github-profile-rules
Command`github-profile-rules` — extract programming rules and coding conventions from a GitHub user's public profile via API.
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.
`github-profile-rules` — extract programming rules and coding conventions from a GitHub user's public profile via API.
Breaks down a call recording/transcript into metrics, highlights, risks, and recommended actions.
Produces competitive landscape brief with threat levels, differentiators, and recommended actions.
Audits inquiry → enrollment funnel to surface channel gaps, yield risks, and experiments.
Create an editable draw.io grc audit workflow diagram for GRC professionals
Deploy latest Docker image to {{DEV_MACHINE}} dev environment
Manage sprite palettes - set, optimize, or load preset palettes
Configure pixel-mcp server and verify Aseprite installation
Find the canonical fix commit(s) for a CVE across sources, then diff for root cause
Execute Phase 4 - Exploitation and Access Establishment
Create comprehensive documentation with intelligent type detection and orchestration
Create in-depth explanations that build conceptual understanding of complex topics
Create practical how-to guides for solving specific problems and accomplishing tasks
Generate a custom checklist for the current feature based on user requirements.
Identify underspecified areas in the current feature spec by asking up to 5 highly targeted clarification questions and encoding…
Create or update the project constitution from interactive or provided principle inputs, ensuring all dependent templates stay in…
Commit what is already staged — runs the commit subagent in the background, following the ATLAS commit convention.
Discover the project's visual identity, prototype 3 HTML design variants for Boss to compare in a browser, iterate, then lock in…
Create a development phase the lean way — resolve ambiguity through Q&A, then capture it as a self-contained low-fidelity…
Apply labels + milestone + priority to a new issue using the llmwiki triage rules.
Run the full llmwiki pipeline end-to-end: build → graph → export all → lint.
Set up Databricks CLI auth: install check, then an OAuth / PAT / service-principal profile (workspace or account-level), then…
Switch the status-bar look (aurora blocks / aurora thin / classic)
You MUST use this before any creative work - creating features, building components, adding functionality, or modifying behavior.…
Skip quality gate — use for abandoned or superseded tracks
Deep code and data analysis with batch processing capabilities.
Implement an approved OpenSpec change and keep tasks in sync.
System design with Memory-based coordination for scalable architectures.
AgentRecall session opener — status board (no args), project loader (<slug>), or cold-start bootstrap. Use first every session.
Phase 6 Execution & Report Analysis of api-aqa-flow (USER INTERACTION REQUIRED)
Phase 3 Gap & Requirements Clarification of api-aqa-flow (USER INTERACTION REQUIRED)
Generates professional documents (assessments, features, analysis, process, custom) with language support and specialized…
Generates comprehensive security assessment document after security audit completion. Use when you need to create a structured…
Creates a GitHub pull request with branch creation, commits, and detailed description. Use when you need to submit changes for…
Start the Claude Nights Watch daemon to begin autonomous task execution monitoring
Check the status of Claude Nights Watch daemon and view current configuration
Stop the Claude Nights Watch daemon and halt autonomous task execution
Force critical evaluation of proposals from 5 adversarial perspectives
Define the collaboration style between Claude Code and the user for the current session
Define or audit a brand — positioning, visual identity system, voice and tone, and brand architecture.
Design a chart or data visualization — selects the right chart type, applies accessible color palettes, adds annotations, and…
Capture a competitor website with Playwright and extract its color system, typography, layout patterns, and 'steal this'…
**Navigation**: [← Step 3: Plan](3-plan.md) | [Main Workflow](../workflow-steps.md) | [Step 5: Validate →](5-validate.md)
**Navigation**: [← Step 4: Fix](4-fix.md) | [Main Workflow](../workflow-steps.md) | [Step 6: Complete →](6-complete.md)
**Navigation**: [<- Step 5: Validate](5-validate.md) | [Main Workflow](../workflow-steps.md)
Check market sentiment indicators (Fear & Greed, market movers)
Top-level alias — see lesson/check-setup.md for the full body.
Top-level alias — see lesson/check-setup.en.md for the full body.
Alias de nivel superior — el cuerpo completo está en lesson/check-setup.es.md.
Run a planning-aware cadence with Claude Code's /loop. Default tick checks plan status, runs check-complete, nudges progress.md…
Short alias for /plan. Starts Manus-style file-based planning: task_plan.md, findings.md, progress.md. Available since v3.0.0.
Show current planning status at a glance - phases, progress, and any logged errors.
**作用**: 将论文从原模板迁移至目标模板,自动处理图表尺寸、页数、宏兼容性等问题。它是专家快捷入口;普通自然语言如“把这篇论文迁移到 CVPR 模板”也应能触发同类任务。
Inspect or repair LaTeX paper layout with the PaperFit skill.
**作用**: 读取当前状态、视觉重点和修复计划,给出本轮应该先处理什么;若用户明确指定优先顺序,可将该顺序写入 `next_actions` 供后续 `/fix-layout` 直接遵循。
使用 Playwright 生成并运行端到端测试。创建测试流程,运行测试,捕获截图/视频/追踪记录,并上传测试产物。
Opens an interactive diff viewer showing uncommitted changes in your working directory and per-turn diffs from Claude's edits.
Analyses your codebase and generates a starter `CLAUDE.md` file. This is the fastest way to give Claude persistent context about…
Selects or switches the model Claude Code uses. You can pick by a convenient alias instead of remembering exact version numbers.
Create or repair the user's default cross-project wiki.
Interactive workflow for adding one source file to the wiki. The LLM reads the file, discusses key takeaways with the user, then…
Interactive, conversational setup for a new knowledge base wiki. One question at a time, multiple choice when possible.
Figure out what the user wants to design — even when they don't know yet. Extracts the design brief: purpose, audience, brand…
复盘 PROJECT_LOG.md——统计哪个模块出错最多、哪类错误重复、标准变更几次;重复 TOP 的错误输出为"该下沉成 lint/测试"的候选清单。LOG 从流水账变资产。
统一配置新项目、讨论后项目或已有项目的产品文档包与 Agent 入口;先识别资料与授权,再编排专项 Skill,保留现有主源。
Configure claude-sync for cross-device session synchronization
Show the status of the current Vercel project — recent deployments, linked project info, and environment overview.
Transform into backend specialist for scalable API and system design
Cloud architect persona for designing scalable, secure cloud infrastructure using modern cloud-native technologies
Comprehensive code review with security, quality, and maintainability analysis
Mine recent agent history (claude-mem + usage stats) for recurring failures and repeated patterns, audit MEMORY.md health, and…
Plamen v2 Smart Contract audit wizard. Collects config, launches deterministic driver.
Run ClawdStrike self-test to verify all components are working
Perform a non-destructive cross-artifact consistency and quality analysis across spec.md, plan.md, and tasks.md after task…
Generate a custom checklist for the current feature based on user requirements.
Identify underspecified areas in the current feature spec by asking up to 5 highly targeted clarification questions and encoding…
Create a feature specification using spec-driven development
© 2026 Flowy
Built for Claude Code · Not affiliated with Anthropic
Logos are trademarks of their owners.