Agent skills
Skills you can use with AI coding agents, indexed from public GitHub repositories.
-
eld-model-term-card
LDE（Law-Driven Engineering）のTerm Card作成スキル。
ドメインの語彙（Vocabulary）を標準フォーマットで文書化し、名辞抽象を具体化する。
使用タイミング: (1) 新しいTermを追加する時、(2) 既存Termを更新する時、
(3) Vocabulary Catalogに新規エントリを追加する時、(4) Phase Dでカード化する時
majiayu000/claude-skill-registry 163
-
git-commit-standards
Use when creating git commits or pull requests. Enforces conventional commit format and atomic change principles. Verified on Git 2.30+
majiayu000/claude-skill-registry 163
-
GitHub Issue Triage
Monitor and triage GitHub issues against design docs and implementation status. Use when user asks to "check issues", "triage issues", "sync issues", "what issues are open", or wants to ensure issues are up-to-date with development progress.
majiayu000/claude-skill-registry 163
-
encode-repo-serena
Systematically populate the Forgetful knowledge base using Serena's LSP-powered symbol analysis for accurate, comprehensive codebase understanding.
majiayu000/claude-skill-registry 163
-
theme-handler
Manage and update application themes using shadcn and tweakcn.
majiayu000/claude-skill-registry 163
-
shell-error-handling
Use when implementing error handling, cleanup routines, or debugging in shell scripts. Covers traps, exit codes, and robust error patterns.
majiayu000/claude-skill-registry 163
-
before-pushing
Use when about to push commits to remote repository
majiayu000/claude-skill-registry 163
-
bugfixforever
State-of-the-art procedure for fixing bugs in software projects. Use this skill when a bug has been detected or declared by the user, agent, or another skill (not during early-stage work in progress). Enforces a disciplined test-driven approach - understand, reproduce experimentally, write failing tests, fix the code, and clean up.
majiayu000/claude-skill-registry 163
-
hypogenic
Automated LLM-driven hypothesis generation and testing on tabular datasets. Use when you want to systematically explore hypotheses about patterns in empirical data (e.g., deception detection, content analysis). Combines literature insights with data-driven hypothesis testing. For manual hypothesis formulation use hypothesis-generation; for creative ideation use scientific-brainstorming.
majiayu000/claude-skill-registry 163
-
latchbio-integration
Latch platform for bioinformatics workflows. Build pipelines with Latch SDK, @workflow/@task decorators, deploy serverless workflows, LatchFile/LatchDir, Nextflow/Snakemake integration.
majiayu000/claude-skill-registry 163
-
git-workspace-review
Lightweight preflight checklist for verifying repo path, staged changes, and
diffs before other workflows.
Triggers: git status, preflight, workspace check, staged changes, diff review,
git verification, repo state
Use when: verifying workspace state before other git operations, checking
staged changes, preflight checks before commits or PRs
DO NOT use when: full commit workflow - use commit-messages instead.
DO NOT use when: full PR preparation - use pr-prep.
Use this skill as foundation for git workflows.
majiayu000/claude-skill-registry 163
-
wochenendplaner
Erstelle einen Wochenendplan für Wien mit Wetter, Tageslicht und Aktivitäten
majiayu000/claude-skill-registry 163
-
deep-work-session
Enter and manage Deep Work sessions in Agent Hive. Use this skill when starting a focused work session on a project, generating session context, following the handoff protocol, or managing your responsibilities as an agent during a work session.
majiayu000/claude-skill-registry 163
-
terraform-module-writer
Эксперт по Terraform модулям. Используй для создания переиспользуемых модулей, variables, outputs и best practices.
majiayu000/claude-skill-registry 163
-
budget-analyzer
Analyze personal or business expenses from CSV/Excel. Categorize spending, identify trends, compare periods, and get savings recommendations.
majiayu000/claude-skill-registry 163
-
gemini-api-rate-limiting
Best practices for handling Gemini API rate limits, implementing sequential queues, and preventing 429 RESOURCE_EXHAUSTED errors in WescoBar
majiayu000/claude-skill-registry 163
-
ux-ui-responsive
반응형 디자인 에이전트. 다양한 디바이스에 대응하는 반응형 디자인을 검토합니다.
majiayu000/claude-skill-registry 163
-
nx-docs-writer
Documentation writing and editing for nx.dev docs. Use when adding, editing, or polishing documentation, migrating Markdoc to Starlight, debugging content transformations, or fixing documentation site issues. Triggers on "docs", "documentation", "nx.dev", "Markdoc", "Starlight", "astro-docs".
majiayu000/claude-skill-registry 163
-
nvim-config
majiayu000/claude-skill-registry 163
-
multi-agent-rl
Master QMIX, MADDPG, CTDE - multi-agent learning with coordination and credit assignment
majiayu000/claude-skill-registry 163
-
add-package
パッケージを追加する際に使用します。開発用と、プロダクト用途問わずこれを使います。
majiayu000/claude-skill-registry 163
-
boardkit-canvas-input-model
Canvas input model: pan/zoom, pointer events, keyboard shortcuts, selection, gestures.
Use when working on canvas interactions, navigation, or input handling.
majiayu000/claude-skill-registry 163
-
creating-skills
Use when creating new skills, documenting workflows, or standardizing processes into reusable skill definitions.
majiayu000/claude-skill-registry 163
-
lead-magnet-therapy
Create CRPO-compliant lead magnets for therapy practices that build email lists without crossing ethical boundaries. Use when planning top-of-funnel content to capture leads. Creates concepts for guides, frameworks, and educational resources. CRITICAL: NO diagnostic assessments, NO outcome promises, NO psychological tests. Triggers on: create lead magnet, build email list, free resource ideas, content upgrade concepts. Outputs educational lead magnet concepts that provide genuine value while staying compliant.
majiayu000/claude-skill-registry 163