contractor
Parses a user feature request into a structured contract.json. Scans codebase for scope signals and risk assessment. Read-only -- never writes code files, only…
An agent is a specialist Claude hands a whole job to, with its own tools and its own context.
455 agents across 675 plugins.
Parses a user feature request into a structured contract.json. Scans codebase for scope signals and risk assessment. Read-only -- never writes code files, only…
Implements code changes according to a contract.json specification. The ONLY agent in Signum that writes code. Includes a repair loop: generate -> check -> fix…
Synthesizes project.intent.md and project.glossary.json from deterministic scan signals. Uses ranked source hierarchy and explicit-only Non-Goals extraction.…
Use this agent ONLY when a human has just run /memory-seed and the new L1 atoms need folding into scenes and persona. Automatic consolidation no longer goes…
Clean-context design reviewer. Reviews just-written code changes with zero memory of writing them — catches half-finished changes and cross-file drift (a file…
Evidence verifier for repo-xray scan results. Opens the actual code at each scanner candidate and decides which ones are real — filtering the noise a regex/AST…
Build and TypeScript error resolution specialist. Use PROACTIVELY when build fails or type errors occur. Fixes build/type errors only with minimal diffs, no…
Personal communication chief of staff that triages email, Slack, LINE, and Messenger. Classifies messages into 4 tiers…
Designs feature architectures by analyzing existing codebase patterns and conventions, then providing implementation blueprints with concrete files,…
Build and TypeScript error resolution specialist. Use PROACTIVELY when build fails or type errors occur. Fixes build/type errors only with minimal diffs, no…
Personal communication chief of staff that triages email, Slack, LINE, and Messenger. Classifies messages into 4 tiers…
Designs feature architectures by analyzing existing codebase patterns and conventions, then providing implementation blueprints with concrete files,…
Web performance engineer focused on Core Web Vitals, loading, rendering, and network optimization. Use for performance-focused audits, CWV analysis, and…
Analyzes Figma structural nodes (pages, screens, components, instances, tokens) from a deterministic manifest and adds semantic enrichment — concise summaries,…
Analyzes codebases to extract business domain knowledge — domains, business flows, and process steps. Produces a domain-graph.json that maps how business logic…
Analyzes batches of source files to produce knowledge graph nodes and edges. Extracts file structure, functions, classes, and relationships using a two-phase…
Cross-platform creative specialist. Returns schema-valid findings covering creative fit, concept diversity, fatigue, format coverage, message match, and…
Google Ads evidence and controls specialist. Returns schema-valid findings for conversion tracking, search terms, campaign structure, bidding, PMax, Demand…
LinkedIn Ads evidence and controls specialist. Returns schema-valid findings for Insight Tag and conversions, professional audiences, lead generation,…
You prevent the interview from collapsing onto a single thread when the user actually has multiple unresolved concerns.
You are an autonomous coding agent executing a task for the Ouroboros workflow system.
You analyze existing codebases to extract context for brownfield development.
Use this agent when the user provides a research paper (PDF/DOCX/arXiv link) or asks to learn writing patterns from papers, extract venue-specific writing…
Use this agent when the user asks to "write rebuttal", "respond to reviewers", "analyze review comments", or needs help with academic paper review response.…
Test-driven development guide for writing tests first, implementing the smallest passing change, and keeping verification tight. Use when the user explicitly…
E-E-A-T curator for the Claude Blog Brain. Maintains and answers from the E-E-A-T theme of the brain, grounded in the vault and its dated sources. Advisory and…
FLOW curator for the Claude Blog Brain. Maintains and answers from the FLOW theme of the brain, grounded in the vault and its dated sources. Advisory and…
GEO and AEO curator for the Claude Blog Brain. Maintains and answers from the GEO and AEO theme of the brain, grounded in the vault and its dated sources.…
Authors and edits brooks-lint skill content — the six shipped skills (skills/{name}/SKILL.md + {name}-guide.md) and the shared framework under skills/_shared/.…
Audits the trigger boundaries of the six brooks-lint skills for false-triggering risk and routing collisions. Use before a release, or after editing any…
Analyzes a plan and generates multiple-choice technical comprehension questions to verify user understanding before RLCR loop. Use when validating user…
Manage Datadog App Builder applications including listing, creating, updating, publishing, and managing custom low-code internal tools.
Manage Application Security Management (ASM) including WAF rules, threat detection, API protection, and application-level security monitoring.
Query and segment RUM users and accounts, manage data connections to enrich audience data with external sources like CRMs and reference tables.
`quality-gatekeeper-agent` 是 PaperFit 的最终门禁。它不负责修复,也不负责发现新问题;它负责判断当前结果是否真的可以对外宣称“完成”。
你是 **Rule Engine Agent**(规则引擎),是 PaperFit 系统中专门负责 **解析编译日志、识别确定性错误与警告** 的智能体。你的核心职责是:
`semantic-polish-agent` 只负责受控语义修改,而且只能在排版手段已经用尽后出场。它不是常规修复主路径,而是最后阶段的受限补充能力。
Independent code reviewer powered by OpenAI Codex (GPT-5) via the local Codex CLI. Use when the user asks to review changes, a PR, a branch, or a module —…
Get an independent opinion from OpenAI Codex (GPT-5) on a design decision, an approach, a tradeoff, or an unfamiliar area of the codebase — a general-purpose…
Use this agent when you need to create comprehensive test plan for a web application or website
Orchestrates multi-step QA workflows by delegating to specialized agents. Activate when task involves planning, generating, healing, or refactoring tests…
© 2026 Flowy · Free and open source
Built for Claude Code · Not affiliated with Anthropic