分析
分析、报表与可视化
analytics-tracking
freekmurze
When the user wants to set up, improve, or audit analytics tracking and measurement. Also use when the user mentions "set up tracking," "GA4," "Google Analytics," "conversion tracking," "event tracking," "UTM parameters," "tag manager," "GTM," "analytics implementation," or "tracking plan." For A/B test measurement, see ab-test-setup.
data-visualization
cosmix
Creates effective data visualizations, charts, dashboards, and reports across analytics, infrastructure monitoring, and ML domains. Covers library selection, UX design, and accessibility. Trigger keywords: chart, graph, plot, dashboard, report, visualization, matplotlib, plotly, d3, seaborn, grafana, tableau, superset, metabase, KPI, metric, analytics, histogram, heatmap, time-series, scatter, bar-chart.
bazi-mingli
Wolke
"八字命理 (Bazi / Four Pillars of Destiny) divination skill. Use when users request birth chart analysis, fortune telling based on birth date/time, or Chinese astrology. Triggers on: 八字, 四柱, 命盤, 排盤, 算命, 命理, 生辰八字, 天干地支, 五行, 流年, 大運, bazi, four pillars, Chinese astrology, birth chart."
memory-systems
guanyang
Guides implementation of agent memory systems, compares production frameworks (Mem0, Zep/Graphiti, Letta, LangMem), and designs persistence architectures for cross-session knowledge retention. Use when the user asks to "implement agent memory", "persist state across sessions", "build knowledge graph for agents", "track entities over time", "add long-term memory", "choose a memory framework", or mentions temporal knowledge graphs, vector stores, entity memory, or memory benchmarks (LoCoMo, LongMemEval).
wechat-daily-report
leonense22
微信群聊天记录日报图片生成工具。分析微信群聊天记录，结合 AI 生成内容，最终输出为手机端分辨率的日报长图（PNG）。
k8s-helm
rohitg00
Manage Helm charts, releases, and repositories. Use for Helm installations, upgrades, rollbacks, chart development, and release management.
grafana
cosmix
Observability visualization with Grafana and LGTM stack. Dashboard design, panel configuration, alerting, variables/templating, and data sources. USE WHEN: Creating Grafana dashboards, configuring panels and visualizations, writing LogQL/TraceQL queries, setting up Grafana data sources, configuring dashboard variables and templates, building Grafana alerts. DO NOT USE: For writing PromQL queries (use /prometheus), for alerting rule strategy (use /prometheus), for general observability architecture (use senior-software-engineer with infrastructure focus). TRIGGERS: grafana, dashboard, panel, visualization, logql, traceql, loki, tempo, mimir, data source, annotation, variable, template, row, stat, graph, table, heatmap, gauge, bar chart, pie chart, time series, logs panel, traces panel, LGTM stack.
bk-monitor-weekly-report
TencentBlueKing
通过 GitHub MCP 获取用户 PR 并生成周报。当用户提到生成周报、写周报时使用。
feature-verify
sd0xdev
"Feature verification (READ-ONLY). Use when: verifying feature behavior, validating data integrity, confirming system state. Not for: modifying data (use feature-dev), code review (use codex-code-review). Output: verification report + confidence assessment."
codex-brainstorm
sd0xdev
"Adversarial brainstorming via Claude+Codex debate. Use when: exploring solutions, feasibility analysis, exhaustive enumeration. Not for: implementation (use feature-dev), architecture only (use codex-architect). Output: Nash equilibrium consensus + action items."
code-investigate
sd0xdev
"Dual-perspective code investigation. Use when: deep code analysis needing both Claude and Codex perspectives. Not for: quick exploration (use code-explore), code review (use codex-code-review). Output: integrated findings from dual analysis."
git-investigate
sd0xdev
"Git history investigation. Use when: tracking code changes, finding where bugs were introduced, root cause analysis. Not for: code exploration (use code-explore), issue analysis (use issue-analyze). Output: history trace + root cause report."
issue-analyze
sd0xdev
"GitHub Issue deep analysis. Use when: analyzing issue root cause, classifying problems, investigation planning. Not for: fixing bugs (use bug-fix), code exploration (use code-explore). Output: classified analysis + investigation strategy."
代码评审专家
TencentBlueKing
基于 Google Code Review 指南的代码评审技能
implement-plan
steveclarke
Execute implementation plans incrementally with verification at each step. Works through numbered sections one at a time, sanity-checks assumptions against the codebase, and stops on inconsistencies. Use when implementing a pre-defined plan document. Triggers on "implement this plan", "execute step 3.1", "resume plan at section 4".
pentest-evidence-structuring-report-synthesis
crtvrffnrt
"Security assessment skill for structuring evidence, deduplicating findings, and producing decision-ready security reports. Use when prompts include write report, consolidate findings, severity ranking, remediation guidance, executive summary, or technical appendix generation. Do not use for live exploit execution, reconnaissance, or payload experimentation tasks."
pentest-business-logic-abuse
crtvrffnrt
"Security assessment skill for business workflow abuse, state-machine manipulation, and control-plane logic flaws. Use when prompts include workflow bypass, race condition, replay, quota abuse, order-of-operations flaws, delegated execution abuse, or unauthorized state transitions. Do not use for pure input injection fuzzing, broad recon, or standalone report formatting tasks."
fiftyone-embeddings-visualization
voxel51
Visualizes datasets in 2D using embeddings with UMAP or t-SNE dimensionality reduction. Use when exploring dataset structure, finding clusters, identifying outliers, or understanding data distribution.
route-researcher
dreamiurg
Research North American mountain peaks and generate comprehensive route beta reports
stat-writing
fuhaoda
End-to-end statistical writing assistant for LaTeX - draft title/abstract/keywords, expand outlines into sections, audit manuscripts, write reviewer reports and response letters, and scaffold book manuscripts.
improve-codebase-architecture
eltmon
Scan a codebase for deepening opportunities, present them as a visual HTML report, then grill through whichever one you pick.
flow-next-prime
gmickel
Comprehensive codebase assessment for agent and production readiness. Scans 8 pillars (48 criteria), verifies commands work, checks GitHub settings. Reports everything, fixes agent readiness only. Triggers on /flow-next:prime.
loop
saadshahd
Start autonomous iteration loop. Triggers on "loop", "keep going", "continue until done", "implement feature", "fix all", "loop status", "cancel loop".
remove-dead-code
qdhenry
Safely identifies and removes dead code in TypeScript/JavaScript projects using multi-agent analysis with automatic backup branches. Use when cleaning up unused exports, orphaned files, dead imports, unreachable functions, or unused dependencies.