wiki-reader
Search and query the wiki — index-first navigation, reads relevant pages, synthesizes cited answers. Automatically researches if wiki doesn't have the answer.
An agent is a specialist Claude hands a whole job to, with its own tools and its own context.
2,200 agents across 245 plugins.
Search and query the wiki — index-first navigation, reads relevant pages, synthesizes cited answers. Automatically researches if wiki doesn't have the answer.
Use this agent when documentation needs to be generated or updated as part of a session — user-facing READMEs, dev-focused CLAUDE.md sections, or vault…
Use this agent during the /eval Skill Phase 3 (Epic #803, issue #810) to judge — from a session-eval record's dimension evidence, kpis, and session_id — the…
Reference documentation (NOT a dispatchable agent) for the coordinator-direct AUQ rendering flow at session-end Phase 3.6.3. The coordinator collects proposals…
Finds verified contextual internal link opportunities with websearch and review-ready paragraph edits.
Runs keyword research with DataForSEO when enabled and produces normalized keyword evidence for clusters and content.
Initializes Agentic SEO project with the required folder layout, blank brain templates, contents directories, and first log entry. Use when creating a new…
Eval Agent for AutoResearch. Designs the scoring system — receives user-confirmed criteria and the target prompt, then generates eval.py + test_cases.json…
Judge Agent for AutoResearch. Scores outputs against a locked rubric for quality assessment. Operates with fresh context every iteration — knows NOTHING about…
Test Runner Agent for AutoResearch. Executes the prompt/skill for real using all available tools (web search, APIs, file access). Operates with fresh context —…
Checks code for security vulnerabilities including OWASP Top 10, secret leaks, and injection attacks. Use PROACTIVELY before commits when working with…
Guides test-driven development, helps write test cases, and ensures code quality. Use PROACTIVELY when writing new features, fixing bugs, or refactoring code.…
UI/UX design agent. Creates design variants, component systems, and developer handoffs. For founders and designers who want pixel-perfect apps.
Fullstack vibe coding assistant. Talk naturally — I plan, code, test, and deploy for you. Perfect for non-tech founders and solo builders.
Psychological synthesizer that distills raw research into AI agent personas. Invoked by /craft:become during Phase 3 (Crystallization). Takes research branch…
Technical documentation writer crystallized from studying how Stripe/Linear-quality doc practitioners think. Consult when writing or reviewing any…
The craft guide - an educated, read-only guide to using the craft plugin itself. Use proactively when the user asks how craft works or how to use it on their…
코드베이스 탐색 전문가. 기존 패턴, 유사 구현, 의존성 그래프 파악. Use before BUILD to understand existing code landscape.
프론트엔드 전문가. React/Next.js/Vue/Svelte UI 구현 + 접근성 + UX 검증. Spawned for *.tsx/*.vue/*.svelte files in Phase 2 and Phase 3.5.
설계 vs 구현 Gap 분석 전문가. Match Rate 계산 및 미구현 항목 추출. Use proactively in GAP/ITERATE modes.
Creates executable phase plans with task breakdown, dependency analysis, and goal-backward validation. Spawned by /hunt:plan orchestrator.
Creates project huntmaps with phase breakdown, requirement mapping, success criteria derivation, and coverage validation. Spawned by /hunt:new-program…
Investigates bugs using scientific method, manages debug sessions, handles checkpoints. Spawned by /thrunt:debug orchestrator.
Research a topic landscape, generate and select research ideas, and save them under ideas/.
Improve an existing idea using reviewer feedback and write the next idea version.
Review an idea for novelty and quality, write the review, and update its ideas.xml score.
Objective fact-finder who finds code first, theories second. Verifies claims with evidence.
Identifies benefits, opportunities, and value across the full spectrum - from simple wins to bold strategic plays.
Execute ENCODE WGBS pipeline from FASTQ to methylation calls using Bismark and MethylDackel
審查程式碼品質、正確性和專案慣例遵循情況。發現錯誤、提供改進建議, 並確保程式碼符合專案標準。 使用時機範例: - "審查這個新功能的程式碼品質" - "檢查是否有潛在的錯誤或問題" - "確認程式碼遵循專案慣例" - "提供改進建議"
簡化和優化程式碼以提升清晰度、一致性和可維護性,同時保持原有功能不變。預設專注於最近修改的程式碼,除非另有指示。
深入調查程式碼庫,定位問題相關程式碼,識別多個可能原因並評估可能性。 基於 problem-analyzer 提供的調查方向,系統化地搜尋程式碼庫,找出所有可能導致問題的程式碼位置。 使用時機: - "調查這個問題在程式碼庫中的可能位置" - "搜尋與這個錯誤相關的程式碼" - "找出所有可能導致這個問題的程式碼"…
Advanced technical analysis with indicators and pattern recognition. Use for RSI, MACD, Bollinger, chart patterns, support/resistance, and trading signals.
TDD implementation agent for beast. Executes plan tasks with strict RED-GREEN-REFACTOR discipline.
TDD implementation agent for forge pipeline-v3. Spawned per-stream; enforces RED-GREEN-REFACTOR with retry protocol and phase-2 short-circuit.
Quick codebase explorer for beast. Maps project structure, tech stack, test infrastructure, and key patterns.
Use when: reviewing PRs, analyzing code quality, or checking SOLID/OWASP/Clean Code compliance. Do NOT use for: writing or implementing code (use a domain…
Use when: the owner wants to commit, save work, or release — the lead delegates ALL commits here, never runs `git commit` itself. Do NOT use for: read-only git…
Use PROACTIVELY when: user says commit/save/git, mentions wip/feat/fix/chore. Do NOT use for: code review, non-commit git ops (log/diff/status).
Focus on implementing the proxy of UI components accurately according to the design draft, and save the implementation report as a Markdown file. Supports six…
Front-end performance analysis and optimization specialization: Core Web Vitals, packaging volume, runtime and rendering, network and cache, memory leak…
Front-end Dead Code & Technical Debt Cleanup Subagent: Identifies unused components, exports, styles, routes, dependencies and test fixtures, categorizes them…
Use project form components instead of native elements in all `.tsx` files. Native form elements bypass GAIA's Conform integration and accessible error/label…
- Single `useTranslation()` call per component, flag multiple `useTranslation` calls in the same component - Namespace override via `{ns: 'other'}` as the…
- Import only from `tailwind-merge`, flag any use of `clsx`, `classnames`, or `cn` wrappers for class merging - `twJoin` when no class conflict is possible…
© 2026 Flowy · Free and open source
Built for Claude Code · Not affiliated with Anthropic