Product & Planning

paulpas Skill

Implements Google's Agent-to-Agent (A2A) protocol for cross-framework agent communication using HTTP-based JSON-RPC 2.0 with agent card discovery, SSE streaming, and secure multi-agent interoperability patterns.

anhvu1107 Bundle

ALWAYS use this when the request matches Filesystem Context: Use for file-based context management, dynamic context discovery, and reducing context window bloat.

paulpas Skill

Constructs agent-centric knowledge graphs representing tools, capabilities, and their relationships for intelligent tool discovery during planning.

paulpas Skill

Implements proactive agent exploration patterns for discovering unknown opportunities, generating hypotheses, designing experiments, and sharing findings through autonomous research loops beyond predefined optimization targets.

paulpas Skill

Maximizes the value of a chosen technology or framework through progressive adoption strategies, feature discovery patterns, integration anti-pattern avoidance, and optimization techniques for sustainable long-term utilization.

paulpas Skill

Implements microservices architecture patterns, including service discovery, inter-service communication, and data management techniques.

paulpas Skill

Engineers precision trigger sets for AI agent skills using two-tier discovery patterns, anti-trigger calibration, archetype alignment, and hybrid scoring optimization to maximize auto-loading accuracy while minimizing false positive rates.

paulpas Skill

Implements causal models, directed acyclic graphs (DAGs), confounding adjustment, and mediation analysis for causal discovery

paulpas Skill

Implements intelligent message queue troubleshooting for Kafka, RabbitMQ, SQS, and NATS clusters with diagnostic commands, dead letter handling, and backlog resolution

anhvu1107 Bundle

ALWAYS use this when the request matches Idea OS: Five-phase pipeline (triage → clarify → research → PRD → plan) that turns a raw idea into four linked files: clarifying questions, deep research, a PRD with non-goals and metrics, and a phased execution plan with mermaid user journey and kill criteria.

anhvu1107 Bundle

ALWAYS use this when the request matches Loki Mode: Version 2.35.0 | PRD to Production | Zero Human Intervention > Research-enhanced: OpenAI SDK, DeepMind, Anthropic, AWS Bedrock, Agent SDK, HN Production (2025)

anhvu1107 Bundle

ALWAYS use this when the request matches Vexor CLI: Semantic file discovery via `vexor`.

anhvu1107 Bundle

ALWAYS use this when the request matches EXA Search: Semantic search, similar content discovery, and structured research using Exa API.

paulpas Skill

Applies YAGNI to project planning and backlog management to prevent scope creep, enforce MVP boundaries, and reject features not needed for current delivery goals.

paulpas Skill

Implements intelligent apify influencer discovery with multi-factor skill selection, fallback chains, and adherence to the 5 Laws of Elegant Defense

adu2021 Skill

Combine NFVP4 quantization with LoRA to accelerate RL rollout phases while using quantization noise as implicit exploration bonus. Achieve 1.5x speedup and better strategy discovery through noise-enhanced policy entropy.

adu2021 Skill

Build effective retrieval systems for deep research agents by understanding query-retriever mismatch, preferring BM25 for keyword-oriented queries, and augmenting corpus documents with metadata and LLM-generated keywords to improve information discovery.

adu2021 Skill

Train LLMs for multi-turn tool-integrated reasoning end-to-end using RL without supervised pretraining. SimpleTIR stabilizes training by filtering void turns (responses lacking code blocks or final answers) to prevent gradient explosion from distributional drift, enabling discovery of emergent reasoning patterns like self-correction and cross-validation on mathematical benchmarks.

adu2021 Skill

Automatically discovers optimal in-context learning prompts through evolutionary token pruning that removes redundant demonstrations to create effective 'gibberish' prompts. Matches state-of-the-art optimization with low-data regimes. Use for automated prompt discovery without manual tuning or human expertise.

adu2021 Skill

Evaluate LLM agents on realistic tool-use tasks via 28 live MCP servers with 250 tools, assessing fuzzy tool discovery, multi-step planning, and cross-domain workflow coordination

adu2021 Skill

Convert natural language to SQL for unknown database schemas by formulating the task as a partially observable MDP. Use dual-track GRPO (token-level masked advantages) to learn schema discovery and query generation jointly.

nota-america Skill

Update, create, or reprioritize your product roadmap. Use when adding a new initiative and deciding what moves to make room, shifting priorities after new information comes in, moving timelines due to a dependency slip, or building a Now/Next/Later view from scratch.

nota-america Skill

Plan a sprint — scope work, estimate capacity, set goals, and draft a sprint plan. Use when kicking off a new sprint, sizing a backlog against team availability (accounting for PTO and meetings), deciding what's P0 vs. stretch, or handling carryover from the last sprint.

nota-america Skill

Generate a stakeholder update tailored to audience and cadence. Use when writing a weekly or monthly status for leadership, announcing a launch, escalating a risk or blocker, or translating the same progress into exec-brief, engineering-detail, or customer-facing versions.

