分析
分析、报表与可视化
grafana-dashboard-design
taptap
创建/修改 Grafana Dashboard 时触发，提供专业的设计规范。
cursor-rules-writing
meriley
Create Cursor IDE rules in .mdc format with proper frontmatter, glob patterns, and cross-references. Covers rule structure, file organization, triggering mechanisms, and quality standards. Use when creating or modifying Cursor rules for context injection.
Hoshinkanri
robdtaylor
Strategic policy deployment system for automotive manufacturing. Cascades Group-level targets to shop floor through X-Matrix, catchball process, and bowling chart tracking. USE WHEN user says 'hoshin', 'x-matrix', 'catchball', 'bowling chart', 'strategy deployment', 'cascade objectives', 'breakthrough objectives', 'strategic planning', 'policy deployment', or requests help with annual planning integration. Integrates with IATF 16949 quality systems and AutomotiveManufacturing skill for work instruction cascade.
helm-chart-expert
meriley
Production-ready Helm chart creation and review guide. Covers chart structure, ArgoCD/GitOps integration, secrets management, testing strategies, deployment patterns (blue-green, canary), monitoring, and troubleshooting. Use when creating charts, reviewing for security/quality, integrating with ArgoCD, or debugging chart issues.
gap-analysis
jschulte
Route-aware gap analysis. For Brownfield - uses /speckit.analyze to compare specs against implementation. For Greenfield - validates spec completeness and asks about target tech stack for new implementation. This is Step 4 of 6 in the reverse engineering process.
soc-operations
SherifEldeeb
Security Operations Center workflows, alert triage, shift handovers, and operational reporting. Automate SOC documentation and standardize processes. Use for SOC-related tasks, alert management, and operational metrics.
pptx
SherifEldeeb
Read, modify, and create Microsoft PowerPoint presentations (.pptx). Generate slides from content, apply templates, and build executive presentations. Use when creating presentations or converting content to slides.
incident-postmortem
LKB-99
"Conduct detailed post-mortem analysis of incidents, including root cause analysis (RCA). Use this skill when users need to analyze a service outage, data breach, or any system failure. Triggers: post-mortem, postmortem, incident analysis, root cause analysis, RCA, outage, service down, system failure, after-action report, AAR, análise de incidente, causa raiz."
sleep-analyzer
LKB-99
"Use this skill when users want to analyze their sleep data, understand sleep patterns, or get personalized recommendations to improve sleep quality. Triggers: sleep analysis, sleep data, sleep quality, sleep patterns, sleep hygiene, sleep tracker, improve sleep, sono, análise de sono, qualidade do sono, melhorar o sono."
langgraph-graph-api
evanfang0054
使用 StateGraph、节点、边、START/END 节点和 Command API 构建图，结合控制流与状态更新
state-estimator-evaluate-bags
Idate96
"Evaluate the Moleworks ROS2 mole_estimator on recorded MCAP/rosbag2 datasets: replay _sensors bags through the estimator (use_sim_time), record a reprocessed eval bag with /mole/state + /graph_msf/, run the offline analyzer, and generate a per-bag metrics markdown + summary table for tuning turn-joint filtering and base velocity smoothness."
langgraph-memory
evanfang0054
LangGraph 中的内存：短期（线程范围）vs 长期（跨线程）内存，使用检查点器和存储
@tank/token-redaction
tankpkg
"Detect and redact API tokens, keys, bearer values, and JWTs in local OpenCode SQLite session stores. Covers backup-first workflow, pattern matching for common token formats, dry-run verification, database integrity checks, and session cleanup. Triggers: redact, token, API key, secret, JWT, bearer, session store, SQLite, cleanup, sensitive data, credential leak, key rotation, security."
load
laststance
Load project context from Serena MCP memory for session initialization. Discovers memories, reads project overview and critical rules, and validates context sufficiency. Portable across all Serena-enabled agents (Claude Code, Cursor, Windsurf, etc.). Use when: starting a session, resuming work, or needing project context. Keywords: session, load, initialize, context, memory, restore, resume
linear-workflow
srobinson
"INVOKE THIS SKILL before creating any Linear issues. Required when creating issues, planning features, breaking down work, or organizing tasks in Linear. Enforces parent/sub-issue pattern, proper sizing, and metadata conventions."
langgraph-state
evanfang0054
在 LangGraph 中管理状态：模式、reducer、通道和消息传递，用于协调 Agent 执行
product-design
Semprini
Design and declare MD-DDL data products from an existing domain model. Use when the user wants to create, update, or review data product declarations — choosing product class, schema type, entity scope, governance overrides, masking strategies, cross-domain references, or SLA. Also use when populating the domain file Data Products summary table.
code-quality-report
khanhuitse05
Produces structured code quality assessment reports for Frontend (Mobile & Web) or Backend codebases (IEEE 730/1016/829, Clean Code, OWASP). Use when the user asks for a code quality report, quality assessment, codebase review, or wants a report for frontend vs backend or mobile vs web vs backend.
langgraph-persistence
evanfang0054
在 LangGraph 中实现持久化和检查点：保存状态、恢复执行、线程 ID 和检查点器库
langgraph-interrupts
evanfang0054
人机交互与动态中断和断点：暂停执行以供人工审查和使用 Command 恢复
knowledge-graph
Semprini
Use this skill when the user asks to generate a knowledge graph, graph database schema, Cypher DDL, or Neo4j model from an MD-DDL domain. Also use when the user wants to realize MD-DDL entities, relationships, events, and enums as labeled property graph structures.
@tank/web-analytics-consent
tankpkg
"Privacy-compliant web analytics and cookie consent. Covers tool selection
research-spike
gpu-cli
"Conducts time-boxed technical investigations, competitive research, or feasibility analysis. Asks clarifying questions upfront and produces a structured markdown report with executive summary. Use for technical spikes, architecture decisions, or evaluating new technologies."
thegraph
hairyf
The Graph — subgraph manifest, schema, mappings, GraphQL API, templates, Substreams, and performance practices for agent-driven indexing.