Agent skills
Skills you can use with AI coding agents, indexed from public GitHub repositories.
-
claude-consult
Consult Claude specialist agents during implementation for codebase understanding, pattern checking, security review, debugging help, and more. Use this skill whenever you're unsure about conventions, stuck on a failure, or need expert input before writing code. Does not replace the formal review gates in agent-loops — this is for mid-implementation consultation.
majiayu000/claude-skill-registry 163
-
ln-820-dependency-optimization-coordinator
Upgrades dependencies across all detected package managers. Use when updating npm, NuGet, or pip packages project-wide.
majiayu000/claude-skill-registry 163
-
severity
Data-driven severity classification for smart contract audit findings with statistical breakdowns and 30 representative examples per level from top audit firms. Use when assigning severity to findings, justifying classifications with historical data, or calibrating severity judgment against Code4rena, Sherlock, and Cyfrin benchmarks.
majiayu000/claude-skill-registry 163
-
safe-edit
Automatically backs up files, saves diffs, uses agents/skills, and ensures modular code (<200 lines) before any implementation. Use this skill for ALL code changes to ensure safe, reversible, and clean implementations.
majiayu000/claude-skill-registry 163
-
i18n-patterns
Internationalization (i18n) patterns using inline t() calls with compile-time Babel transformation. Use when adding or modifying translated text, working with locales, creating new pages or components that need translations, using the t() function, mentioning i18n, translations, locale switching, useLocale, setLocale, or when the user asks about how translations work in this project. Also use when working with the i18n codegen pipeline, Babel plugin, or generated translation bundles.
majiayu000/claude-skill-registry 163
-
planning-with-files
Implements Manus-style file-based planning to organize and track progress on complex tasks. Creates task_plan.md, findings.md, and progress.md. Use when asked to plan out, break down, or organize a multi-step project, research task, or any work requiring 5+ tool calls. Supports automatic session recovery after /clear.
majiayu000/claude-skill-registry 163
-
V3 Memory Unification
Unify 6+ memory systems into AgentDB with HNSW indexing for 150x-12,500x search improvements. Implements ADR-006 (Unified Memory Service) and ADR-009 (Hybrid Memory Backend).
majiayu000/claude-skill-registry 163
-
bmad-bmm-edit-prd
bmad-bmm-edit-prd skill
majiayu000/claude-skill-registry 163
-
cost-explain
Explain all costs in human terms. Always compare with real-world equivalents. Recommend cheapest that works.
majiayu000/claude-skill-registry 163
-
ui-ux-polish
Iterative UI/UX polishing workflow for web applications. The exact prompt and methodology for achieving Stripe-level visual polish through multiple passes.
majiayu000/claude-skill-registry 163
-
ena-database
Access European Nucleotide Archive via API/FTP. Retrieve DNA/RNA sequences, raw reads (FASTQ), genome assemblies by accession, for genomics and bioinformatics pipelines. Supports multiple formats.
majiayu000/claude-skill-registry 163
-
compliance-review
Regulatory compliance check for SOC2, PCI-DSS, GDPR, HIPAA — checklists, audit trails, access controls
majiayu000/claude-skill-registry 163
-
af
Agent Farm CLI quick reference. Use when running af commands to check correct syntax, subcommands, and flags. Prevents guessing at command names.
majiayu000/claude-skill-registry 163
-
running-effective-meetings
Help users run more effective meetings. Use when someone is dealing with meeting overload, wants to improve meeting culture, is preparing an important meeting, or struggles to get decisions made in meetings.
majiayu000/claude-skill-registry 163
-
scout-repos
Fetch .claude/ configs from curated repos in sources.yml, compare against dotforge template, report novel patterns.
majiayu000/claude-skill-registry 163
-
error-diagnostics-error-analysis
You are an expert error analysis specialist with deep expertise in debugging distributed systems, analyzing production incidents, and implementing comprehensive observability solutions.
majiayu000/claude-skill-registry 163
-
af-query-linear-api
Query and interact with Linear for issue tracking and workflow management. Use when running GraphQL queries, managing team operations, or performing advanced Linear API operations beyond linearis CLI.
majiayu000/claude-skill-registry 163
-
create-design-board
Generate and maintain iterative design boards from image directories. Composite PNG grids, markdown boards with size previews, round tracking, and side-by-side comparison tables.
majiayu000/claude-skill-registry 163
-
bmad-wds-implement
Code the designed improvement in a new branch
majiayu000/claude-skill-registry 163
-
technical-change-tracker
Track code changes with structured JSON records, state machine enforcement, and AI session handoff for bot continuity
majiayu000/claude-skill-registry 163
-
memory-systems
Design and implement memory architectures for agent systems. Use when building agents that need to persist state across sessions, maintain entity consistency, or reason over structured knowledge.
majiayu000/claude-skill-registry 163
-
cortex-skills-loop
Drives the cortex skills recommend-feedback-rate loop. Use when a context change occurs (new file types, domain shift, task pivot) or when a task completes and skill effectiveness should be recorded.
majiayu000/claude-skill-registry 163
-
release
Create a GitHub issue, commit, tag, and push a release. Detects repo type and runs mode-specific pre-flight checks with user confirmation at every step.
majiayu000/claude-skill-registry 163
-
competitive-intelligence
Porter's Five Forces, SWOT analysis, and competitive positioning matrix for strategic market analysis. Identifies threats, opportunities, and recommends positioning strategy.
majiayu000/claude-skill-registry 163