Agent skills
Skills you can use with AI coding agents, indexed from public GitHub repositories.
-
optimization-vuralserhat86-antigravity-agentic--2
majiayu000/claude-skill-registry 163
-
moai-core-issue-labels
Enterprise GitHub issue labeling orchestrator with semantic label taxonomy, AI-powered auto-labeling, label hierarchy system, workflow automation, issue triage acceleration, and stakeholder communication; activates for issue classification, label management, workflow automation, priority assignment, and team communication
majiayu000/claude-skill-registry 163
-
write-e2e-tests
Writing Playwright E2E tests for tldraw. Use when creating browser tests, testing UI interactions, or adding E2E coverage in apps/examples/e2e or apps/dotcom/client/e2e.
majiayu000/claude-skill-registry 163
-
create-storyboard
Transform screenplay output from /create-story into animatics with camera framing, visual panels, and timing. Highly collaborative - the skill acts as a creative cinematographer, making suggestions and asking questions throughout the process. Integrates with /memory for learned techniques.
majiayu000/claude-skill-registry 163
-
resolve-conflict
Resolve disagreements between security and architecture reviews conservatively.
majiayu000/claude-skill-registry 163
-
recursive-refiner
Self-improvement engine. Implements generate-critique-iterate loops for enhanced reasoning. Use when working through complex problems, synthesizing across domains, or when initial output needs refinement. Integrates with ego-check to prevent runaway confidence. Maximum 3 iterations to conserve tokens.
majiayu000/claude-skill-registry 163
-
extract-images
Extract and catalog illustrations from historical books using AI vision. Generates rich metadata (subjects, figures, symbols, style, technique) and museum-style descriptions. Use when asked to extract images, run image detection, or process book illustrations.
majiayu000/claude-skill-registry 163
-
data-lake-platform
Data lake and lakehouse platform patterns: ingestion/CDC, transformations, open table formats (Iceberg/Delta/Hudi), query and serving engines (Trino/ClickHouse/DuckDB), orchestration, governance/lineage, cost and operations. Self-hosted and cloud options.
majiayu000/claude-skill-registry 163
-
weaviate-data-ingestion
Upload and process data into local Weaviate collections with support for single objects, batch uploads, and multi-modal content
majiayu000/claude-skill-registry 163
-
seamless
Enables Claude to browse restaurants and track orders on Seamless (Grubhub)
majiayu000/claude-skill-registry 163
-
check-mentions
Slack で自分へのメンションを確認する。「メンション確認」「Slackメンション」「自分へのメンション」「@mention を見せて」などで起動。Pythonスクリプト `slack_message.py mentions` を使用。
majiayu000/claude-skill-registry 163
-
seo-review
Perform a focused SEO audit on JavaScript concept pages to maximize search visibility, featured snippet optimization, and ranking potential
majiayu000/claude-skill-registry 163
-
fusion-api
Design and compare alternative API shapes; use when deciding on endpoints, request or response formats, or versioning.
majiayu000/claude-skill-registry 163
-
gh-address-comments
Help address review/issue comments on the open GitHub PR for the current branch using gh CLI; verify gh auth first and prompt the user to authenticate if not logged in.
majiayu000/claude-skill-registry 163
-
pytorch-model-cli
Guidance for implementing CLI tools that perform inference using PyTorch models in native languages (C/C++/Rust). This skill should be used when tasks involve extracting weights from PyTorch .pth files, implementing neural network forward passes in C/C++, or creating standalone inference tools without Python dependencies.
majiayu000/claude-skill-registry 163
-
design-tool-picker
Help choose the right design tool based on your current task. Use when unsure whether to use frontend-design, ui-ux-designer, visual-validator, or ui-code-auditor.
majiayu000/claude-skill-registry 163
-
csv-parser
Parse and analyze CSV files with data validation
majiayu000/claude-skill-registry 163
-
uv-scripts
Use when running or authoring standalone Python scripts with uv, especially when choosing Python versions, adding one-off dependencies, using no-project mode, or embedding inline script metadata.
majiayu000/claude-skill-registry 163
-
git-workflow
Git 版本控制与协作专家，涵盖 GitHub/Gitee 平台操作、Conventional Commits 规范及 PR/MR 最佳实践。
majiayu000/claude-skill-registry 163
-
Research Ladder (right-sized depth)
A tiered approach to answering research questions with clear stop rules, evidence capture, and escalation to Tavily/Playwright only when needed.
majiayu000/claude-skill-registry 163
-
ghostwriter
Master the art of converting source material into authentic, human-written content. Transform transcripts, notes, and research into polished prose that avoids AI tells while maintaining distinctive voice. Combines anti-AI writing fundamentals with voice style adaptation.
majiayu000/claude-skill-registry 163
-
astro-cta-injector
Inject Call-to-Action blocks into Astro site content with intelligent placement strategies. Use when the user wants to add CTAs, newsletter signups, product promotions, or any content blocks to blog posts. Supports multiple placement strategies (end, after 50%, after 60%), content scoring for relevance, and dry-run preview.
majiayu000/claude-skill-registry 163
-
skills-managing
Create and manage ASE skills following best practices. Use when creating new skills, importing skills, understanding the Registry V3.1 structure, or debugging skill activation.
majiayu000/claude-skill-registry 163
-
playwright-skill
Complete browser automation with Playwright. Auto-detects dev servers, writes clean test scripts to /tmp. Test pages, fill forms, take screenshots, check responsive design, validate UX, test login flows, check links, automate any browser task. Use when user wants to test websites, automate browser interactions, validate web functionality, or perform any browser-based testing.
majiayu000/claude-skill-registry 163