create-command
CommandCreate a new obsidian-second-brain command via interview - zero markdown editing required
11,199 slash commands. The ones you type, shipped in plugins found in public marketplaces and GitHub repositories. A command runs exactly when you ask, never before.
Create a new obsidian-second-brain command via interview - zero markdown editing required
Share a plain-folder logbook across Claude Code, Codex, Cursor, and Grok Bot
Surface 3-5 next-direction candidates by reading ungraduated ideas, open project questions, and orphan research notes - what is…
Head-to-head graded battle card between two sites — eight dimensions, bar-by-bar, verdict line.
Generate a full editorial brand-guidelines book for any URL. 14 chapters covering brand essence/archetype, colour, typography,…
Place a design in the measured design space — nearest systems, per-axis percentiles, outliers
Create a new beta release using the automated justfile target with quality checks and tagging.
Create a stable release using the automated justfile target with comprehensive validation.
Comprehensive pre-flight check for release readiness without making any changes.
Scan, analyze, and fix security vulnerabilities reported by Snyk for frontend/JS projects. Creates a PR with minimal, safe…
Generate a changelog comparing a specified tag (or latest if not provided) with the previous version.
Analyze 18-month scenarios from a news headline. Generate a comprehensive English report including 1st/2nd/3rd-order impacts,…
Run the Claude Code-native US undervalued-growth/GARP discovery pipeline, underwrite every selected name, and publish an audited…
Autonomous performance optimization: research, PoC, benchmark, implement, review, PR
ChatGroup architecture — how conversation data flows from raw JSONL to rendered chat groups. Use when working on UserGroup,…
Design system and visual language — theming, CSS variables, Tailwind config, component styling patterns, icon usage, animations,…
Explains what "Visible Context" is — the 6 trackable token categories, what falls outside tracking, how it's displayed, and why…
Compatibility shim for entering the governed Vibe-Skills runtime through the canonical vibe skill.
Run the governed Vibe-Skills runtime for implementation after planning approval.
Run the governed Vibe-Skills runtime for review-first work.
Ask the AWS DevOps Agent for cost optimization opportunities, scoped to your local IaC
Start a deep root-cause investigation on the AWS DevOps Agent and stream progress
Run a comprehensive audit of an existing design system for consistency, completeness, and accessibility.
Run a competitive benchmark across a set of products — pattern comparison, gap analysis, and opportunity callouts.
Build a design presentation end to end — audience framing, narrative structure, and supporting rationale.
Update CHANGELOG.md with all changes from the latest tag to current commit.
Step 4 of the vibe-coding workflow: generate `AGENTS.md` + tool configs so the AI builder stays on track.
Step 5 of the vibe-coding workflow: build the MVP one verified feature at a time.
Step 2 of the vibe-coding workflow: define WHAT to build, WHO it's for, and WHY it matters.
Act as a planning interviewer. Your goal is to turn a rough idea or plan into a clear plan.
Run every objective gate this project can prove and report the real N/N. Use before claiming any screen or component is done.
Run a paid-ads (ROAS) workflow: audience segments, account structure, ad creative, experiment design, pre-launch signal QA + the…
Natural-language front door to the marketing pack (narrative/TALE, SEO/GEO/SITE, social/ECHO, email/SEND, Paid Ads/ROAS,…
Run an email-marketing (SEND) workflow: deliverability/consent setup, segmentation, email creative, lifecycle flows, newsletter…
Checks running Claude Code or Codex sessions, finds zombies, and offers a safe cleanup. Use when sessions feel stuck or many are…
Runs a 10-second context health check with a quality score and the top issues. Use for a fast pulse on the current session.
Auto-detect project type and configure quality gates, permissions, and hooks for a new codebase
Smart context compaction with state preservation — saves critical state before compact and restores after
⚠️ 2026-07-02부터 프로덕션은 [gomdori-mcp](https://github.com/chrisryugj/gomdori-mcp) 통합 호스트(fly 앱 `korean-law-mcp`, MCP 5종 동거)가 서빙합니다.…
Scan web application components for accessibility violations against WCAG guidelines.
Add a new API endpoint to an existing backend service with validation and tests.
Add a new feature module to an existing project with all supporting files.
Perform competitive analysis on companies or products
Research current market trends in a specific industry or domain
Connect and authenticate the Vybe Solana MCP server over OAuth.
Add a skill to the project with validation and README generation
Create a detailed implementation plan using Codex 5.2 with high reasoning
Draft a professional email using the What-Why-How framework. Use when you need to compose emails to colleagues, stakeholders, or…
Initialize the current project with Scientific Writer - a deep research and writing tool that combines AI-driven research with…
Share improvements - issues, PRs, skills, templates, and videos you made
Sets and refines how a video looks with the `video-design` skill, taking direction from the project's design source: plug in your…
Guided Apify Actor development with best practices and systematic workflow
List pentest-ai agents relevant to a domain or tag (web, ad, cloud, mobile, recon, etc.).
{ "name": "memory", "description": "Update the project memory with what was accomplished in this session", "prompt": "Update the…
Recommend the right pentest-ai agent and concrete next steps for a freeform task description.
Weekly autonomous triage of claude-usage — merge no-brainers to DEV, run tests, Codex collab, close duplicates /…
This obsolete slash command is disabled for this repository.
This obsolete slash command is disabled for this repository.
This obsolete slash command is disabled for this repository.
You are installing or updating Trail of Bits' Claude Code configuration into the user's `~/.claude/` directory.
@description End-to-end: plan, implement, test, review, fix, push, and PR for a GitHub issue. @arguments $ISSUE_NUMBER: GitHub…
@description Evaluate and merge dependabot PRs with parallel builds, dependency-aware batching, and transitive dep analysis.…
Analyze code quality, identify issues, and suggest improvements.
Audit recent AI coding sessions to find repeated mistakes, speed losses, and missed Nimbalyst tool usage — then propose harness…
Create an animated explainer diagram (.anim.json) for a system, protocol, or process
Deep Q&A on a paper already analyzed. Actively records valuable insights to the note file during the discussion, without waiting…
Execute all steps without asking for user confirmation at intermediate stages. Report results at the end.
Synthesizes accumulated literature notes into a structured **Research Foundation Document (RFD)**.
Strategically explore the most recent parent session from the session lineage (shown in the first user message) to extract the…
A human-friendly name for this agent session (e.g., architect, tester, reviewer)
启动 NanoClaw 智能体 (Agent) REPL — 一个由 claude CLI 驱动的持久化、会话感知 (session-aware) 的 AI 助手。
© 2026 Flowy
Built for Claude Code · Not affiliated with Anthropic
Logos are trademarks of their owners.