comments
Verify comment accuracy, detect comment rot, and ensure documentation quality through systematic 5-step analysis.
An agent is a specialist Claude hands a whole job to, with its own tools and its own context.
8,249 agents across 643 plugins.
Verify comment accuracy, detect comment rot, and ensure documentation quality through systematic 5-step analysis.
**Scope**: Failure modes in agent output style — over-reporting, self-congratulation, verbose narration, and hedging. Covers what to detect and how to fix…
Use this agent when the user encounters SAC script errors, needs to debug Analytics Designer or Optimized Story scripts, or asks "why is my script not…
Use this agent when reviewing SAP Analytics Cloud test automation intake packets, dashboard profiles, scenario YAML, selector choices, readiness rules,…
Use this agent when the user asks to "analyze my SQLScript", "review HANA procedure", "check procedure performance", "find SQLScript issues", "audit SQLScript…
Interactive document accessibility audit wizard. Use to run a guided, step-by-step accessibility audit of Office documents (.docx, .xlsx, .pptx) and PDFs.…
Internal helper agent. Invoked by orchestrator agents via Task tool. Internal helper for exporting document accessibility audit findings to CSV format.…
Internal helper agent. Invoked by orchestrator agents via Task tool. Internal helper for document file discovery, inventory building, and metadata extraction.…
Bug修复与根因分析专家,负责问题定位、二分法缩小范围、最小化修复、回归测试编写,确保每个修复都精准且不引入新问题
Compares old vs new instruction outputs against original codebase, scores 8 quality categories, emits pass/fail JSON verdict for CI/CD validation pipeline
Validate that implementation matches intent via execution and evidence. Full subagent.
Validate that implementation matches intent via execution and evidence. Full subagent.
Advanced code quality analysis agent for comprehensive code reviews and improvements
Deploy specialized AI agents to perform comprehensive, intelligent code reviews that go beyond traditional static analysis
Implementation specialist for writing clean, efficient code with self-learning capabilities
Git workspace analysis agent specializing in repository state assessment,
Orchestrates active security hardening. Discovers languages, dispatches per-area scans, synthesizes findings with NIST/CWE citations, and proposes concrete…
Execute implementation tasks systematically following the task plan with
NestJS database specialist that provides expertise in Drizzle ORM setup, schema design, migrations, queries, transactions, and database operations. Use…
NestJS security specialist that provides authentication, authorization, JWT implementation, guards, security middleware, and security best practices. Use…
NestJS testing specialist that provides unit tests, integration tests, end-to-end tests, test database setup, mocking strategies, and testing best practices.…
Creates executable phase plans with task breakdown, dependency analysis, and goal-backward verification. Spawned by /gsd-plan-phase orchestrator.
Researches domain ecosystem before roadmap creation. Produces files in .planning/research/ consumed during roadmap creation. Spawned by /gsd-new-project or…
Synthesizes research outputs from parallel researcher agents into SUMMARY.md. Spawned by /gsd-new-project after 4 researcher agents complete.
Expert Python code reviewer specializing in PEP 8 compliance, Pythonic idioms, type hints, security, and performance. Use for all Python code changes. MUST BE…
PyTorch runtime, CUDA, and training error resolution specialist. Fixes tensor shape mismatches, device errors, gradient issues, DataLoader problems, and mixed…
Dead code cleanup and consolidation specialist. Use PROACTIVELY for removing unused code, duplicates, and refactoring. Runs analysis tools (knip, depcheck,…
Git operations: branch management, rebases, merges, stacked PRs, recovery operations, clean commit history.
Infrastructure as Code specialist who designs Terraform modules, Kubernetes manifests, and cloud architecture. Focuses on AWS/GCP/Azure patterns, networking,…
LLM integration: OpenAI/Anthropic/Ollama APIs, prompt templates, function calling, streaming, token cost optimization.
Tally session token cost vs milestone budget. Warn when a phase is on track to exceed allocation.
Maintain a canonical lore/world bible — characters, places, rules, factions. Source of truth for continuity checks.
Audit research method, bias surface, source quality, and traceability for a single research artefact. Trigger per artefact pre-publish.
Autonomously diagnoses Nuxt 4 issues through 7-phase analysis. Use when encountering hydration, SSR, routing, data fetching, or performance problems.
Autonomously migrates Nuxt 3 to v4 through 6-phase analysis. Use when upgrading projects or encountering v3 compatibility issues.
Autonomous performance analysis agent that optimizes Nuxt 4 applications through 6-phase analysis (bundle, components, data fetching, rendering, assets,…
You are a structural analyst. Your job is to examine the static architecture of a specified focus area — how modules are organized, how they depend on each…
You are an adversarial system architect. Your default posture: the current cross-service / cross-context topology is wrong until evidence says otherwise.
You are a test engineer. Your job is to examine code, discover which behaviors are and aren't tested, and produce a prioritized test plan that achieves…
© 2026 Flowy · Free and open source
Built for Claude Code · Not affiliated with Anthropic