A curated set of skills
This repository also configures its own agents. See what skill-quiver tells them →
Skill Claude Code
SEO strategist covering technical SEO, content optimization, link authority, and organic growth. Invoke for site audits, keyword research, on-page optimization, or SEO strategy.
Skill Claude Code
Find interesting, positive, shareable story hooks from history, news, or data. Turns calendar anniversaries, current events, or raw facts into a narrative you can tell in 1 minute.
Skill Claude Code
Twitter/X growth specialist — thought leadership, community engagement, viral thread creation, and brand authority building. Invoke for Twitter content, thread writing, or engagement strategy.
Skill Claude CodeCodex
Structured writing assistant engine that explores and refines a perspective through natural, low-AI-signature prose and computer-science analogical framing. TRIGGER when: user asks to write an article, essay, or thoughts about a specific topic.
Skill Claude Code
A specialist for creating lifestyle content and growth plans for Xiaohongshu, a Chinese social platform focused on personal recommendations and visual posts.
Skill Claude CodeCodex
Interact with X/Twitter via the x-cli terminal client using official X API credentials. Use for posting, reading timelines, searching tweets, liking, retweeting, bookmarks, mentions, and user lookups.
Skill Claude CodeCodex
X/Twitter via xurl CLI: post, search, DM, media, v2 API.
Skill Claude CodeCodex
Review PRs: diffs, inline comments via gh or REST.
Skill Claude CodeCodex
Pre-commit verification pipeline: security scan, baseline-aware quality gates, independent reviewer subagent, and auto-fix loop. No agent verifies its own work. TRIGGER when: user says "commit", "push", "ship", "done", "verify", or "review before merge", or after implementing a feature with 2+ file edits.
Skill Claude CodeCodex
Expert code reviewer who provides constructive, actionable feedback focused on correctness, maintainability, security, and performance — not style preferences.
Skill Claude CodeCodex
Use this skill when adding authentication, handling user input, working with secrets, creating API endpoints, or implementing payment/sensitive features. Provides comprehensive security checklist and patterns.
Skill Claude CodeCodex
Scan your Claude Code configuration (.claude/ directory) for security vulnerabilities, misconfigurations, and injection risks using AgentShield.
Skill Claude CodeCodex
Security scan a SKILL.md using NVIDIA SkillSpector before curation or promotion. Detects 64 vulnerability patterns across 16 categories including prompt injection, data exfiltration, harmful content, MCP poisoning. TRIGGER when: user says "/skill-scan [path]", "scan this skill", or "is this skill safe". Also called…
Skill Claude CodeCodex
Cloud infrastructure and CI/CD pipeline security practices, including IAM configurations, secrets management, VPC security, logging, WAF, and disaster recovery.
Skill Claude CodeCodex
Deployment workflows, CI/CD pipeline patterns, Docker containerization, health checks, rollback strategies, and production readiness checklists for web applications.
Skill Claude CodeCodex
Expert DevOps engineer specializing in infrastructure automation, CI/CD pipeline development, and cloud operations.
Skill Claude CodeCodex
Docker and Docker Compose patterns for local development, container security, networking, volume strategies, and multi-service orchestration.
Skill Claude CodeCodex
Expert infrastructure specialist focused on system reliability, performance optimization, and technical operations management. Maintains robust, scalable infrastructure supporting business operations with security, performance, and cost efficiency.
Skill Claude CodeCodex
Capture architectural decisions made during Claude Code sessions as structured ADRs. Auto-detects decision moments, records context, alternatives considered, and rationale. Maintains an ADR log so future developers understand why the codebase is shaped the way it is.
Skill Claude CodeCodex
Audits persistent context files (CLAUDE.md, SESSIONCONTEXT, handoffs, memory) for staleness, duplication, hot/cold mismatch, orphan references, and bloat. Produces a prioritized action list. User confirms before any changes.
Skill Claude CodeCodex
Audits Claude Code context window consumption across agents, skills, MCP servers, and rules. Identifies bloat, redundant components, and produces prioritized token-savings recommendations.
Skill Claude CodeCodex
HITL skill curation pipeline. Evaluates a candidate skill against quality/ feasibility/freshness dimensions, normalizes frontmatter to quiver spec, and guides promotion or rejection. TRIGGER when: user says "/curate", "evaluate this skill", "curate [skill name or path]", or drops a file in incoming/.
Skill Claude CodeCodex
Normalize an existing SKILL.md to quiver frontmatter spec. Checks completeness, line count, heading structure, and description quality. Outputs a diff-style view of changes. Does NOT alter skill body logic. TRIGGER when: user says "/format [path]", "normalize this skill", or "fix frontmatter for [skill]".
Skill Claude CodeCodex
Instinct-based learning system that observes sessions via hooks, creates atomic instincts with confidence scoring, and evolves them into skills/commands/agents. v2.1 adds project-scoped instincts.
At most 3 mods per repository are shown here, and a mod shipped inside a plugin is left to that plugin's page — the rest are on their repository pages: