slime
Provides guidance for LLM post-training with RL using slime, a Megatron+SGLang framework. Use when training GLM models, implementing custom data generation…
A skill ships inside a plugin. Install the plugin, and a skill that gets Auto-invokedWhat is this?This plugin ships a FLOW.md router the engine fires, so the matching skill runs itself. No slash command to remember.Learn how → runs itself when your prompt calls for it.
40,077 skills across 2,408 plugins. 1,867 of them fire as you prompt.
Provides guidance for LLM post-training with RL using slime, a Megatron+SGLang framework. Use when training GLM models, implementing custom data generation…
Accelerate LLM inference using speculative decoding, Medusa multiple heads, and lookahead decoding techniques. Use when optimizing inference speed (1.5-3.6×…
State-of-the-art text-to-image generation with Stable Diffusion models via HuggingFace Diffusers. Use when generating images from text prompts, performing…
Morning orientation that recaps recent work, checks agenda, emails, meetings and tasks, then helps decide what to work on. Trigger when user says 'good…
Two-tier memory system that makes Claude a true workplace collaborator. Decodes shorthand, acronyms, nicknames, and internal language so Claude understands…
Review and organize Todoist tasks in the Evolution project. Finds uncategorized, untranslated, or messy tasks and organizes them with proper categories, PT-BR…
Generate a concrete executable attack/probe against a chosen threat surface.
Generate diverse candidate research fields/subfields consistent with current context while permitting deliberate boundary-crossing.
Generate mechanism-distinct explanations rather than superficial paraphrases.
Use to run day-to-day loyalty reward catalog management and fulfillment.
Use when identifying launch risks, mitigation plans, and escalation owners.
Use to track pursuit risks, owners, mitigation steps, and escalation
Use when converting a PDF into another format such as Markdown, HTML, text, JSON, DOCX, or structured notes and the agent must choose the best extraction…
This guide covers essential PDF processing operations using Python libraries and command-line tools. For advanced features, JavaScript libraries, and detailed…
IMPORTANT - Path Resolution: This skill can be installed in different locations (plugin system, manual installation, global, or project-specific). Before…
Core skill for the deep research and writing tool. Write scientific manuscripts in full paragraphs (never bullet points). Use two-stage process with (1)…
Machine learning: clustering, PCA/t-SNE/UMAP, classification, prediction regression (Ridge/Lasso/ensemble), cross-validation, Pipelines. For unsupervised…
PubMed search with keyword optimization, result parsing, and metadata extraction
Systematically evaluate scholarly work using the ScholarEval framework, providing structured assessment across research quality dimensions including problem…
Use when planning an end-to-end scholarly publishing workflow, including manuscript source-of-truth, submission assets, revision/rebuttal files, camera-ready…
Open-ended scientific ideation partner. Use for research gaps, mechanism exploration, interdisciplinary connections, assumptions, possible research directions,…
Feature specification creation from codebase research. Produces requirements, acceptance criteria, architecture decisions, implementation plans, and risk…
Specification creation and management for the Pilot Shell methodology. Covers semantic search, clarifying questions, structured spec generation, and iterative…
Für Leasing AGB: ordnet Norm, Beweislast und Gegenargument; Ergebnis: Prüfprodukt mit Risiko und nächstem Schritt.
Für Legal Note Redline Output: ordnet Norm, Beweislast und Gegenargument; Ergebnis: Prüfprodukt mit Risiko und nächstem Schritt.
Für Leistungsänderung Produktupdate: ordnet Norm, Beweislast und Gegenargument; Ergebnis: Prüfprodukt mit Risiko und nächstem Schritt.
Visualize training metrics, debug models with histograms, compare experiments, visualize model graphs, and profile performance with TensorBoard - Google's ML…
Optimizes LLM inference with NVIDIA TensorRT for maximum throughput and lowest latency. Use for production deployment on NVIDIA GPUs (A100/H100), when you need…
Provides guidance for PyTorch-native agentic RL using torchforge, Meta's library separating infra from algorithms. Use when you want clean RL abstractions,…
Weekly trends analysis — compares community, GitHub, and financial metrics week-over-week to detect patterns, risks and opportunities. Use when user says…
Daily community pulse report — reads Discord AND WhatsApp messages from the last 24h, analyzes activity, sentiment, support questions, and top topics.…
Sync and update the community FAQ from Discord conversations, WhatsApp groups, and GitHub issues. Identifies recurring questions, adds new entries, and keeps…
Generate a concrete counterexample candidate that satisfies the target claim's stated scope while violating its conclusion or claimed structural property;…
Generate a deliberate pattern-breaking perturbation: PO, reversal, negation, random stimulus, exaggeration, or distortion.
Decompose a research question into MECE subquestions with coverage and independence arguments.
Method for calculating customer health/risk tiers using quantitative
Reference benchmarks for CAC, CPL, ROAS, and payback across channels
Use when defining or adjusting marketing-to-sales assignment rules.
Postgres performance optimization and best practices from Supabase. Use this skill when writing, reviewing, or optimizing Postgres queries, schema designs, or…
Comprehensive guide to writing effective, blameless postmortems that drive organizational learning and prevent incident recurrence.
A user may ask you to create, edit, or analyze the contents of a .pptx file. A .pptx file is essentially a ZIP archive containing XML files and other resources…
Diverga v12.0 setup wizard. 4-step researcher profile setup. Captures discipline, experience, tools, database access, and Agent Teams + VS Arena preference.…
Design and implementation of comprehensive simulation studies
Guide for creating and auditing DAAF skills (SKILL.md). Covers frontmatter, metadata vocabulary, progressive disclosure, decision trees, reference files. Use…
Evaluate scientific claims and evidence quality. Use for assessing experimental design validity, identifying biases and confounders, applying evidence grading…
⚠️ CRITICAL USER EXPERIENCE-BASED SKILL - ALWAYS CONSULT BEFORE DATA PREPROCESSING ⚠️ Prevents catastrophic errors (88.9% error rate in V1.0 case study)…
Write research/technical reports with strong structure + figure standards. Supports Markdown/HTML/PDF outputs (Quarto optional), executive summary, methods,…
© 2026 Flowy · Free and open source
Built for Claude Code · Not affiliated with Anthropic