spec-execution
6-phase iterative specification execution workflow covering implementation, testing, review, improvement, commit, and progress tracking with quality-gated…
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.
6-phase iterative specification execution workflow covering implementation, testing, review, improvement, commit, and progress tracking with quality-gated…
Convert requirements into structured technical specifications with architecture decisions
Write feature specifications as requirements and user stories with acceptance criteria, focusing on business value and testable conditions.
Für Lieferfrist Teillieferung: prüft Frist, Form, Zuständigkeit und Eilbedarf; Ergebnis: Fristen- und Risikoampel.
Für Liquidated Damages: ordnet Norm, Beweislast und Gegenargument; Ergebnis: Prüfprodukt mit Risiko und nächstem Schritt.
Für Logistik Spedition AGB: ordnet Norm, Beweislast und Gegenargument; Ergebnis: Prüfprodukt mit Risiko und nächstem Schritt. Fachgebiet: AGB-Recht-Prüfer.…
Provides PyTorch-native distributed LLM pretraining using torchtitan with 4D parallelism (FSDP2, TP, PP, CP). Use when pretraining Llama 3.1, DeepSeek V3, or…
Provides guidance for mechanistic interpretability research using TransformerLens to inspect and manipulate transformer internals via HookPoints and activation…
Fine-tune LLMs using reinforcement learning with TRL - SFT for instruction tuning, DPO for preference alignment, PPO/GRPO for reward optimization, and reward…
Monthly community report — aggregates Discord and WhatsApp activity for the full month: MAM, growth, sentiment trends, top contributors, product insights, docs…
Weekly community analysis report — aggregates Discord AND WhatsApp activity, engagement metrics, sentiment trends, top contributors, product insights, and docs…
Analyze competitive landscape and market positioning. Use when user says 'competitive analysis', 'positioning', 'who are our competitors', 'benchmark', 'market…
Identify the limiting dimension or dependency currently constraining progress.
Identify the longest/limiting dependency path while accounting for resource contention and convergence points.
Identify the dominant framing/paradigm or governing variable constraining the current problem representation.
Use to catalog churn/expansion plays tied to specific signals, cohorts,
Use when designing filters, suppression logic, and personalization cohorts
Use to design and document customer segments with clear criteria, metrics,
Use when building apps that collect user data. Ensures privacy protections are built in from the start—data minimization, consent, encryption.
Essential tools and frameworks for modern product management, from discovery to delivery.
Expert guide on prompt engineering patterns, best practices, and optimization techniques. Use when user wants to improve prompts, learn prompting strategies,…
Full autonomous research workflow using swarm mode for parallel execution
Multi-agent review for research presentation slides in the sewage-house-prices project (visual, econometric fidelity, proofreading, substance). Use for…
Download, split, and deeply read academic PDFs. Use when asked to read, review, or summarize an academic paper. Splits PDFs into 4-page chunks, reads them in…
Create publication-quality scientific diagrams using Nano Banana Pro AI with smart iterative refinement. Uses Gemini 3 Pro for quality review. Only regenerates…
Build slide decks and presentations for research talks. Use this for making PowerPoint slides, conference presentations, seminar talks, research presentations,…
Create publication figures with matplotlib/seaborn/plotly. Multi-panel layouts, error bars, significance markers, colorblind-safe, export PDF/EPS/TIFF, for…
Plan implementation sprints with story selection, goal definition, and execution ordering.
STATE.md reading, writing, and field-level updates. Provides cross-session state persistence via .planning/STATE.md with structured fields for current task,…
Break technical specifications into small, implementable stories with dependency ordering
Für Logistik Spedition AGB: ordnet Norm, Beweislast und Gegenargument; Ergebnis: Prüfprodukt mit Risiko und nächstem Schritt. Fachgebiet: AGB-Recht-Prüfer.…
Für Mängelrechte 309: ordnet Norm, Beweislast und Gegenargument; Ergebnis: Prüfprodukt mit Risiko und nächstem Schritt.
Für Mahngebühren und Zinsanpassung AGB: ordnet Norm, Beweislast und Gegenargument; Ergebnis: Berechnungstabelle mit Annahmen und Kontrollfragen.
Expert guidance for fast fine-tuning with Unsloth - 2-5x faster training, 50-80% less memory, LoRA/QLoRA optimization
Provides guidance for training LLMs with reinforcement learning using verl (Volcano Engine RL). Use when implementing RLHF, GRPO, PPO, or other RL algorithms…
Serves LLMs with high throughput using vLLM's PagedAttention and continuous batching. Use when deploying production LLM APIs, optimizing inference…
Review and track OKRs progress. Use when user says 'OKR review', 'OKR progress', 'update OKRs', 'define quarterly OKRs', or any reference to objectives, key…
Generate weekly strategy digest consolidating financial, product, community, and market data into strategic insights. Use when user says 'strategy digest',…
Flush session to memory — review what happened, update markdowns, create session log
Identify paired parameters or requirements where improving one worsens another, and distinguish technical from physical contradictions.
Identify factors/assumptions/uncertainties whose change most strongly controls the conclusion.
Enumerate obstacles that block a target goal/direction, with type, evidence, and blocking relation.
Use to interpret qualitative feedback, trends, and risks across community
Process for capturing qualitative feedback and injecting it into CS playbooks.
Use when planning or drafting search-optimized content that balances keyword intent with GTM messaging.
Create Pydantic models following the multi-model pattern for clean API contracts.
Python development principles and decision-making. Framework selection, async patterns, type hints, project structure. Teaches thinking, not copying.
Implement comprehensive testing strategies with pytest, fixtures, mocking, and test-driven development. Use when writing Python tests, setting up test suites,…
© 2026 Flowy · Free and open source
Built for Claude Code · Not affiliated with Anthropic