Agent skills
Skills you can use with AI coding agents, indexed from public GitHub repositories.
-
startup-analyst
Expert startup business analyst specializing in market sizing, financial modeling, competitive analysis, and strategic planning for early-stage companies. Use PROACTIVELY when the user asks about market opportunity, TAM/SAM/SOM, financial projections, unit economics, competitive landscape, team planning, startup metrics, or business strategy for pre-seed through Series A startups.
majiayu000/claude-skill-registry 163
-
epist
Epistemological tracking system for managing facts, conclusions, and provenance chains with Git integrity and semantic search. Integrates with Quarto for visual provenance analysis. Use when analyzing data from multiple sources, conducting research, working with metrics/surveys, making data-driven conclusions, or tracking complex findings. Triggers on data analysis (analyze data, metrics, survey, research, findings, insights), conclusions (conclude, recommend, decide, infer), quantitative work (percentage, trend, correlation, statistic), source attribution (according to, based on, from source), or any epistemological tracking. Skip for trivial calculations.
majiayu000/claude-skill-registry 163
-
github-webhook-setup
Configures GitHub webhooks for auto-deployment by verifying secrets, checking endpoint
accessibility, and guiding configuration. Use when you need to add a new repo for
auto-deploy, configure GitHub webhooks, set up continuous deployment, or troubleshoot
webhook issues. Triggers on "setup webhook", "add webhook for [repo]", "configure
auto-deploy", "GitHub deployment", or "webhook not working". Works with config/hooks.json,
.env (WEBHOOK_SECRET), and webhook.temet.ai endpoint.
majiayu000/claude-skill-registry 163
-
Community Manager
Manage online communities with engagement strategies, moderation, and relationship building
majiayu000/claude-skill-registry 163
-
learning-loop
Capture new learnings discovered during code exploration or user interaction that were not present in context, memories, or codebase documentation. This skill should be invoked when Claude discovers something new about the codebase, tools, workflows, or domain knowledge that could benefit future sessions.
majiayu000/claude-skill-registry 163
-
changelog-guide
Write and maintain CHANGELOG.md following Keep a Changelog format.
Use when: creating changelog entries, preparing releases, documenting changes.
Keywords: changelog, release notes, CHANGELOG.md, keep a changelog, 變更日誌, 發布說明.
majiayu000/claude-skill-registry 163
-
swift-combine
Master Combine framework for reactive programming - publishers, subscribers, operators, schedulers
majiayu000/claude-skill-registry 163
-
intermittent-issue-debugging
Debug issues that occur sporadically and are hard to reproduce. Use monitoring and systematic investigation to identify root causes of flaky behavior.
majiayu000/claude-skill-registry 163
-
xcode-build
Build and run iOS/macOS apps using xcodebuild and xcrun simctl directly. Use when building Xcode projects, running iOS simulators, managing devices, compiling Swift code, running UI tests, or automating iOS app interactions. Replaces XcodeBuildMCP with native CLI tools.
majiayu000/claude-skill-registry 163
-
vm-template-creation
Create, configure, and manage VM templates in Proxmox. Build reusable VM images for rapid deployment of standardized environments, including Kubernetes clusters and managed applications.
majiayu000/claude-skill-registry 163
-
gnu-recutils
Work with GNU recutils for plain-text record databases. Use when creating, querying, or validating .rec files, defining record schemas with %rec descriptors, converting between rec/CSV formats, or when the user mentions recutils, recsel, recins, recfmt, or record-oriented data files.
majiayu000/claude-skill-registry 163
-
fetch-team-context
Fetch Semicolon team standards from docs wiki. Use when (1) providing workflow or process advice, (2) recommending DevOps strategies, (3) referencing team conventions for decision-making, (4) checking team standards compliance.
majiayu000/claude-skill-registry 163
-
least-astonishment
El sistema debe comportarse como el usuario espera. Use cuando diseñe interacciones, tome decisiones sobre comportamientos, o evalúe sorpresas en la UX.
majiayu000/claude-skill-registry 163
-
research-ai-sdk
Research Vercel AI SDK patterns, streaming, and multi-provider integration using Exa code search and Ref documentation
majiayu000/claude-skill-registry 163
-
email-systems
Email has the highest ROI of any marketing channel. $36 for every $1 spent. Yet most startups treat it as an afterthought - bulk blasts, no personalization, landing in spam folders. This skill covers transactional email that works, marketing automation that converts, deliverability that reaches inboxes, and the infrastructure decisions that scale. Use when: keywords, file_patterns, code_patterns.
majiayu000/claude-skill-registry 163
-
godot-fix-positions
Use when Godot project has position conflicts between editor (.tscn) and code (.gd), camera-following backgrounds, or runtime positions don't match editor preview. Orchestrates all 3 position sync mini-skills: sync-static-positions, sync-camera-positions, and sync-parallax. Each operation targets specific position conflict types.
majiayu000/claude-skill-registry 163
-
deploy-cloudflare
Deploy to Cloudflare edge platform. Use when deploying static sites to Pages, serverless functions to Workers, or configuring CDN/DNS. Covers Wrangler CLI.
majiayu000/claude-skill-registry 163
-
castella-agent-ui
Build chat interfaces and agent management UIs with Castella. Create chat components, display tool calls, manage multiple agents, and build agent hubs.
majiayu000/claude-skill-registry 163
-
terminal
Execute shell commands in persistent, stateful VT100 terminal sessions. WHEN: User needs to "run a command", "execute shell", "build project", "run tests", "deploy", system administration. WHEN NOT: Simple file operations (use fs_* tools), reading known files (use fs_read_file).
majiayu000/claude-skill-registry 163
-
final-release-review
Perform a release-readiness review by locating the previous release tag from remote tags and auditing the diff (e.g., v1.2.3...<commit>) for breaking changes, regressions, improvement opportunities, and risks before releasing openai-agents-python.
majiayu000/claude-skill-registry 163
-
ai-runtime-toolkit
AI Runtime工具装备系统,支持8个内部专业工具和10+个外部CLI工具的整合管理,提供工具发现、执行和配置功能,遵循整合优于创造的设计理念
majiayu000/claude-skill-registry 163
-
arguments-test
Test skill for argument substitution
majiayu000/claude-skill-registry 163
-
send
Emit a message or event to an external system with policy enforcement and approval gates. Use when publishing messages, calling APIs, sending notifications, or triggering external workflows. REQUIRES EXPLICIT APPROVAL.
majiayu000/claude-skill-registry 163
-
http-interceptors
Angular 21+ functional HTTP interceptors for auth, error handling, loading states, retry logic, caching, and security best practices
majiayu000/claude-skill-registry 163