Skill Creator
majiayu000
6838 published skills · 19,665 GitHub stars across the catalog. View on GitHub ↗
ml-model-explainer
Explain ML model predictions using SHAP values, feature importance, and decision paths with visualizations.
logging-standards
Zap logging standards for Go services. Use when writing, generating, or reviewing code that includes logging.
context-preservation-protocol-execution
Execute context preservation protocols for session continuity.
mindmap-skill
Maintain and evolve interactive mind maps generated from OPML outlines and XML palettes.
svelte5
Svelte 5 syntax reference. Use when writing ANY Svelte component. Svelte 5 uses runes ($state, $derived, $effect, $props) instead of Svelte 4 patterns. Training data is heavily Svelte 4—this skill prevents outdated syntax.
abm-specialist
Эксперт ABM. Используй для account-based marketing, target account selection и personalized campaigns.
database-management
Implement SQLite database patterns using the database.py interface with complete SQL isolation. MANDATORY for all database projects. Use when working with databases, data persistence, or SQLite.
spec-validator
Validates Spec-Driven Development artifacts for completeness, consistency, and quality. Use when checking specs, validating features, reviewing SDD artifacts, or ensuring spec quality before implementation.
video-clipper
Cut video segments by timestamp, split videos into chunks, trim start/end, and extract specific scenes with precise frame control.
managing-deployment
Deployment and infrastructure for the site. Consult when troubleshooting deployments, modifying CI/CD, or diagnosing build issues.
troubleshooting-kubernetes
Diagnoses and fixes Kubernetes issues with interactive remediation. Use when pods crash (CrashLoopBackOff, OOMKilled), services unreachable (502/503, empty endpoints), deployments stuck (ImagePullBackOff, pending). Also use when tempted to run kubectl fix commands directly without presenting options, or when user says "just fix it" for K8s issues.
readme-updater
更新 README.md。觸發:readme、說明、文檔、怎麼用、安裝說明。
two-stage-boundary-encounter-sop
Execute two-stage protocol for boundary condition encounters.
spring-reactive
Build reactive applications - WebFlux, Mono/Flux, R2DBC, backpressure, reactive streams
refactor-dedupe-and-cleanup
[Code Quality] Removes code duplication and cleans up dead code. Use to eliminate copy-paste code, consolidate similar logic, and remove unused code paths.
plugin-builder
Scaffold complete elizaOS plugins with actions, providers, evaluators, and services. Triggers when user asks to "create plugin", "build elizaOS extension", or "scaffold plugin structure"
professional-development-superskill
Comprehensive superskill consolidating 41 professional development skills across planning, testing, debugging, code review, git workflow, writing, architecture, meta-skills, thinking frameworks, and communication. Use when you need a complete reference for software development best practices, workflows, and methodologies.
data-storage
Implement client-side data storage with localStorage, IndexedDB, or SQLite WASM. Use when storing user preferences, caching data, or building offline-first applications.
linking-hms-to-hecras
Links HEC-HMS watershed models to HEC-RAS river models by extracting HMS DSS resultsand preparing them for RAS boundary condition import. Handles flow hydrograph export,spatial referencing (HMS outlets to RAS cross sections), DSS pathname formatting,quality validation, and time series alignment. Use when setting up HMS→RAS workflows,exporting HMS results for RAS, preparing upstream boundary conditions, or coordinatingwatershed-to-river integrated modeling. Leverages shared RasDss infrastructure forconsistent DSS operations across both tools.Trigger keywords: HMS to RAS, link HMS RAS, boundary condition, upstream BC, watershedto river, integrated model, export HMS, DSS pathname, spatial matching, hydrograph.
plan-adjuster
Recomputes upcoming workouts based on recent runs and user feedback. Use when recent performance deviates from plan, user provides negative feedback, or recovery signals indicate adjustment needed with deterministic safety caps.
graphql-schema-design
Design production-grade GraphQL schemas with best practices and patterns
claude-get-session-info
Shared utility script for getting Claude PID and Session ID. Source this in other scripts to access CLAUDE_PID and SESSION_ID variables.
compliance-report-builder
Эксперт по compliance отчётам. Используй для SOX, GDPR, HIPAA, SOC 2 аудитов и документации соответствия.
using-pixi
Guidance for developing under a projects managed by pixi. Always use when workspace managed by pixi (have pixi.toml or pixi.lock in root directory.) Covers all you should know while developing under a pixi-based project: pixi environment commands (install, run, shell, add, task), multi-environment management (-e flag, features), task configuration in pixi.toml, dependencies (conda vs PyPI), lock files, and development workflows. Helps with environment setup, package management, running tasks, debugging pixi.toml errors, and production deployment patterns.