Use when starting feature work that needs isolation from current workspace or before executing implementation plans - creates isolated git worktrees with smart directory selection…
Score 70/100
Creates comprehensive implementation plans with exact file paths, complete code examples, and verification steps for engineers with zero codebase context.
Score 70/100
Helps prepare and submit popcorn-cli GPU Mode solutions. Use when users ask to set up a project, create a submission template, or run/register submissions.
Score 70/100
Automate Poptin tasks via Rube MCP (Composio). Always search tools first for current schemas.
Score 70/100
Provides real-world API endpoint examples and specifications from well-known platforms and domain-specific systems.
Score 70/100
54 production-quality design systems extracted from real websites. Load a template to generate HTML/CSS that matches the visual identity of sites like Stripe, Linear, Vercel,…
Score 70/100
Stratify patient populations by risk level using claims data, clinical data, and social determinants to prioritize care management interventions
Score 70/100
Consensus cell type annotation: runs 10+ algorithms (KNN-Harmony/BBKNN/Scanorama/scVI, CellTypist, ONCLASS, Random Forest, SCANVI, SVM, XGBoost) on a labeled reference and…
Score 70/100
Helps design port traits and adapter implementations for external dependencies. Activates when users need to abstract away databases, APIs, or other external systems.
Score 70/100
Automatically allocate and manage development server ports, avoiding port conflicts between multiple Claude Code instances
Score 70/100
Keep the universal skill compact yet discoverable by loading minimal frontmatter first and heavy content on demand.
Score 70/100
Use when gathering requirements for a customer portal, partner community, or self-service Experience Cloud site.
Score 70/100
Report portfolio real-time con PnL, posizioni attive, cash, stato strategie. Use when user says "portfolio", "posizioni", "quanto ho", "stato portafoglio", "balance".
Score 70/100
Review investment portfolios for risk, diversification, fees. Asset allocation recommendations, tax-loss harvesting, rebalancing.
Score 70/100
Compose Unicode pose variants by swapping localized fragments so each expression shares the same base silhouette and spacing.
Score 70/100
Bepaal je marktpositie met Blue Ocean Strategy, ERRC Grid en Six Paths Framework. Van concurrentieanalyse tot positioneringsstatement.
Score 70/100
Universal post-commit actions. CHANGELOG update and git tag for all repos. Plugin version bumping for marketplace repos. Triggered after any code commit (except wip/amend/undo).
Score 70/100
Generate a Twitter/X post highlighting a Forge feature. Use when the user asks to write a tweet, create a Twitter post, or promote a ForgeCode feature on social media.
Score 70/100
Generate realistic coach/player interview responses for wins, losses, controversies, injuries. Authentic coachspeak and player personalities.
Score 70/100
Update repository documentation after code implementation. Maintains README, CHANGELOG, docs/ folder, and inline docstrings based on changes made.
Score 70/100
Post-recording cleanup for minutes — wait for processing, update title from calendar, identify speakers, re-ingest knowledge base, add action items to reminders.
Score 70/100
Analisi post-mortem della giornata di trading. PnL, WR per strategia e citta', skip reasons, filtri, raccomandazioni. Aggiorna memoria persistente.
Score 70/100
Analyze failures and suboptimal deliveries to identify root causes, contributing factors, and raw lessons.
Score 70/100
Runs the full post-plan workflow. Refine plan, create Linear issues, setup CLAUDE.md. Use after /plan-project produces a v1 plan. Pauses between phases for optional review.
Score 70/100
Run automated post-release workflow (eval baselines, dashboard, docs) for AILANG releases. Runs the tier-based benchmark suite (core+stretch by default) for standard + agent evals…
Score 70/100
Create tiered post-show follow-up email sequences to convert leads into pipeline.
Score 70/100
Suit la récupération après une opération chirurgicale avec suivi des symptômes, douleurs, cicatrisation et rendez-vous.
Score 70/100
Expert guidance for GRPO/RL fine-tuning with TRL for reasoning and task-specific model training
Score 70/100
Provides guidance for enterprise-grade RL training using miles, a production-ready fork of slime. Use when training large MoE models with FP8/INT4, needing train-inference…
Score 70/100
Simple Preference Optimization for LLM alignment. Reference-free alternative to DPO with better performance (+6.4 points on AlpacaEval 2.0).
