Productivity

undermybelt Skill

Use when a task is multi-step, may span context resets or sessions, uses subagents, or risks losing state before completion.

undermybelt Bundle

Use when strict TDD is explicitly requested, or when an approved atomic implementation task has already chosen TDD Route strict.

undermybelt Skill

Django + Celery async task patterns — configuration, task design, beat scheduling, retries, canvas workflows, monitoring, and testing. Use when adding background jobs, scheduled tasks, or async processing to a Django app.

undermybelt Skill

Route for Spice decision runtime and `spice-hermes-bridge`. Use when the task mentions Spice, spice-runtime, Spice decision layer, spice-hermes-bridge, or Chinese triggers such as Spice 决策层、Spice 决策运行时、决策层 runtime.

undermybelt Skill

Route newly learned information into the right Hermes layer: repo doc, skill, memory, or session_search/L4. Use when deciding where a fact, workflow, correction, or task artifact should live after execution.

tomevault-io Bundle

Use this when starting any LOBSTER workflow -- planning, building, reviewing, testing, or coordinating a team of agents

tomevault-io Bundle

Personalize COG for your workflow - creates profile, interests, and watchlist files with guided setup (run this first!) Use when this capability is needed.

ferroxlabs Bundle

End-to-end workflow for building a professional photography portfolio from niche selection through shooting, editing, website creation, and client acquisition. Covers gear decisions, shooting technique, post-processing workflow, portfolio curation, online presence, and the transition from hobbyist to working photographer. Use when the user wants to build photography portfolio or needs a structured multi-step process for this goal. Do NOT use when the request is a single-step task or requires professional advice beyond educational guidance.

ferroxlabs Bundle

Designs a personal work context system that minimizes cognitive switching costs. Groups tasks by context, assigns time blocks, sets transition rules, and produces a context-optimized schedule. Use when the user asks about reducing context switching, batching similar work, minimizing distractions, or improving focus by grouping related tasks. Do NOT use for general time blocking (use time-blocking), email-specific management (use inbox-zero), or team workflow optimization (use business operations skills).

ferroxlabs Bundle

Navigate cross-cultural communication effectively using Hofstede's cultural dimensions, high vs low context frameworks, region-specific business etiquette, meeting and negotiation styles, gift-giving and dining protocols, trust-building strategies, and practical guidance for working across diverse cultural contexts. Use when the user asks about cross cultural communicator or needs help with related topics. Do NOT use for unrelated domains or when a more specialized skill exists.

ferroxlabs Bundle

Guided workflow for creating a comprehensive financial independence plan from current financial assessment through budgeting, investment strategy, tax optimization, and timeline projection. Covers the FIRE methodology adapted for individual circumstances and risk tolerances. Use when the user wants to financial independence plan or needs a structured multi-step process for this goal. Do NOT use when the request is a single-step task or requires professional advice beyond educational guidance.

ferroxlabs Bundle

Creates a filing system for household documents including financial records, legal documents, medical files, warranties, and ongoing paperwork. Covers physical filing structure, retention schedules by document type, and a workflow for processing incoming paper. Use when the user asks about organizing paperwork, setting up a filing system, document retention periods, or managing household paperwork flow. Do NOT use for digital file organization, business document management, or general decluttering (use decluttering-method).

ferroxlabs Bundle

Portfolio rebalancing education covering target allocation setting, drift threshold strategies, calendar vs threshold triggers, tax-efficient rebalancing methods, rebalancing across multiple account types, and behavioral coaching to maintain discipline through market volatility. Use when the user asks about portfolio rebalancing coach, related techniques, best practices, or needs guidance in this domain. Do NOT use when the request is outside the scope of portfolio rebalancing coach or requires a different specialized skill.

ferroxlabs Bundle

Designs personalized accountability systems for habit and goal maintenance, including accountability partner structures, check-in formats, commitment contracts, and progress reporting templates. Gathers the user's goals and social context, then produces a complete accountability framework with partner selection criteria, meeting agendas, and escalation protocols. Use when the user asks about accountability partners, staying accountable to goals, creating check-in systems, commitment devices, or building social support for habit change. Do NOT use for clinical supervision structures, addiction recovery sponsorship, or group therapy facilitation.

ferroxlabs Bundle

Comprehensive preparation workflow for system design interviews at top technology companies. Covers mastering fundamentals like scalability and distributed systems, learning common design patterns, structured practice with real problems, mock interviews with feedback, and peak performance strategies for interview day. Use when the user wants to ace system design interviews or needs a structured multi-step process for this goal. Do NOT use when the request is a single-step task or requires professional advice beyond educational guidance.

ferroxlabs Bundle

Guided workflow for building passive and semi-passive income streams from initial assessment and skill matching through building, automating, diversifying, and optimizing income-generating assets. Covers digital products, investments, and automated business models. Use when the user wants to create passive income streams or needs a structured multi-step process for this goal. Do NOT use when the request is a single-step task or requires professional advice beyond educational guidance.

ferroxlabs Bundle

Identifies a user's visual preferences from described examples, extracts the defining characteristics including color treatment, contrast, subject selection, and composition, and produces a personal photography style guide with specific settings targets. Applicable to any camera and processor. Use when the user asks to develop a photography style, create visual consistency, define their aesthetic, or build a cohesive portfolio look. Do NOT use for single-photo composition (use composition-guide), camera settings for a specific shot (use exposure-triangle), or photo editing steps (use photo-editing-workflow).

ferroxlabs Bundle

Structured workflow for selecting, preparing for, and passing a professional certification exam. Covers choosing the right certification for your career goals, building a study plan with spaced repetition, intensive exam preparation, test-day execution, and maintaining the certification with continuing education. Use when the user wants to get professional certification or needs a structured multi-step process for this goal. Do NOT use when the request is a single-step task or requires professional advice beyond educational guidance.

