分析
分析、报表与可视化
ab-test-setup
alexwelcing
Design and implement statistically valid A/B tests
stock_analyzer
majuntao12369-code
"分析股票和市场。当用户想要分析单个或多个股票，或进行市场复盘时调用。"
report-writer
crossx362-commits
영숙(비서)이 예원·펫나 팀 산출물(감사·리뷰·주간 정리 등)을 정식 리포트로 포맷한다. 채팅/텔레그램엔 핵심 요약, 노션엔 풀 리포트를 작성하는 분리 규칙을 적용한다. "리포트 작성", "노션에 정리", "보고서로 만들어", "정식 리포트", "주간 정리" 등에 트리거.
edge-performance
robertsben333-cmyk
Folds every newly closed position and every newly resolved edge-hunt run into the performance ledger, rebuilds the dashboard, and writes down what changed. Use when asked to update the performance dashboard, check what the edge hunt is earning, score the closed trades, or analyse stage E's results over time.
improve-codebase-architecture
YuukiFST
Scan a codebase for deepening opportunities, present them as a visual HTML report, then grill through whichever one you pick.
mintlify-setup
hk-vk
Mintlify documentation and resources. Use this skill when working with Mintlify or when the user mentions mintlify.
dashboard
yshi0730
Build and serve visual dashboards for any agent — install hub, register modules, add widgets, push data, accessible from anywhere via stable URL.
build-family-dashboard
emirtdede
Builds adult read/admin dashboards with completion, overdue, accuracy, speed and topic analytics.
imagine-best-practices
midhunxavier
Publication-quality scientific figures with the Imagine framework (React → SVG/PNG). Use when designing, reviewing, or exporting charts/diagrams/multi-panel figures for papers, posters, or preprints, especially when you need mm+dpi sizing, vector-first SVG, typography/color guidance, and final submission checks.
release-checklist
hwy-game
Use when reviewing whether a change is ready to release.
okane-skills
inoue2002
家計簿の残高予測・シミュレーションスキル。「残高予測」「何ヶ月後にいくら」「この出費大丈夫？」「お金足りる？」「貯金シミュレーション」「ログ圧縮」「危険ポイント検出」などの依頼時に使用。okane-backup-*.json形式のファイルを読み込み、将来の残高推移予測、大きな出費の可否判定、残高不足警告を行う。
langgraph-agent
avenstack
Design, implement, and debug LangGraph agents for building stateful, multi-step workflows with LLMs. Use when creating LangGraph agents, implementing StateGraph workflows, adding memory and persistence, incorporating human-in-the-loop patterns, or implementing complex agent architectures with conditional branching and multi-agent systems.
zcl
marcohefti
Orchestrator workflow for running ZeroContext Lab (ZCL) attempts/suites with deterministic artifacts, trace-backed evidence, and fast post-mortems (shim support for "agent only types tool name").
observability-grafana-dashboards
baotoq
Create and manage production Grafana dashboards for real-time visualization of system and application metrics. Use when building monitoring dashboards, visualizing metrics, or creating operational observability interfaces.
Credit Card Chris - Feature Specifications
confire15
Environment validation — Validate all env vars at startup (fail fast)
complete-spec
jschulte
Interactive conversation to resolve [NEEDS CLARIFICATION] markers using /speckit.clarify command. Claude asks questions about missing features, UX/UI details, behavior, and priorities. Updates specs in .specify/memory/ with answers to create complete, unambiguous documentation. This is Step 5 of 6 in the reverse engineering process.
implementing-code-splitting
djankies
Teaches code splitting with lazy() and Suspense in React 19 for reducing initial bundle size. Use when implementing lazy loading, route-based splitting, or optimizing performance.
refactor-dependency
ShotaIuchi
Dependency mapping and analysis for refactoring. Apply when mapping import chains, call graphs, coupling relationships, circular dependencies, and hidden connections in target code.
viz
robdmc
Data visualization and inspection skill. Use for (1) creating matplotlib/seaborn plots from data files or marimo notebooks, or (2) inspecting DataFrames by showing first N rows, column names, and dtypes. For plots, provide chart type, data context, and styling. For inspection, ask to "show" or "display" the data.
ops-core
Dgardenhire
"Ops core Skill. Run on the approved schedule after one successful manual test."
daily-cost-report
0xjohmsmith
Calculate and report daily OpenClaw API usage costs from session files. Use when asked about daily costs, spending, API usage, token costs, or "how much did we spend" questions. Returns day-by-day cost breakdown for last N days (default 7), including per-agent and per-model breakdown with token counts.
methodology-v2
johnnylugm-tech
這個方法論幫助團隊標準化多 Agent 協作開發流程
three-teams-operating-model
carloscostato-cmyk
Opera o projeto com 3 times paralelos e papéis fixos (gerente de projetos, analista de sistemas, analista de processos, analista de testes) sob coordenação central. Use quando o usuário pedir diagnóstico completo, feedback por papel, operação simultânea dos times, status do sistema no GitHub, plano de correção ou acompanhamento da execução.
ideation-groom
specfuse
"Periodically triage the whole initiative ideation backlog -- surfacing ideas whose specs are authored and awaiting a mint decision, parking stale ones, and flagging internal dupes, items overtaken by minted work, under-shaped entries, bundle drift, and orphaned dossiers. The backlog analog of the PM's roadmap-sync: report-first, read-mostly (orchestrator registries/roadmap read-only), writing only the backlog index and never deleting a row or dossier."