Skills for your AI
Sends and receives cryptographically signed messages between AI agents using the AMP CLI, covering identity setup, sending, inbox checks, reading, replying, deleting, and status. Use when the user asks to set up agent messaging, send or reply to another agent,
Guides building LLM applications with LangChain, covering model setup, chains, ReAct agents, memory, RAG pipelines, structured output, and parallel/streaming execution. Use when a user wants to initialize a model or switch providers, build a chain, create a to
Prepares a company for audits by reviewing policies, assessing risks and controls, analyzing financial data, drafting auditor communications, and organizing documentation. Use when the user needs audit schedules, checklists, risk assessments, mock audits, mana
Generates personalized 250-400 word cover letters from a resume and job description, handling gaps, tone, and alternatives. Use when the user asks for a cover letter, application letter, or motivation letter for a specific role, or wants help with under/overqu
Converts a coding request into a single actionable plan with scope, checklist, and open questions. Use when the user asks for a plan for a coding task, wants a repo scanned before planning, or needs a scoped checklist of steps.
/cs:cross-eval <memo> — Multi-model consensus on a board memo or strategy brief. Claude + Codex + Gemini cross-review with graceful degradation. Use when a high-stakes memo needs an independent sanity check before the boardroom — e.g. a bet-the-company pivot o
Analyzes, compares, and recommends data structures for performance, memory, scalability, and integration needs, and provides optimization, validation, and reference guidance. Use when comparing complexity of operations, evaluating trade-offs for a scenario, op
Guides engineers in selecting, analyzing, and implementing data structures, from requirements clarification through trade-off evaluation, memory and scalability analysis, code generation, and optimization. Use when choosing a data structure, comparing performa
/cs:decide <memo> — Log a decision to two-layer memory via decision-logger. Approved memo becomes durable; raw transcripts kept for reference. Use when the founder has approved a boardroom memo and the decision must become durable company memory — e.g. right a
Prepares and organizes new hire onboarding materials, including paperwork checklists, schedules, policy explanations, IT guides, training plans, introductions, orientation content, checklists, buddy matches, and feedback surveys. Use when an HR manager needs o
Builds equipment maintenance programs — inspection checklists, lubrication and calibration schedules, filter and battery plans, safety testing, training and compliance reporting — from equipment lists, usage data and manufacturer specs. Use when the user needs
Compresses scattered notes, data and signals into a one-page executive decision memo with recommendation, tradeoffs, risks and next actions. Use when the user supplies raw material and asks for a decision memo, briefing memo, board paper, or a 3-minute executi
Detects system CPU, GPU, memory, and disk resources and recommends parallel processing, memory, GPU, and data-loading strategies for scientific computing tasks. Use when starting a compute-intensive task, checking available resources, or choosing between panda
One-time setup skill that builds a personalized inbox triage knowledge base via interactive interview. Interviews the user about their email patterns, business context, reply style, and priorities using grill-me discipline (one question at a time, forcing form
Runs a full inbox triage using the knowledge base created by the 'inbox-setup' skill. Light-intake by design (most invocations skip questions and run with KB-default preferences); asks at most 2 grill-me override questions when invocation is outside normal cad
Builds and manages lab equipment maintenance schedules, checklists, calibration plans, records, and compliance documents for laboratory technicians. Use when a technician needs inspection checklists, calibration intervals, cleaning or parts plans, maintenance
Searches conversation history and semantic memory to recall past discussions, decisions, and code symbols. Use when the user asks to recall prior context, find where something was discussed, or before starting a task that needs background from earlier sessions
Installs, configures, or uninstalls the memU long-term memory bridge for the host agent by following the packaged install or uninstall guide. Use when the user asks to install, set up, integrate, remove, or uninstall memU.
Completes the human-judgment steps of a NanoClaw v1 to v2 migration after the automated script runs, covering preflight, routing fixes, owner seeding, access policy, memory migration, container configs and fork customizations. Use when a user asks to finish a
Coordinates new-hire onboarding tasks including scheduling, welcome emails, checklists, IT setup, benefits explanations, introductions, training, mentoring, surveys, and exit or remote support. Use when an HR Director needs to plan orientation, draft onboardin
Generates customized client onboarding checklists with phases, owners, dependencies, acceptance criteria, and five milestone email templates for Consulting, SaaS, or Agency engagements. Use when the user requests a new or updated onboarding checklist or change
Guides integration of Flash Attention into PyTorch models for speed and memory gains, covering native SDPA, flash-attn, FP8 on H100, troubleshooting, benchmarking, and fit assessment. Use when a user asks to speed up or reduce memory of transformer attention,
Systematic performance profiling for Node.js, Python, and Go applications. Identifies CPU, memory, and I/O bottlenecks, generates flamegraphs, analyzes bundle sizes, optimizes database queries, runs load tests with k6 and Artillery. Always measures before and
Analyzes application performance data (CPU, memory, event loop, HTTP) to find bottlenecks and produce optimization recommendations. Use when asked to profile CPU or memory, detect leaks, measure event loop delay, instrument functions, or generate a performance