ferroxlabs Bundle

Design and facilitate effective meetings for distributed teams by choosing between async and synchronous formats, maximizing engagement across time zones, leveraging collaboration tools, and building meeting cultures that respect everyone's time Use when the user asks about distributed meeting facilitator, related techniques, best practices, or needs guidance in this domain. Do NOT use when the request is outside the scope of distributed meeting facilitator or requires a different specialized skill.

ferroxlabs Bundle

Systematic workflow for decomposing a monolithic application into microservices using the strangler fig pattern. Covers domain analysis, service extraction, inter-service communication, data ownership migration, deployment strategies, and the organizational changes needed to support a distributed architecture. Use when the user wants to migrate monolith to microservices or needs a structured multi-step process for this goal. Do NOT use when the request is a single-step task or requires professional advice beyond educational guidance.

paulasilvatech Skill

Transform lessons learned into domain-organized memory instructions for global or workspace scope. Use this skill when the user says /remember, asks to save a workflow lesson, records repeated mistakes, documents shortcuts or commands, discovers effective workflows, or wants durable VS Code memory instructions.

paulasilvatech Skill

Run an interactive task-refinement workflow before implementation by asking targeted questions, exploring the project, defining deliverables, and confirming success criteria. Use when the user asks to act informed, clarify before doing, plan with human input, or refine scope before execution. Requires Joyride human input support.

adu2021 Skill

Apply reinforcement learning to pre-training by framing next-token prediction as a reasoning task with verifiable rewards, achieving superior scaling compared to standard language modeling.

adu2021 Skill

Adapt web agents to new domains through targeted synthetic data generation and quality-aware refinement—identifying and correcting hallucinations while preserving task consistency to enable efficient adaptation with minimal human supervision.

adu2021 Skill

Synthesize diverse, verifiable training tasks by executing real tools first, then reverse-deriving tasks from execution traces. Ensure diversity across tools and reasoning patterns while maintaining grounding by construction.

adu2021 Skill

Synthesize unlimited verifiable training tasks from unverifiable text by converting reasoning passages into multiple-choice problems. Creates higher-quality training data for RLHF systems without requiring new human labels.

adu2021 Skill

Segment-level credit assignment for RL in LLMs using Monte Carlo advantage estimation, enabling precise reward attribution without critic models for improved reasoning task performance.

adu2021 Skill

Build robust reward models for computer-use agents by processing execution videos with spatiotemporal token pruning (STP+TTP) to remove redundancy while preserving task-relevant UI details. Achieve 84.7% accuracy with adversarial instruction translation.

undermybelt Skill

Use when evaluating or absorbing ideas from math-formalization agents such as MathCode into Hermes workflows. Activate when a task involves theorem proving, reusable theorem/axiom stores, subgoal decomposition, proof planning, Lean feedback loops, or tool/skill/plugin split for math work.

undermybelt Skill

数学建模竞赛工作流入口。用于启动完整建模流程：询问用户偏好，生成 plan.md 和 todo.md，并按阶段调用赛题分析、建模、代码与图表、流程图、论文撰写、验证验收等 skills。

undermybelt Skill

Operate notifications as one ECC-native workflow across GitHub, Linear, desktop alerts, hooks, and connected communication surfaces. Use when the real problem is alert routing, deduplication, escalation, or inbox collapse.

undermybelt Skill

Use when the user wants a task done much faster through parallel work, concurrent agents, batched tool calls, isolated worktrees, or many independent verification lanes without losing correctness.

undermybelt Bundle

Estimate the intrinsic value of a public company using DCF, relative (peer multiple) and sum-of-parts (SOTP) methods, then triangulate to an implied share price with upside/downside versus the current market price. Use this skill whenever the user asks: "what is AAPL worth", "valuation of NVDA", "fair value of TSLA", "intrinsic value", "DCF for MSFT", "build a DCF", "discounted cash flow", "WACC", "terminal value", "implied share price", "upside to fair value", "is X overvalued/undervalued", "relative valuation", "peer comparison valuation", "EV/EBITDA target", "SOTP", "sum of the parts", "how much is [company] worth", "price target from fundamentals", "value this company", or any ticker in the context of computing intrinsic or relative valuation. Default to running ALL three methods (DCF + relative + SOTP-if-applicable) and presenting a blended implied price with a sensitivity table. Do not answer valuation questions from memory — always run the workflow.

undermybelt Bundle

Create new skills, modify and improve existing skills, and measure skill performance. Use when users want to create a skill from scratch, update or optimize an existing skill, run evals to test a skill, benchmark skill performance with variance analysis, or iterate on skill quality. Triggers: "create a skill", "make a new skill", "build a skill for", "write a skill that", "skill for doing X", "I want a skill to", "new skill", "design a skill", "scaffold a skill", "improve this skill", "optimize this skill", "this skill isn't working well", "evaluate this skill", "score this skill", "how good is this skill", "run evals on", "benchmark this skill", "test this skill's quality", "skill quality", "skill performance". Also triggers when a user describes a repeatable workflow they want to automate, says "I keep doing X manually", "can you remember how to do X", or "turn this into a skill".

adu2021 Skill

Apply reinforcement learning to Vision-Language-Action models for robotic control, achieving 99% LIBERO task success and discovering novel manipulation strategies (pushcut) without task-specific reward engineering. Scales efficiently via parallelized trajectory sampling and outcome-based rewards.

adu2021 Skill

Discover that large pretrained models have dense neighborhoods of task-specific experts—random weight perturbations improve performance. Use RandOpt: sample perturbations, select top performers, ensemble via voting for multi-task adaptation.