分析
分析、报表与可视化
glyph
yonatangross
"Render an answer as ASCII art plus semantic emojis inline, right now, with no setup questions. Use for a fast visual take on status, comparisons, trade-offs, architecture, or any ad-hoc 'show me X visually' ask. For a full multi-artifact plan playground, use visualize-plan instead."
okr-design
yonatangross
"OKR trees, KPI dashboards, North Star Metric, leading/lagging indicators, and experiment design. Use when setting team goals, defining success metrics, building measurement frameworks, or designing A/B experiment guardrails."
grace-refresh
osovv
"Synchronize the GRACE knowledge graph with the actual codebase. Use after manual code changes, refactoring, or when you suspect drift between the knowledge graph and the code — scans all source files, detects missing/orphaned modules and stale CrossLinks, and proposes fixes."
taffybar-ecosystem-release
colonelpanic8
Use when releasing, version-bumping, or propagating changes across taffybar GitHub org packages (taffybar, gtk-sni-tray, gtk-strut, status-notifier-item, dbus-menu, dbus-hslogger)
complete-plan
openakita
Mark the plan as completed and generate a summary report. Call when ALL steps are done. Returns execution summary with success/failure statistics.
bio-atac-seq-atac-qc
GPTomics
Quality control metrics for ATAC-seq data including fragment size distribution, TSS enrichment, FRiP, and library complexity. Use when assessing ATAC-seq library quality before or after peak calling to identify problematic samples.
bio-alignment-validation
GPTomics
Validate alignment quality with insert size distribution, proper pairing rates, GC bias, strand balance, and other post-alignment metrics. Use when verifying alignment data quality before variant calling or quantification.
bio-chipseq-differential-binding
GPTomics
Differential binding analysis using DiffBind. Compare ChIP-seq peaks between conditions with statistical rigor. Requires replicate samples. Outputs differentially bound regions with fold changes and p-values. Use when comparing ChIP-seq binding between conditions.
bio-causal-genomics-pleiotropy-detection
GPTomics
Detect and correct for horizontal pleiotropy in Mendelian randomization analyses using MR-PRESSO for outlier removal, MR-Egger regression for directional pleiotropy, and Steiger filtering for variant directionality. Use when validating MR results, detecting pleiotropic instruments, or running sensitivity analyses for causal inference.
data-pipeline
jmagly
Data dictionary: .aiwg/marketing/data/dictionary.md
regression-report
jmagly
@agentic/code/frameworks/sdlc-complete/agents/metrics-analyst.md
sdlc-reports
jmagly
Dashboard guide: docs/dashboard-configuration.md
performance-digest
jmagly
Benchmark data: .aiwg/marketing/benchmarks/
Workspace Health Check Skill
jmagly
/check-traceability - Verify requirement links
grace-reviewer
osovv
"GRACE integrity reviewer. Use when validating semantic markup correctness, contract completeness, knowledge graph consistency, or after code changes to ensure GRACE conventions are maintained."
grace-execute
osovv
"Execute the full GRACE development plan step by step, generating code for each pending module with validation and commits. Use when the architecture is planned and you want to generate all modules sequentially with review checkpoints."
market-session-tracker
Innei
Use when monitoring stocks/ETFs/indices across pre-market, open, intraday, or close — especially when the user is reading session action live and may revise their take as it unfolds. Triggers include 盘前/盘中/收盘 sessions, multi-symbol watchlists (e.g. MU/TSM/SMH semi tracking), user observations like "突破"/"冲高"/"回调"/"假突破", capital flow checks, market temperature checks, semi/AI/memory plays, and any request that bundles a position context with a live read.
weekly-analytics
NeverSight
Weekly analytics report combining GA4, Google Search Console, and Microsoft Clarity into a premium HTML email. Use for automated Sunday cron jobs that generate weekly product analytics reports. Tracks users, sessions, pageviews, SEO performance (queries, impressions, CTR, position), UX friction (dead clicks, rage clicks, quickbacks), and week-over-week trends. Includes accountability tracking (did we do what we said?), prioritized recommendations with impact/effort ratings, and actionable checklists. Persona: $15K/month SEO consultant. Outputs: HTML email + chat summary.
metric-reconciliation
nimrodfisher
Cross-source metric validation and discrepancy investigation. Use when metrics from different sources don't match, investigating data quality issues between systems, or validating data migration accuracy.
root-cause-investigation
nimrodfisher
Systematic investigation of metric changes and anomalies. Use when a metric unexpectedly changes, investigating business metric drops, explaining performance variations, or drilling into aggregated metric drivers.
dashboard-specification
nimrodfisher
Design specifications for effective dashboards. Use when planning new dashboards, improving existing ones, or documenting dashboard requirements before development.
grace-status
osovv
"Show the current health status of a GRACE project. Use to get an overview of project artifacts, codebase metrics, knowledge graph health, and suggested next actions — helps identify drift, missing contracts, or unpaired semantic blocks."
grace-explainer
osovv
"Complete GRACE methodology reference. Use when explaining GRACE to users, onboarding new projects, or when you need to understand the GRACE framework — its principles, semantic markup, knowledge graphs, contracts, and unique tag conventions."
report-generation
apconw
生成数据分析报告：查询数据 → 深度分析归因 → 输出 HTML 可视化报告