qa-report-reviewer-age…
Auto-Harness reviewer subagent for sprint QA report compliance. Use only immediately after evaluator_qa writes the current sprint QA report.
An agent is a specialist Claude hands a whole job to, with its own tools and its own context.
4,470 agents across 361 plugins.
Auto-Harness reviewer subagent for sprint QA report compliance. Use only immediately after evaluator_qa writes the current sprint QA report.
Auto-Harness reviewer subagent for parallel sprint QA report compliance. Use only immediately after evaluator_qa_parallel writes the current sprint QA report.
- [Identity] Mystique MCP를 활용해 Figma 디자인 노드를 분석하고, 코드 구현 또는 디자인-코드 일치 검증을 수행하는 전문가
Yield aggregator and ERC-4626 specialist. Yearn V3, Beefy, Sommelier, MetaMorpho, custom vaults with strategies. Use when target is an ERC-4626 vault or…
ZK proof-verifier contract specialist. Groth16/PLONK/Halo2 on-chain verifiers, public-input binding, pairing-precompile misuse, field-range checks, nullifier…
Tests must be **isolated** (independent of each other) and **deterministic** (same result every run). That means controlling everything that crosses a boundary…
You can't fix what you can't see. Observability is the practice of making a system's internal state inspectable from the outside, through three complementary…
Write this after a significant bug or incident is resolved. The goal is **systems, not scapegoats** — ask how the process let the defect through, not who typed…
Recommends the cheapest direct-read, Markdown, graph build, update, or query path for a corpus while keeping graphify as the primary long-lived memory engine.
Evaluates ML experiment setups for rigorous baseline comparisons, proper metric tracking, and reproducibility.
Audits evaluation code to ensure test sets are clean, metrics are appropriate for the problem, and confidence intervals are computed.
Engineering-перспектива тестов. Читает фичу, GitHub-pattern для похожих, предлагает 3-7 verification commands (1 happy + 2-3 edge + 1-2 error + 1 e2e). Не…
Top-down критика глазами реального пользователя продукта. Читает PRODUCT.md и domain-rules.yaml, спрашивает "какой сценарий не покрыт?", "оптимизируем по…
Строит валидационную выборку 50-100 реалистичных сценариев (синтетика ≤20%) + ground truth + бинарная оценка. Прогоняет на текущей сборке. Финальный gate ≥90%…
Stage 2 reviewer focused on logging, metrics, tracing, and alertability.
Stage 2 reviewer focused on cross-system bottlenecks, capacity, and hot paths.
Stage 2 reviewer focused on PII handling, GDPR-style data subject rights, retention, and consent.
Final report assembly specialist. Invoke in Phase 06, once artifacts/findings/validated-findings.json exists (PoCs if any). Synthesizes validated findings,…
SAST specialist for hardcoded secrets and cryptographic failures (API keys/credentials in source, weak crypto on sensitive data), scoped to Medium-Critical…
SAST specialist for SQL/NoSQL injection. Invoke during Phase 03 Testing after artifacts/mapping/attack-surface.json exists. Statically traces user input into…
Use when the sprint is done and the team wants to prepare a release — assembles a signed, submission-ready build for iOS and Android, owns version bumps, build…
Use on flagship work for the reliability review dimension — offline behaviour, retries, idempotency, sync conflict resolution, state restoration, and recovery…
Use before /app-ship to audit the codebase for shippable-state security issues — credential handling, network safety, data-at-rest, third-party SDKs, OS…
Elite AI-powered customer support specialist mastering conversational AI, automated ticketing, sentiment analysis, and omnichannel support experiences.…
Build scalable data pipelines, modern data warehouses, and real-time streaming architectures. Implements Apache Spark, dbt, Airflow, and cloud-native data…
Expert data scientist for advanced analytics, machine learning, and statistical modeling. Handles complex data analysis, predictive modeling, and business…
Act as an Azure Bicep Infrastructure as Code coding specialist that creates Bicep templates.
Act as implementation planner for your Azure Bicep Infrastructure as Code task.
Use this agent when building smart contracts, DApps, and blockchain protocols that require expertise in Solidity, gas optimization, security auditing, and Web3…
Long-form marketing content producer orchestrating the content-production skill (research → brief → draft → optimize → gate). Use when content must be written,…
Execution-OS COO advisor for operating cadence, OKRs, scorecards, DRI clarity, and scaling playbooks
JTBD-driven CPO advisor for product vision, portfolio strategy, PMF, North Star metrics, and roadmap focus
Analyzes one function in depth for audit context: invariants, assumptions, and what its callees establish. Writes the prose analysis to disk and returns a…
Creates proof-of-concept exploits (pseudocode, executable, and unit tests) demonstrating a verified vulnerability, plus negative PoCs showing exploit…
Deduplication judge for the rust-review pipeline. Merges duplicate findings deterministically by exact location and bug class, then runs LLM passes over…
Review implementation by comparing plan (intent) vs Braintrust session (reality) vs git diff (changes)
© 2026 Flowy · Free and open source
Built for Claude Code · Not affiliated with Anthropic