Analytics
Data analysis and visualization
decision-support
by EnesMeyzin98
Maintain or extend the advisory decision-support layer that structures signal fusion, external context, AI validation, probabilistic edge, pipeline stage, and supervisor readiness without changing execution behavior. Use when working in app/decision_support.py, journaled decision-support payloads, or operator-facing decision interpretation.
review
by kelvinz
"Review branch changes against a base branch for correctness, security, tests, and scope, then return a clear go/no-go decision. Triggers: review, readiness check, pre-commit review, pre-finalise review."
prose-release
by nanomia-ai
Use when a prose-defined release review must be followed without losing its evidence and ordering rules.
stock_analyzer
by ddddd-r
"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。"
bug-report-root-cause
by dolessHQ
Produce per-item root cause analysis from bug report input. Inputs source and target where source is pasted file or linear issue and target is env scope.
benchmark
by hoangsonww
Benchmark one session (or a small recent set) against the rolling average using Agent Monitor data — cost, total tokens, tool count, and workflow complexity score — and report where each metric lands as a percentile of the population. Tells you whether a session was normal, cheap, or an outlier. Use when judging whether a session was typical or out of band.
concurrency-report
by hoangsonww
Report concurrency and parallelism for a session — how many agents ran in parallel, concurrency-lane utilization, peak parallel width, and serialization bottlenecks (sequential chains that could have run as parallel lanes) — using the Agent Monitor workflow intelligence API. Use when checking whether a multi-agent session used parallelism efficiently.
market-analyzer-meta
by Pengko
A股市场分析聚合层。根据用户意图自动识别分析方向（个股/大盘板块/消息面），路由到对应子 skill 执行。支持三种分析模式：个股微观→宏观、大盘宏观→微观、消息面驱动→板块→个股。
strategic-review-interactive
by kanghohyeong
This skill supports the strategic review process through a web interface.
retrieve_subgraph
by HowardKao-1130
Expand the document set by retrieving a KG subgraph and evidence.
model-mix
by hoangsonww
Break down Claude Code usage by model family (Opus / Sonnet / Haiku) from the Agent Monitor dashboard — each family's share of tokens, share of cost, and the spots where an expensive model is doing cheap work. Pulls per-model token and cost splits from /api/pricing/cost, current rates from /api/pricing, fleet token totals from /api/analytics, and per-session model assignment from /api/sessions. Use when deciding model routing or whether to downshift work to a cheaper tier.
research-report
by Weizhena
将deep调研结果汇总为markdown报告，覆盖所有字段，跳过不确定值。
react-useeffect
by VisualxIntelligence
React useEffect best practices from official docs. Use when writing/reviewing useEffect, useState for derived values, data fetching, or state synchronization. Teaches when NOT to use Effect and better alternatives.
binance-event-horizon
by 2675030956
Generate a futuristic Binance Event Horizon report that fuses spot, futures, Alpha, Web3 social hype, smart money signals, launchpad meme flows, and official Binance announcements into scenario cards, catalyst lanes, gravity alerts, orbit watchlists, and reusable broadcast packs. Use this skill when users ask for a multi-source Binance opportunity map, forward-looking market scenarios, catalyst tracking, leverage heat, Alpha early signals, meme launch attention, or a focused Event Horizon analysis on a single token or trading pair.
dead-code-eliminator
by abpai
Audit a codebase for dead code — unreachable functions, unused imports, orphaned classes, unreachable branches, and stale feature flags — by tracing live call paths from all entry points. Also audits correctness (do implementations match their claimed purpose?) and algorithmic soundness. Produces an ASCII call graph and a categorized dead code report. Use when a codebase has gone through many iterations, a large refactor has landed, a feature was removed but its support code may remain, or the user asks to "find dead code", "clean up unused code", "audit what's actually used", or "find orphaned functions".
workflow-report
by hoangsonww
Create a workflow-intelligence report from CCAM orchestration, delegation, tool flow, concurrency, complexity, compaction, and fleet-run data. Use for architecture reviews, agent-fleet analysis, or workflow optimization reports.
evaluator
by Overlord-Z
Skill evaluation and telemetry framework. Collects anonymous usage data and feedback via GitHub Issues and Projects. Privacy-first, opt-in, transparent. Helps improve ClaudeShack skills based on real-world usage. Integrates with oracle and guardian.
Stock Analysis
by Andy160675
Sovereign Skills Season 1: Foundation — Intelligence & Strategy
commit
by aravhawk
Commits with perfect messages. Use when making a commit.
lwql-charts
by langwatch
Author a saved analytics chart from a plain question and place it on a dashboard. Discovers the LangWatchQL analytics schema, writes and test-runs the SQL, saves it as a chart with a Vega-Lite specification, and places it where the team already looks. Use when asked to build, save, run, or dashboard a metric or chart.
advanced-data-visualization
by Hack23
Advanced chart types, D3.js/Vaadin Charts patterns, political data visualization, time series analysis
tech-visualizer
by yfe404
Create interactive, animated visualizations of technical and algorithmic concepts. Use this skill whenever the user asks to visualize, illustrate, explain visually, or create a diagram/animation for any technical concept — including but not limited to: cryptographic algorithms (HMAC-SHA, AES-CBC, RSA, TLS handshake), computer vision pipelines (ORB keypoints, SIFT, optical flow, convolutions), networking protocols (TCP handshake, DNS resolution, HTTP/2 streams), data structures (B-trees, hash maps, bloom filters), ML concepts (backpropagation, attention mechanism, gradient descent), or any algorithmic/engineering process. Also trigger when the user says "show me how X works", "animate X", "interactive explainer for X", or wants to turn a technical concept into a presentation-ready visual. This skill produces polished, interactive artifacts — not static diagrams.
paid-ads-linkedin
by nowork-studio
Audit, diagnose, plan, and safely operate connected LinkedIn Ads accounts through the NotFair MCP, with an export-based fallback. Use for LinkedIn advertising, sponsored content, lead-generation forms, job-title or company targeting, campaign groups, creatives, conversions, lead quality, budgets, bids, or approved LinkedIn campaign changes.
reliability-report
by hoangsonww
Generate a CCAM reliability report from session outcomes, hook events, alerts, tool failures, and data freshness. Use for health reviews, incident follow-up, hook-delivery audits, or reliability trend summaries.