nota-america Skill

Synthesize user research from interviews, surveys, and feedback into structured insights. Use when you have a pile of interview notes, survey responses, or support tickets to make sense of, need to extract themes and rank findings by frequency and impact, or want to turn raw feedback into roadmap recommendations.

undermybelt Skill

Use the reviewed local bpc-fetch source as an optional article discovery, supported-site lookup, and authorized article-export CLI wrapper. Activate when the user mentions bpc-fetch, Bypass Paywalls Clean, paywall article discovery, supported paywall sites, batch article export, 付费墙抓取, 绕过付费墙, 新闻文章批量抓取, or article-to-Markdown workflows.

undermybelt Bundle

Use when doing research or knowledge-work from Hermes: arXiv discovery, prediction-market data, wiki/markdown knowledge bases, Obsidian notes, or DSPy-style research/prototyping of LM programs.

undermybelt Skill

Guides collaborative requirements discovery before implementation. Creates task directory, seeds PRD, asks high-value questions one at a time, researches technical choices, and converges on MVP scope. Use when requirements are unclear, there are multiple valid approaches, or the user describes a new feature or complex task.

ferroxlabs Bundle

Produces a complete client onboarding workflow including discovery call agenda, contract checklist, kickoff document, communication expectations, and first deliverable timeline. Creates a reusable onboarding process document. Use when the user needs to onboard a new freelance or consulting client, create a structured onboarding process, or set up a new client engagement with clear expectations and milestones. Do NOT use for employee onboarding (use HR skills), project kickoff for internal teams (use project management skills), or writing client proposals (use freelance-proposal-writer).

ferroxlabs Bundle

Synthesizes Debt Snowball, Debt Avalanche, Debt Consolidation, and Balance Transfer strategies into The Debt Freedom Roadmap - a systematic approach to eliminating debt based on your financial profile and psychology. Use when the user asks about debt elimination strategist, related techniques, best practices, or needs guidance in this domain. Do NOT use when the request is outside the scope of debt elimination strategist or requires a different specialized skill.

ferroxlabs Bundle

Engineering management practices covering one-on-one meetings, performance reviews, team building, hiring, conflict resolution, career development frameworks, sprint planning, technical debt management, and stakeholder communication. Includes templates for 1:1 agendas, performance feedback, team health assessments, and org design. Use when the user asks about engineering manager toolkit, related techniques, best practices, or needs guidance in this domain. Do NOT use when the request is outside the scope of engineering manager toolkit or requires a different specialized skill.

ferroxlabs Bundle

Plans community environmental projects from concept to launch, covering stakeholder identification, goal setting, action planning, volunteer coordination, and impact measurement. Gathers the user's community context, environmental concern, and available resources to produce a structured project plan with timeline, roles, and measurable outcomes. Use when the user asks about starting a community environmental project, organizing a neighborhood cleanup, planning a community garden, building a conservation coalition, or measuring community environmental impact. Do NOT use for lobbying or political campaign strategy, large-scale nonprofit management, environmental policy analysis (use environmental-policy-researcher), individual personal sustainability actions (use other sustainability skills), or corporate sustainability programs.

ferroxlabs Bundle

Teaches the process of researching and evaluating environmental policy at local, state, and federal levels. Provides a structured research framework for identifying active legislation, understanding policy mechanisms, evaluating stakeholder positions, and forming evidence-based personal positions. Teaches HOW to research and evaluate policy, not which policies to support. Use when the user asks about researching environmental legislation, understanding environmental policy mechanisms, evaluating environmental proposals, or engaging with environmental policy as an informed citizen. Do NOT use for recommending specific policy positions, lobbying or campaign strategy, climate science education (use climate-science-explainer), personal sustainability actions (use other sustainability skills), or business regulatory compliance.

ferroxlabs Bundle

Builds a sport-agnostic skill progression plan using assessment, skill decomposition, drill progression, milestone marking, and reassessment cycles. Gathers the user's chosen sport, current level, and goals to produce a structured skill ladder with drills, practice schedules, and measurable milestones. Use when the user asks about improving at a specific sport, building a practice plan for athletic skills, creating a skill development roadmap, or structuring deliberate practice for any sport. Do NOT use for team coaching or managing other athletes, professional/competitive training periodization, injury rehabilitation programs, or general fitness without a sport-specific skill focus (use health-wellness skills instead).

ferroxlabs Bundle

Structured digital transformation readiness evaluation covering current digital maturity, capability gaps, change management preparedness, technology stack assessment, and producing an actionable transformation roadmap. Use when the user asks about digital transformation readiness, related techniques, best practices, or needs guidance in this domain. Do NOT use when the request is outside the scope of digital transformation readiness or requires a different specialized skill.

ferroxlabs Bundle

Cloud infrastructure maturity evaluation assessing automation, resilience, security, observability, and cost optimization to produce a maturity level scorecard with a roadmap. Use when the user asks about infrastructure maturity assessment, related techniques, best practices, or needs guidance in this domain. Do NOT use when the request is outside the scope of infrastructure maturity assessment or requires a different specialized skill.