Skill Creator
majiayu000
6838 published skills · 19,665 GitHub stars across the catalog. View on GitHub ↗
collaboration-hub
Develop and modify the AILANG Collaboration Hub UI. Use when user asks to add features to the monitoring dashboard, modify the approval queue, update the message center, or make changes to the React frontend.
audit-coordinator
Orchestrates comprehensive audits across multiple specialized auditors for Claude Code customizations and provides guidance on naming, organization, best practices, and troubleshooting. Use when: (1) Auditing - wants complete evaluation, multi-faceted analysis, coordinated audit reports, thorough validation, or asks to audit multiple components; (2) Guidance - asks "what should I name...", "how should I organize...", "best practices for...", troubleshooting issues, understanding evaluation criteria, or needs pre-deployment validation. Automatically determines which auditors to invoke (agent-audit, skill-audit, hook-audit, command-audit, output-style-audit, evaluator, test-runner) based on target type and compiles unified reports with consolidated recommendations.
session-log-fixer
Fix session protocol validation failures in GitHub Actions. Use when a PR fails with "Session protocol validation failed", "MUST requirement(s) not met", "NON_COMPLIANT" verdict, or "Aggregate Results" job failure in the Session Protocol Validation workflow. With deterministic validation, failures show exact missing requirements directly in Job Summary - no artifact downloads needed.
command-authoring
Guide for authoring, creating, writing, building, reviewing, or improving slash commands that delegate to agents or skills. Use when designing /commands for user shortcuts, fixing existing commands, or learning command best practices. Helps design simple command files, choose delegation targets, handle arguments, and decide when to use commands vs skills. Also triggers when asking how to create commands, whether to use a command vs skill, or understanding command patterns. Expert in command patterns, best practices, and keeping commands focused.
coolify-deploy
Deploy to Coolify with best practices
oracle-gemini
This skill should be used when the user asks to "use Gemini", "ask Gemini", "consult Gemini", "Gemini review", "use Gemini for planning", "ask Gemini to review", "get Gemini's opinion", "what does Gemini think", "second opinion from Gemini", mentions using Gemini as an oracle for planning or code review. NOT for implementation tasks.
hook-audit
Comprehensive audit of Claude Code hooks for correctness, safety, and performance. Use when reviewing, validating, or debugging hooks, checking JSON stdin handling, verifying exit codes (0=allow, 2=block), analyzing error handling, fixing hook failures, ensuring safe degradation, optimizing performance, or validating settings.json registration. Also triggers when user asks about hook best practices, wants to create a new hook, or needs help with hook configuration.
vendure
Vendure e-commerce framework for Node.js. Use for headless commerce, GraphQL APIs, order management, product catalogs, payment integration, and TypeScript e-commerce development.
editing-assistant
Comprehensive text editing and improvement assistant with multiple specialized modes. Use when editing, improving, proofreading, polishing, reviewing, rewriting, or cleaning up written content. Supports fixing typos and grammar errors, checking grammar, correcting mistakes, improving flow and readability, adding punctuation, restructuring with headings, adding examples, citing sources, fact-checking, and preserving detail. Handles spelling, grammar, structure, citations, accuracy improvements, and formatting. Works with documentation, articles, markdown files, and any written content.
documenting-apis
Generate API specification documentation from codebase analysis. Detects REST endpoints, function signatures, type definitions, and schemas. Triggers: API specification, endpoints, REST API, type definitions, OpenAPI, Swagger, API documentation.
matlab-live-script
Create MATLAB plain text Live Scripts (.m files) following specific formatting rules. Use when generating MATLAB scripts, educational MATLAB content, Live Scripts, or when the user requests .m files with rich text formatting.
hammer-quality-check
Runs comprehensive code quality checks for SDL3 HammerEngine including compilation warnings, static analysis (cppcheck), coding standards validation, threading safety verification, and architecture compliance. Use before commits, pull requests, or when the user wants to verify code meets project quality standards.
introspect
Soul self-examination (Svadhyaya). Use when diagnosing performance, finding improvements, or examining wisdom health.
new-skill-wizard
Creates a new skill in the Powerhouse Lab skills library with proper git workflow. Use when the user wants to create a new skill, add a skill, build a skill, or says "new skill called X".
pr-review
Manage GitHub PR review comments - fetch, resolve, dismiss, and interact with PR review threads. Handles comment detection, fetching, resolution, and dismissal with reasons. Use when: (1) Working on a PR with review comments, (2) Need to fetch and review PR feedback, (3) Want to resolve comments after making fixes, (4) Need to dismiss comments that are not applicable, (5) Managing PR comment files, (6) When GitHub PR comments need to be processed, (7) When working with pull requests that have received feedback, (8) For PR workflow automation and comment organization, or (9) For GitHub API integration and PR management. Triggers: PR comments, review comments, fetch PR feedback, resolve comment, dismiss comment, PR review, pull request comments, handle review feedback, get PR comments, manage PR comments.
ct
Guide for using the ct (CommonTools) binary to interact with charms, recipes, and the Common Fabric. Use this skill when deploying recipes, managing charms, linking data between charms, or debugging recipe execution. Triggers include requests to "deploy this recipe", "call a handler", "link these charms", "get data from charm", or "test this recipe locally".
swarm
Multi-perspective reasoning through Upanishadic Antahkarana voices. Use for complex problems requiring diverse viewpoints and synthesis.
bash-scripting
Master of defensive Bash scripting for production automation, CI/CD pipelines, and system utilities. Expert in safe, portable, and testable shell scripts. Use when writing, creating, authoring, generating, or developing bash scripts, shell scripts, or automation. Also triggers for learning bash best practices, understanding defensive programming patterns, implementing error handling, ensuring portability, following shellcheck recommendations, or applying production-grade bash standards. Helps with CI/CD scripts, system utilities, deployment automation, and production bash code.
hammer-benchmark-regression
Runs performance benchmarks for SDL3 HammerEngine and detects regressions by comparing metrics against baseline. Use when testing performance-sensitive changes to AI, collision, pathfinding, particle systems, or before merging features to ensure no performance degradation.
skill-audit
Audits skills for discoverability and triggering effectiveness. Use when analyzing skill descriptions, checking trigger phrase coverage, validating progressive disclosure, reviewing SKILL.md structure, ensuring skill discoverability, testing skill triggering, improving skill descriptions, fixing skills that aren't being invoked, debugging discovery issues, or evaluating whether a skill will be invoked appropriately. Also triggers when user asks about skill best practices, wants to improve skill discoverability, or needs help with skill structure.
sdd-methodology
Use when explaining or applying Spec-Driven Development workflow, guiding through SDD phases, or helping with workflow decisions. Invoked for methodology guidance, workflow optimization, and best practices.
subagent-prompting
Apply instruction-engineering to all subagent prompts. Use BEFORE invoking the Task tool, spawning agents, or dispatching parallel workers. Ensures subagents receive persona-driven, research-backed prompts that maximize compliance and output quality. Triggers on: "use a subagent", "spawn agent", "dispatch", "Task tool", parallel agent work, or any multi-agent orchestration.
newsletter-coach
Writing coach that extracts educational content from your daily experiences and turns it into publish-ready newsletter drafts. Use when brainstorming newsletter ideas, writing content for The Little Blue Report, or when you want help turning experiences into educational articles.
analyzing-root-causes
Root cause analysis with 5 Whys methodology for software problems. Triggers: 根本原因, root cause, 5 Whys, なぜなぜ分析, 対症療法, patch, symptom, 症状, 表面的, workaround, ワークアラウンド, 本質的, 応急処置, bandaid, quick fix.