Agent skills

Skills you can use with AI coding agents, indexed from public GitHub repositories.

Latest Most Popular

moai-essentials-perf Performance optimization with profiling, memory analysis, and benchmarking
majiayu000/claude-skill-registry 163
review-session Retrieval practice session to test retention on a topic. Use when user wants to test their knowledge, practice recall, quiz themselves, or check what they remember. Triggers on "quiz me", "test my knowledge", "review [topic]", "what do I remember".
majiayu000/claude-skill-registry 163
path-reference Create properly formatted references to paths (files or folders) in a git repository. Use when writing docs that need to link to any path in the repo.
majiayu000/claude-skill-registry 163
intermediate-example An intermediate example with metadata and examples
majiayu000/claude-skill-registry 163
cron-job-scheduler Cron Job Scheduler - Auto-activating skill for Backend Development. Triggers on: cron job scheduler, cron job scheduler Part of the Backend Development skill category.
majiayu000/claude-skill-registry 163
Build-Assistant Build Claude Code framework components (agents, slash commands, skills, plugins) following standardized templates. Use when creating new agents, commands, skills, or plugins for the multiagent framework.
majiayu000/claude-skill-registry 163
js-quality Interpretive guidance for JavaScript/TypeScript code quality using biome (modern) or eslint+prettier (traditional). Use when linting JS/TS files, configuring JS/TS tools, troubleshooting lint errors, or understanding tool selection.
majiayu000/claude-skill-registry 163
morph-search Fast codebase search via WarpGrep (20x faster than grep)
majiayu000/claude-skill-registry 163
pr-description-template PR description templates with format specifications and examples. Use when generating PR descriptions. Provides the complete PR structure and writing guidance.
majiayu000/claude-skill-registry 163
translation-reframing-audience-shift Use when content must be translated between audiences with different expertise, context, or goals while preserving accuracy but adapting presentation. Invoke when technical content needs business framing (engineering decisions → executive summary), strategic vision needs tactical translation (board presentation → team OKRs), expert knowledge needs simplification (academic paper → blog post, medical diagnosis → patient explanation), formal content needs casual tone (annual report → social media post), long-form needs summarization (50-page doc → 1-page brief), internal content needs external framing (roadmap → public updates, bug tracking → known issues), cross-cultural adaptation (US idioms → international clarity, Gen Z → Boomer messaging), medium shifts (written report → presentation script, detailed spec → action checklist), or when user mentions "explain to", "reframe for", "translate this for [audience]", "make this more [accessible/formal/technical]", "adapt for [executives/engineers/customers]", "simplify without losing accuracy", or "same content, different audience". Apply to technical communication (code → business value), organizational translation (strategy → execution), education (expert → novice), customer communication (internal → external), cross-cultural messaging, and anywhere same core message needs different presentation for different stakeholders while maintaining correctness.
majiayu000/claude-skill-registry 163
pseudobulkdeg Performs pseudo-bulk differential gene expression analysis using DESeq2 or edgeR. Aggregates single-cell counts to sample-level pseudo-bulk data, then identifies differentially expressed genes between conditions while accounting for biological replicates. Supports complex experimental designs including batch effects, paired samples, and interaction terms.
majiayu000/claude-skill-registry 163
spec-manager MANDATORY specification writing skill. ONLY way to create/update specs. Auto-invoke when: - Creating specs: New projects, features ("I want to create XX") - Updating specs: Feature additions, requirement changes, architecture updates - Syncing specs: Major code changes (3+ files), refactoring, session end - Keywords: specifications/spec/design/architecture/requirements/PRD Outputs to .spec-manager/. Critical rules and workflow details in skill body.
majiayu000/claude-skill-registry 163
cosmos-vulnerability-scanner Scans Cosmos SDK blockchains for 9 consensus-critical vulnerabilities including non-determinism, incorrect signers, ABCI panics, and rounding errors. Use when auditing Cosmos chains or CosmWasm contracts.
majiayu000/claude-skill-registry 163
automating-pages Automates Apple Pages using JXA with AppleScript dictionary discovery. Use when asked to "automate Pages documents", "create documents programmatically", "JXA Pages scripting", or "export Pages to PDF". Covers documents, templates, text, styles, export, tables, images, and AppleScript bridge fallbacks.
majiayu000/claude-skill-registry 163
imaging-data-commons Query and download public cancer imaging data from NCI Imaging Data Commons using idc-index. Use for accessing large-scale radiology (CT, MR, PET) and pathology datasets for AI training or research. No authentication required. Query by metadata, visualize in browser, check licenses.
majiayu000/claude-skill-registry 163
voice-processing Voice cloning workflows, voice library management, audio format conversion, and voice settings. Use when cloning voices, managing voice libraries, processing audio for voice creation, configuring voice settings, or when user mentions voice cloning, instant cloning, professional cloning, voice library, audio processing, voice settings, or ElevenLabs voices.
majiayu000/claude-skill-registry 163
python-data-classes Use when Python data modeling with dataclasses, attrs, and Pydantic. Use when creating data structures and models.
majiayu000/claude-skill-registry 163
thinking-map-territory Recognize limits of mental models and diagrams. Use when models diverge from reality, debugging expectation mismatches, or questioning abstraction accuracy.
majiayu000/claude-skill-registry 163
word-tracker Comprehensive word counting and tracking system for authors - track word counts across documents, monitor writing progress, and generate detailed analytics for markdown-based writing projects.
majiayu000/claude-skill-registry 163
apply-all-findings Use after code review - implement ALL findings; any finding not fixed MUST have tracking issue created; no finding disappears without trace
majiayu000/claude-skill-registry 163
training-patterns Templates and patterns for common ML training scenarios including text classification, text generation, fine-tuning, and PEFT/LoRA. Provides ready-to-use training configurations, dataset preparation scripts, and complete training pipelines. Use when building ML training pipelines, fine-tuning models, implementing classification or generation tasks, setting up PEFT/LoRA training, or when user mentions model training, fine-tuning, classification, generation, or parameter-efficient tuning.
majiayu000/claude-skill-registry 163
learning-design-review Review educational content against the Four Learning Design Pillars framework. Use when users want to evaluate course materials, lessons, tutorials, e-learning modules, or any instructional content for alignment with evidence-based learning design principles. Provides structured feedback with specific principle references (e.g., 1.1.1, 2.3.4) and actionable recommendations.
majiayu000/claude-skill-registry 163
acc-create-mock-repository Generates InMemory repository implementations for PHP 8.5 testing. Creates fake repositories with array storage, supporting CRUD operations and queries without database.
majiayu000/claude-skill-registry 163
py-alembic-patterns Alembic migration patterns for PostgreSQL. Use when creating migrations, reviewing autogenerated migrations, or handling schema changes safely.
majiayu000/claude-skill-registry 163