tech-writer
Documentation owner. MUST BE USED for README, CHANGELOG, docs/ updates. PROACTIVELY manages all markdown files as sole authority for documentation.
An agent is a specialist Claude hands a whole job to, with its own tools and its own context.
4,481 agents across 361 plugins.
Documentation owner. MUST BE USED for README, CHANGELOG, docs/ updates. PROACTIVELY manages all markdown files as sole authority for documentation.
Action-specific Auto-Harness Generator subagent for approved sprint implementation. Use only when the current legal action is generator_build.
Worktree-bound Auto-Harness Generator worker for one dependency graph node during generator_build_parallel.
Action-specific Auto-Harness Generator subagent for sprint contract drafting and contract revision. Use only when the current legal action is…
- [Specificity] 선택자 우선순위를 의도적으로 관리한다 - [Responsive] 반응형 디자인을 모바일 퍼스트로 작성한다 - [TokenUsage] 디자인 토큰(변수)을 하드코딩 값보다 우선 사용한다
Development guide expert for task breakdown and implementation
PRD quality and feasibility expert for comprehensive reviews
Code quality and testing expert for comprehensive QA
Use this agent when the user wants to autonomously validate and optimize their CLAUDE.md files. This agent runs claudelint validation, analyzes results, and…
Identifies protocol invariants from contract code and intent, generates Foundry invariant tests with handlers. Use from /invariant and /audit-deep.
L2/rollup-risk specialist. Sequencer-uptime oracle, force-inclusion, L1↔L2 messaging delays, address aliasing, opcode/timestamp divergence. Use when the target…
Lending-protocol specialist. Aave V3, Compound V3, Morpho, Silo, Euler, custom lending. Use when the target is a lending pool, isolated market, or liquidation…
Run through this before declaring an API contract done. It is ordered the way you should *design*: resources first, cross-cutting rules last. Every box is a…
A threat model is only as good as the diagram it sits on. The data-flow diagram (DFD) is the map; trust boundaries are where the dangerous neighborhoods are.…
A standalone data-flow diagram with its trust boundaries explained, to illustrate the notation before you build your own. The system: a file-upload feature…
Use this agent for a dedicated secure-coding review of Python or React/JS code — flagging outdated/vulnerable functions with concrete safe alternatives,…
Conducts security investigations and analytical deep-dives — correlates telemetry across sources, enriches with threat intel, reconstructs timelines, scopes…
Designs and reviews system security architecture end to end — secure-by-design, trust boundaries, threat modeling, control selection, and security…
Expert in developer productivity, workspace orchestration, and build system optimization. Use for setting up efficient workspaces, optimizing CI/CD, and…
Scans documentation for stale file paths, outdated code blocks, and broken links after refactoring.
Analyzes logs, stack traces, and error patterns to diagnose complex system failures. Use when investigating production incidents or cryptic test failures.
Dispatched leaf for technical-SEO analysis — runs the 9-category technical audit (crawlability, indexability, security headers, URL structure, mobile, Core Web…
Автономная реализация фичи. TDD по test-strategy.md, Карпати-принципы (think + simplicity + surgical + goal-driven), auto-commits, периодические progress…
Анализ рынка и конкурентов. Минимум 3 прямых конкурента + 3 косвенных. UX-анализ их продуктов (что зашло пользователям). Параллельно с github и best-practices…
Финальный этап FULL pipeline. Готовит пакет запуска — позиционирование, ICP, messaging, pricing, landing-brief для Claude Design, email-sequences. Только при…
The `max` rung of `cad-reviewer`; `bin/route.mjs` picks it, not the user.
The `medium` rung of `cad-reviewer`; `bin/route.mjs` picks it, not the user.
The `xhigh` rung of `cad-reviewer`; `bin/route.mjs` picks it, not the user.
Stage 1 peer code reviewer focused on TypeScript type safety, async correctness, and idioms.
Stage 0. Reads project, interviews user, casts the review committee.
Stage 2 reviewer focused on WCAG 2.2 AA, semantic HTML, keyboard support, and screen reader UX.
SAST specialist for OWASP Mobile M10:2024 Insufficient Cryptography. Invoke during mobile Phase 03 Testing after artifacts/mapping/mobile-attack-surface.json…
Attack-surface prioritization specialist for mobile apps. Invoke in Phase 02 of the mobile pipeline, after artifacts/recon/mobile-recon.json exists. Reads…
SAST specialist for OWASP Mobile M5:2024 Insecure Communication. Invoke during mobile Phase 03 Testing after artifacts/mapping/mobile-attack-surface.json…
Use to implement revenue — StoreKit 2 / Play Billing subscriptions and IAP, the paywall gateway, AdMob ads with consent, frequency caps, and NO-AD zones. Owns…
Use before /app-ship on flagship work for the privacy pass — data inventory, consent, retention, third-party sharing, and regional compliance. Distinct…
Use to compose the screens in the ux-architect's inventory — layout, hierarchy, interaction, visual quality — and to own the design tokens and component…
- LinkedIn Jobs - Indeed - Glassdoor - Wellfound - Remote OK - FlexJobs
Expert C4 Context-level documentation specialist. Creates high-level system context diagrams, documents personas, user journeys, system features, and external…
Expert cloud architect specializing in AWS/Azure/GCP/OCI multi-cloud infrastructure design, advanced IaC (Terraform/OpenTofu/CDK), FinOps cost optimization,…
© 2026 Flowy · Free and open source
Built for Claude Code · Not affiliated with Anthropic