by Timoranjes
Teaches AI coding agents the discipline of context engineering — designing what information the agent sees, when, and in what format — to dramatically reduce token waste, prevent session amnesia, and
by Echo Rose
Api Design Reviewer - A Premium AI Agent Skill
by Timoranjes
Teaches AI coding agents to design safe Prisma schemas that prevent data loss, race conditions, N+1 queries, and the dangerous Prisma migration reset. Covers 12 critical anti-patterns (missing indexes
by DesignBureau
Stop guessing at bugs. A 4-phase method that makes you find root cause before touching the code. Takes debugging from hours to minutes. Works in any language, with any AI agent.
Model quality is table stakes — the harness is where agents win or fail. This designs yours: it writes a structured, testable system prompt (role, tools, boundaries, method, output contract, failure handling) and maps every concern to the right layer — prompt, tool, guardrail, or evaluation — so the pieces reinforce each other instead of fighting.
by PupLogic
Automated WCAG 2.1 AA accessibility auditor that computes contrast ratios and provides code-level fixes.