Score 70/100
Provides guidance for LLM post-training with RL using slime, a Megatron+SGLang framework. Use when training GLM models, implementing custom data generation workflows, or needing…
Score 70/100
Fine-tune LLMs using reinforcement learning with TRL - SFT for instruction tuning, DPO for preference alignment, PPO/GRPO for reward optimization, and reward model training.
Score 70/100
Provides guidance for training LLMs with reinforcement learning using verl (Volcano Engine RL). Use when implementing RLHF, GRPO, PPO, or other RL algorithms for LLM post-training…
Score 70/100
Use when the user wants to post a tweet, reply to a tweet, quote tweet, or publish a note tweet (long-form, up to 25,000 characters) on X (Twitter).
Score 70/100
Proves actions worked in reality — not just exit code 0, not just logs — by validating actual observable outcomes in the system
Score 70/100
PostCSS best practices and configuration guidelines for modern CSS processing and optimization
Score 70/100
Use poster layout planner for other workflows that need structured execution, explicit assumptions, and clear output boundaries.
Score 70/100
Automate Postgrid tasks via Rube MCP (Composio). Always search tools first for current schemas.
Score 70/100
Automate Postgrid Verify tasks via Rube MCP (Composio). Always search tools first for current schemas.
Score 70/100
Automate PostHog tasks via Rube MCP (Composio): events, feature flags, projects, user profiles, annotations. Always search tools first for current schemas.
Score 70/100
Diagnose and fix common PostHog errors: events not appearing, flags returning undefined, 401/429 errors, SDK initialization failures, and identity issues.
Score 70/100
Implement PostHog product analytics: event capture, user identification, group analytics, and property management using posthog-js and posthog-node.
Score 70/100
Optimize PostHog costs: autocapture tuning, event sampling with before_send, bot filtering, session recording sampling, and billing monitoring.
Score 70/100
PostHog PII handling, GDPR compliance, consent management, data deletion, property sanitization, and privacy-safe analytics configuration.
Score 70/100
PostHog enterprise access control: organization/project hierarchy, member roles, scoped API keys, SSO/SAML configuration, and activity audit logging.
Score 70/100
PostHog incident response: triage decision tree, immediate actions for 401/429/500 errors, graceful degradation, evidence collection, and postmortem.
Score 70/100
Install and configure PostHog SDKs with authentication. Use when setting up posthog-js (browser), posthog-node (server), or configuring API keys for a new PostHog integration.
Score 70/100
Migrate to PostHog from Google Analytics, Mixpanel, Amplitude, or Segment. Covers dual-write strategy, historical data import, event name mapping, identity resolution, and feature…
Score 70/100
Configure PostHog across development, staging, and production environments. Separate PostHog projects per environment, environment-specific SDK config, feature flag rollout per…
Score 70/100
Monitor PostHog integration health: event ingestion rates, feature flag evaluation latency, billing volume tracking, and Prometheus/Grafana alerting.
Score 70/100
Production readiness checklist for PostHog integrations: SDK configuration, graceful degradation, health checks, shutdown hooks, and rollback procedures.
Score 70/100
Upgrade posthog-js and posthog-node SDKs with breaking change detection. Covers v4 to v5 posthog-node migration (sendFeatureFlags change), posthog-js autocapture API changes, and…
Score 70/100
Implement PostHog webhook destinations, Action-triggered notifications, and event querying via the Events API and HogQL.
Score 70/100
A modern, open-source HTTP client built as a terminal UI application. Posting provides a Postman-like experience entirely in the terminal, with keyboard-centric workflows,…
Score 70/100
Automate Postmark email delivery tasks via Rube MCP (Composio): send templated emails, manage templates, monitor delivery stats and bounces.
Score 70/100
Receive and process Postmark webhooks. Use when setting up Postmark webhook handlers, handling email delivery events, processing bounces, opens, clicks, spam complaints, or…
Score 70/100
postmark.js is the official Node.js library for the Postmark API, used to send transactional email, templates, and message streams from code.
Score 70/100
Write a postmortem for a regression or incident that escaped to production, broke real users, and traces back to a design flaw worth documenting.
Score 70/100
Run a lightweight, blame-free postmortem after an incident, failed launch, or missed deadline — for one person.
Score 70/100
Comprehensive guide to writing effective, blameless postmortems that drive organizational learning and prevent incident recurrence.
Score 70/100