Analytics
Data analysis and visualization
dough-story-refinement
by terryyin
Clarifies selected stories before execution planning by establishing goal, scope, and key examples in each story's seed, distinguishing promises from rejection constraints. Adds UI or architectural detail only when needed. Continues a ready story into slice planning in the same workspace; --refine-only stops at the refined story. --one-shot refines a queued story without publishing an assignment and keeps the result for review, or lands it with --auto-land. Use for selected-story refinement, not broad problem decomposition, candidate selection, or slice sizing.
dough-resplit-story
by terryyin
Resplits a large story after slice-plan refinement into smaller stories and mapped slice plans. Use when resplitting is requested, including after a more-than-15-slices recommendation. Leaves the first story and plan refined; later plans await story refinement and backlog priorities are reconsidered.
refresh-architecture
by jankneumann
Refresh architecture analysis artifacts (docs/architecture-analysis/) from the codebase
data-analyst
by k1lgor
Use this for exploratory data analysis (EDA), generating visualizations, finding trends, and deriving insights from datasets using Python (Pandas/Seaborn/Plotly) or SQL.
dough-story-refinement
by terryyin
Clarifies selected stories before execution planning by establishing goal, scope, and key examples in each story's seed, distinguishing promises from rejection constraints. Adds UI or architectural detail only when needed. Continues a ready story into slice planning in the same workspace; --refine-only stops at the refined story. --one-shot refines a queued story without publishing an assignment and keeps the result for review, or lands it with --auto-land. Use for selected-story refinement, not broad problem decomposition, candidate selection, or slice sizing.
validate-flows
by jankneumann
"Architecture flow validation for cross-layer interactions"
nsys
by spcl
What the NVIDIA device trace from profile returns for a cuda submission (tool nsys), what it cannot answer, and what each refusal means.
nextdns-api
by tuanductran
NextDNS API integration best practices for authentication, profile management, analytics, logs,
aio-code-review
by aiocean
Ultimate code review with multi-phase pipeline. Triggers when user says "review code", "code review", "review this", "review changes", "review PR", "ultra review", or mentions "comprehensive review". Runs domain-specific skills (Go, iOS, React, XState, observability), CodeWiki static analytics, 4 core + 4 conditional parallel review agents, and a critic meta-review with confidence scoring.
Sync Multi-Repo State
by Sounder25
Detects drift between multiple git repositories (e.g. forks, mirrors, or multi-module projects). Generates a drift report and optionally applies sync actions.
Detect Duplicate Files
by Sounder25
Identify duplicate files across the workspace using SHA256 hashing to reduce redundancy and confusion.
infra-ops
by TinyAssets
Drives domain, DNS, SSL, and Cloudflare/GoDaddy admin for the TinyAssets public surfaces. Use when changing DNS records, nameservers, Cloudflare Workers/routes/tokens, GoDaddy domain or Websites+Marketing settings, or doing emergency DNS routing.
starter-workspace
by TinyAssets
Inspect current workspace state, build UI, deliver files and arrange ongoing work.
coinversaa-pulse
by Coinversaa
"Crypto intelligence for AI agents. 26 tools for Hyperliquid trader analytics, behavioral cohorts, live market data, liquidation heatmaps, and whale tracking across 710K+ wallets and 1.8B+ trades."
meta-ads-analyzer
by Synero
"Analyze Facebook/Instagram Ads campaigns via Meta Marketing API. Get campaign data, performance metrics, and insights directly from your ad account."
capabilities
by TinyAssets
Run tests, deliver files and notify the owner from chat or scheduled work.
wemp-operator
by IanShaw027
"微信公众号自动化运营。触发词：采集热点、公众号日报、周报、检查评论、回复评论、生成文章。依赖 wemp skill。"
czsc-ccxt-analysis
by Lzh-xbccz
"缠论技术分析 — czsc官方全API，CCXT数据源，多级别联立，lightweight-charts可视化+自动Markdown报告。触发: 缠论/czsc/中枢/分型/笔"
review-loop
by ahmadzayan-hub
Run a deliverable or a change through review rounds until it is 100% validated, meaning every gate passes or is accepted by a named person, or until the loop must stop and say why. Deterministic gates first, then specialist reviewer subagents in parallel, then fixes, then gates again. Use before submitting a report, deck, dashboard or clip, before a release, or when the user says "review until it passes", "validate everything" or "make sure it is 100%".
Traversing Citation Networks
by kthorn
Smart backward and forward citation following via Semantic Scholar, with relevance filtering and deduplication
tufte-slide-design
by ingpoc
This skill applies Edward Tufte's data visualization principles from "The Visual Display of Quantitative Information" to create high-impact slides. Use when designing presentations, creating charts/graphs, reviewing slides for clarity, or transforming data into visual displays. Triggers on phrases like "make a slide", "create presentation", "design chart", "visualize data", "review my slides", or "make this more impactful".
songsee
by magnusthovsland
"Audio spectrograms/features (mel, chroma, MFCC) via CLI."
prime
by slamb2k
Load project context before implementing features or making architectural decisions. Invoke proactively when starting significant work on DexAI. Supports domain-specific context loading: security (vault, RBAC, audit), routing (OpenRouter, model selection), adhd (design principles, RSD-safe), dashboard (frontend, backend, API), office (OAuth, email, calendar), memory (context capture, commitments), tasks (decomposition, friction-solving), channels (Telegram, Discord, Slack).
subagent-orchestration
by DimitriGilbert
Orchestrate multi-phase development workflows with strict role separation between implementers and validators. Automatically executes plans using separate subagents for implementation, validation, and fixing with auto-retry loops. Use when building complex systems requiring (1) Multi-step sequential or parallel development phases, (2) Automated validation with typecheck/build/tests after each phase, (3) Auto-retry fix loops until validation passes, (4) Complete execution after single user approval. Triggers include "implement this multi-phase plan", "build a system with phases", "create [complex system] following this architecture", "automate development workflow with validation", or any request for orchestrated development with multiple phases and quality checks. NOT for simple single-file tasks or exploratory coding.