Skills

Agente Drafter do time Code New Project Agents. Sintetiza `ideation.md` e `personas.md` em um PRD completo (problema, métricas, escopo, não-objetivos, restrições, riscos). Use quando o usuário digitar "/reversa-drafter", "reversa-drafter" ou quando invocado pelo orquestrador `/reversa-new`. Produz `_reversa_sdd/prd.md`.

QQ channel management skill. Use qqbot_channel_api for explicit QQ channel-management requests; confirm write, delete, and bulk actions before calling authenticated QQ Open Platform endpoints.

UMAP-learn is a tool for fast nonlinear dimensionality reduction and visualization of high-dimensional data, aiding clustering preprocessing and feature embedding.

Orchestrate a comprehensive legacy system modernization using the strangler fig pattern, enabling gradual replacement of outdated components while maintaining continuous business operations through ex

>

Use when handling sensitive data — SecureStorage, certificate pinning, env vars, token encryption, no secrets in code.

Transcribe audio via OpenAI Audio Transcriptions API (Whisper).

A Python resource management tool that simplifies handling and cleanup of resources such as database connections, file handles, and streaming using context managers and async context managers.

Prüft unzitierte Tatsachenbehauptungen über die reale Außenwelt – Produkte, Institutionen, Zahlen, Funktionsansprüche –, die keine Quellenangabe tragen und deshalb für Teil-Check G, Stresstest und Autoref-Check unsichtbar sind. Läuft als kalte, isolierte Sitzung ohne Projektstatus, Prüfbericht und Änderungshistorie, verifiziert jeden Kandidaten einzeln per Websuche und schreibt faktencheck-bericht.md. Nutzen, sobald alle Kapitel FERTIG sind und ein Marktüberblick, eine Wettbewerbsanalyse, eine W

>-

--- name: bhawna-design-sync description: Use when translating the Bhawna Foundation Pencil design into implementation, including reading the .pen file, extracting tokens and content, mapping desktop and mobile layouts, or inferring missing component states in the same style. --- Read `references/design-map.md` before implementing a new page or section. ## Use this skill for - extracting page and section structure from `Bhawna-foundation.pen` - matching colors, typography, spacing, and hierarchy

Generic skill category 187 - use when working on related tasks

Generate comprehensive C4 architecture documentation for an existing repository/codebase using a bottom-up analysis approach.

Justin Sun Cognitive Framework - 孙宇晨认知操作系统 | 21,829 tweets + 288-page autobiography + 155-episode audio course + 269+ sources → 14 mental models + 19 decision heuristics

An AI tool designed to assist in reviewing GitHub pull requests by identifying critical issues related to code correctness, security, reliability, and performance.

Duplicate a Google Sheets template tab for a new month of tracking.

An AI tool that processes interview transcripts to extract themes, contradictions, and actionable product insights, enabling structured qualitative data analysis.

Delete Oracle Cloud Always Free resources safely with the oci CLI — terminate the instance and unwind NSG, subnet, route table, internet gateway and VCN in reverse order. Use for "tear it down", "destroy everything", "clean up my free tier", `oci compute instance terminate`, `oci network vcn delete`, Conflict or "has dependencies" errors, orphaned boot volumes, stopping charges, and verifying nothing billable survived.

Run the quarter-boundary ritual — roll the quarter-scoped project folders, archive finished projects, grade the closing quarter's GOALS/OKRs, and draft the new quarter's goals behind an approval gate. Trigger on /quarter-rollover, "quarter rollover", "roll the quarter", "close out Q2", "new quarter setup", or when tools/quarter_path.py --check reports drift. Distinct from /triage-tasks (daily gate) and /audit (repo health check).

Browser automation, debugging, and performance analysis using Puppeteer CLI scripts. Use for automating browsers, taking screenshots, analyzing performance, monitoring network traffic, web scraping, form automation, and JavaScript debugging.

Turn any file into a beautiful, interactive, shareable HTML — WhatsApp logs, PDFs, transcripts, code, anything.

Total Recall — Autonomous Agent Memory. The only memory system that watches on its own. Five-layer observational memory for OpenClaw agents. ~$0.10/month.

Use when starting a session and wanting creative engagement, or when user says '/fun' or asks for a persona

Configure deployment settings for /land-and-deploy.

An AI tool that conducts rigorous interviews to refine plans or designs while generating architectural decision records and glossaries.

Procedural memory for AI coding agents: transforms scattered session history into persistent, cross-agent memory so every agent learns from every other

Strava from your terminal. Pipe it, script it, automate it.

gsd-undo is a tool for safely reverting git commits related to project phases or plans with dependency checks and interactive confirmation.

Agente Drafter do time Code New Project Agents. Sintetiza `ideation.md` e `personas.md` em um PRD completo (problema, métricas, escopo, não-objetivos, restrições, riscos). Use quando o usuário digitar "/reversa-drafter", "reversa-drafter" ou quando invocado pelo orquestrador `/reversa-new`. Produz `_reversa_sdd/prd.md`.

Automate Multi-Locale asset creation for your iOS app.

Use this skill for code review and PR review tasks. Covers review methodology, what to flag, what to skip, and output structure.

Representative MoE training playbooks by hardware platform and model family. Summarizes rounded throughput bands, parallelism patterns, and common tuning stacks.

Master Test Architect and Quality Advisor. Use when the user asks to talk to Murat or requests the Test Architect.

Use when computing the 5D Compressed SMA Slope factor from user-supplied real OHLCV data or reviewing its bundled real-data validation metrics.

Python resource management with context managers, cleanup patterns, and streaming. Use when managing connections, file handles, implementing cleanup logic, or building streaming responses with accumulated state.

An AI writing assistant specialized in creating and improving social media posts tailored to each platform's style and audience to boost engagement and reach.

Semantic search, similar content discovery, and structured research using Exa API. Use when you need semantic/embeddings-based search, finding similar content, or searching by category (company, people, research papers, etc.).

Applies Strunk's Elements of Style principles when writing or editing prose. Triggers on "write clearly," "edit for style," "improve writing," or tasks requiring clear, vigorous English — documents, emails, reviews.

Orchestrate a comprehensive legacy system modernization using the strangler fig pattern, enabling gradual replacement of outdated components while maintaining continuous business operations through ex

Multi-disciplinary premium frontend skill used to build elegant, high-end websites with minimal layouts, serif typography, and fluid micro-animations.

An AI tool that facilitates rigorous interview-style sessions to refine plans or designs while generating architectural decision records and glossaries.

Agent skill for load-balancer - invoke with $agent-load-balancer

|

Use when creating or refining WebGL-heavy landing pages and you need to steer toward a specific visual outcome (premium, technical, playful, cinematic) while balancing conversion clarity, performance, and implementation complexity.

Orchestrate a comprehensive legacy system modernization using the strangler fig pattern, enabling gradual replacement of outdated components while maintaining continuous business operations through ex

Sublong is a command-line tool for aligning long FASTQ reads to a reference genome, primarily used in bioinformatics for genomic and RNA-seq analyses.

コードやPRをレビューする際に使用。品質、保守性、よくある問題をカバー。

Create Gentle AI pull requests with issue-first checks. Trigger: creating, opening, or preparing PRs for review.

Self-improvement system for Hermes Agent. Monitors performance, finds weak skills, fixes them with self-evolution, reports results.

Run tests on the codebase.