90 specialist AI agents + 3 project-local extensions for Claude Code / Codex CLI / Antigravity CLI (agy). Anthropic Agent Skills spec-aligned, hub-spoke orchestration via Nexus with 49 Recipes and 11 Skill Packs. Covers development, security, design, testing, FinOps, compliance, observability, and AI/ML.
This repository also configures its own agents. See what agent-skills tells them →
Skill Claude CodeCodex
Brainstorming interactively to deepen ideas via four modes (Expand/Propose/Evaluate/Subtract). Does not write code. Not for decisions (Magi), feature specs (Spark), or one-shot reframing (Flux).
Skill Claude CodeCodex
Advising founders YC-style — socratic probing to surface the #1 bottleneck, anti-pattern detection, and 1-2 week action items. Not for brainstorming (Riff) or long-term scenarios (Helm).
Skill Claude CodeCodex
Designing multi-tenant architectures with tenant isolation strategies, RLS, routing, and scale design for SaaS. Use when designing multi-tenant SaaS systems or tenant isolation.
Skill Claude CodeCodex
Generating AI image-generation code using the Gemini API. Handles text-to-image generation, image editing, and prompt optimization. Use when image generation code is needed.
Skill Claude CodeCodex
Automating iOS UI via XCUITest and fastlane snapshot pipelines for App Store screenshots. Not for cross-platform E2E (Voyager), iOS feature impl (Native), or unit tests (Radar).
Skill Claude CodeCodex
Channeling the documented thinking of named notable figures (an 'itako' medium) — their mental models, heuristics, and decision-style as advisory lenses. Not for decisions (Magi) or personas (Cast).
Skill Claude CodeCodex
Designing scheduling and time-aware logic for cron, timezone/DST, retry/backoff, and business-calendar systems. Use when schedule design is needed.
Skill Claude CodeCodex
Delivering working code fastest via build-first product delivery through minimum agent chains; S/M scopes skip planning and build immediately. Use when compressing time-to-first-PR.
Skill Claude CodeCodex
Architecting crawl and scraping systems: distributed crawler topology, URL frontier, politeness, compliance. Architecture-only. Not for single-page scraping (Vector) or ETL pipelines (Stream).
Skill Claude CodeCodex
Authoring tech blog/article series for note/Zenn/Qiita/dev.to. Not for specs (Scribe) or microcopy (Prose).
Skill Claude CodeCodex
Designing new skill agents via gap analysis, overlap detection, SKILL.md + reference generation, and Nexus integration. Not for task orchestration (Nexus) or format-only audits (Gauge).
Skill Claude CodeCodex
Implementing production frontend code for React/Vue/Svelte: hooks design, state management, Server Components, form handling, data fetching. Converts Forge prototypes to production quality.
Skill Claude CodeCodex
Orchestrating design-to-implementation pipelines (code to visual to code closed loop), persisting a project design system across agents. Not for a single prototype (Forge) or direction only (Vision).
Skill Claude CodeCodex
Analyzing dependencies, circular references, and God Classes; authoring ADRs/RFCs. Use for architecture improvement, module decomposition, and technical debt assessment.
Skill Claude CodeCodex
Verifying spec compliance: extracts ACs from specs, adversarially checks conformance, generates BDD scenarios and traceability matrices. Use when impl must be proven to match a PRD/SRS/AC.
Skill Claude CodeCodex
Engineering observability and reliability: SLO/SLI design, distributed tracing, alerting, dashboards, capacity planning, toil automation, reliability review. Use for instrumentation or SLO definition.
Skill Claude CodeCodex
Optimizing frontend (re-render, memoization, lazy loading) and backend (N+1, indexing, caching, async) performance, plus continuous auto-tuning loops for GC/threadpool/cache/worker settings.
Skill Claude CodeCodex
Designing red team attack scenarios, threat models, MITRE ATT&CK/OWASP application, Purple Team exercises, and AI/LLM red teaming. Use when adversarial security validation is needed.
Skill Claude CodeCodex
Implementing robust business logic, API integrations, data models, and reproducible AI image-generation code with type safety. Use for production implementation, Gemini image API pipelines, or interactive pair programming.
Skill Claude CodeCodex
Assessing standards, regulatory controls, and legal-document coverage with cited evidence and proposed wording. Use for OWASP/WCAG/SOC2/PCI/HIPAA or ToS/privacy/DPA reviews; not legal advice or code fixes.
Skill Claude CodeCodex
Visualizing code, specs, or context as Mermaid, ASCII, or draw.io diagrams: flowcharts, sequence/state/class/ER, Journey Maps, personas, coverage heatmaps. Use to reverse-document systems visually.
Skill Claude CodeCodex
Casting personas: rapid generation from diverse inputs, registry-based persistence and lifecycle, data-driven evolution, inter-agent sync. Not for UI walkthroughs (Echo) or user research (Field).
Skill Claude Code
Auditing skill/plugin/MCP supply chains and live package compromise: manifests, hidden injection, IoC scans, persistence-first eradication, and gated credential rotation. Not for app SAST (Sentinel).
Skill Claude CodeCodex
Converting a supplied prompt into an executable specification: detects vague quality/quantity/explanation/style/design/technical/judgment wording, role and persona theater, and self-contradiction, then replaces each with a numeric bound, an observable behavior, or a scorable criterion — with a per-term ledger of what…
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: