Agent skills
Skills you can use with AI coding agents, indexed from public GitHub repositories.
-
web_search
Search the web and known data registries for data sources
majiayu000/claude-skill-registry 163
-
brand-archetype-selection
Provides Jungian brand archetype frameworks, the 12 archetypes with profiles, the 70/30 primary/secondary rule, archetype combinations, and selection templates. Auto-activates during brand archetype selection, emotional positioning, and brand personality work. Use when discussing brand archetypes, Jungian archetypes, 12 archetypes, Hero, Outlaw, Magician, Creator, Lover, Jester, Everyman, Caregiver, Ruler, Sage, Explorer, Innocent, 70/30 rule, Mark-Pearson, or archetype combinations.
majiayu000/claude-skill-registry 163
-
test-local-skill
A test local skill for Claude. Use when testing local skills detection.
majiayu000/claude-skill-registry 163
-
modernize
Brownfield Upgrade - Upgrade all dependencies and modernize the application while maintaining spec-driven control. Runs after Gear 6 for brownfield projects with modernize flag enabled. Updates deps, fixes breaking changes, improves test coverage, updates specs to match changes.
majiayu000/claude-skill-registry 163
-
backend-dev
This skill should be used when developing backend services for Manjha using Encore.ts, implementing agents, writing E2E tests, or working with the message-driven architecture. It ensures adherence to TDD practices, type safety, proper logging, and Manjha's development principles.
majiayu000/claude-skill-registry 163
-
qa-element-extraction
Extract and capture screenshots of specific UI elements mentioned in QA test procedures. Use when creating visual references for test steps to show exactly what buttons, fields, and components look like.
majiayu000/claude-skill-registry 163
-
before-task
Comprehensive discovery before starting any spec or major task. Searches Graphiti, recommends vibe/MCPs, surfaces patterns.
majiayu000/claude-skill-registry 163
-
conversion-optimizer
Optimize CTA copy, hero sections, and button text for higher conversions using therapy-appropriate frameworks (PAS, AIDA, BAB). Maintains empathetic, non-salesy tone while driving action. Creates A/B test variations, scores conversion potential, and ensures CRPO compliance. Use when user mentions "CTA", "conversion rate", "improve button text", "more bookings", or asks about improving page performance.
majiayu000/claude-skill-registry 163
-
mxql
Complete MXQL (Metrics Query Language) toolkit for generating, analyzing, validating, and testing queries. Supports conversational query generation, automated validation, comprehensive analysis with optimization suggestions, and test query generation with sample data. Use this for all MXQL-related tasks including creating queries, debugging, optimization, and testing.
majiayu000/claude-skill-registry 163
-
sf-integration
Creates comprehensive Salesforce integrations with 120-point scoring. Use when setting up Named Credentials, External Services, REST/SOAP callouts, Platform Events, Change Data Capture, or connecting Salesforce to external systems.
majiayu000/claude-skill-registry 163
-
SpecFirst
Spec-driven development methodology for ANY software project.
USE WHEN developing features, fixing bugs, creating skills, or preparing releases.
USE WHEN user mentions specs, testing, release process, change proposals, or deployment.
Provides flexible spec tooling guidance but STRICT release discipline.
majiayu000/claude-skill-registry 163
-
run-with-timeout
Run commands with timeout protection to prevent hanging. Use for potentially long-running tests or operations.
majiayu000/claude-skill-registry 163
-
integration-agent
Handles integrations with trigger behavior for dynamic agent delegation
majiayu000/claude-skill-registry 163
-
playwright-dotnet
Guide for E2E testing with Playwright for .NET using Microsoft.Playwright.MSTest.v4 integration
majiayu000/claude-skill-registry 163
-
complex-analysis-expert
Expert in complex functions, contour integration, residue theory, and conformal mappings
majiayu000/claude-skill-registry 163
-
Testing Test Writing
Write minimal, focused tests that cover core user flows and primary workflows without over-testing during development. Use this skill when deciding what to test, writing behavior-focused tests, naming test cases clearly, mocking external dependencies, or keeping tests fast. Apply when completing feature implementation and adding strategic tests, testing critical paths rather than edge cases, or deferring edge case testing to dedicated testing phases.
majiayu000/claude-skill-registry 163
-
palantir-docs-local
Palantir 本地文档（en/latest）
majiayu000/claude-skill-registry 163
-
gyazo-latest-image
Gyazo APIを使用して最新の画像を取得して表示するスキル
majiayu000/claude-skill-registry 163
-
writing-tb
Provides svc_unit.sv testbench framework, macros (TEST_CLK_NS, CHECK_EQ, etc.), and template. Triggers when creating or modifying _tb.sv files.
majiayu000/claude-skill-registry 163
-
user-research
Design and conduct user research to understand needs, behaviors, and experiences. Use when user wants "journey mapping", "user interviews", "survey design", "usability testing", "user research", "customer discovery", "card sorting", "information architecture", "accessibility audit", "design critique", "prototype testing", "requirements gathering", "discovery phase", "validation phase", "research planning", or needs to understand users deeply.
majiayu000/claude-skill-registry 163
-
git-operations
Enforce git-expert agent delegation for all git operations in the MCP for LifeOS project. This skill should be used when performing git status checks, branching, merging, committing, or pushing to ensure MCP deployment compliance and Linear integration. (project, gitignored)
majiayu000/claude-skill-registry 163
-
external-model-selection
Choose optimal external AI models for code analysis, bug investigation, and architectural decisions. Use when consulting multiple LLMs via claudish, comparing model perspectives, or investigating complex Go/LSP/transpiler issues. Provides empirically validated model rankings (91/100 for MiniMax M2, 83/100 for Grok Code Fast) and proven consultation strategies based on real-world testing.
majiayu000/claude-skill-registry 163
-
klingai-compliance-review
Execute conduct compliance reviews for Kling AI integrations. Use when preparing for audits,
ensuring regulatory compliance, or reviewing security posture. Trigger with phrases like
'klingai compliance', 'kling ai audit prep', 'klingai security review', 'video generation compliance'.
majiayu000/claude-skill-registry 163
-
emit
Use when working on the Miden compiler (`cargo miden`, `cargo-miden`) and its integration test suite, debugging compiler issues or failing tests, or implementing compiler changes and you need to inspect intermediate artifacts. Covers `MIDENC_EMIT` (the environment-variable equivalent of `--emit`) for emitting WAT/HIR/MASM (and related outputs), plus `MIDENC_EMIT_MACRO_EXPAND` for dumping macro-expanded Rust via `cargo expand` for integration-test fixtures.
majiayu000/claude-skill-registry 163