Menu
SkillsMP a collecté 28 skills depuis foundryside-dev/hamlet. Ouvrez un skill pour examiner sa source et ses détails.
Affichage de 28 skills collectés sur 28.
This skill should be used when the user asks to "track work", "create an issue", "find something to work on", "what should I work on next", "triage bugs", "close an issue", "check what's blocked", "plan a milestone", "review sprint progress", "coordinate…
Langue du texte source : anglais
Use when orienting in an unfamiliar or large codebase and you want to avoid re-reading or grepping the whole source tree: answering "what calls X", "where is X defined", "what does X depend on", "what subsystem is X in", or "find the function/class/module…
Langue du texte source : anglais
Use when starting the HAMLET live-visualization stack — the townlet inference server plus the Vue frontend — to watch trained agents run from checkpoints in a browser.
Langue du texte source : anglais
Use when building Vue 3 components, creating dashboards, implementing forms, optimizing data-heavy interfaces, or making designs responsive. Mandates design tokens, accessibility, proper state management, error states, and template cleanliness for…
Langue du texte source : anglais
Use when scanning for or fixing trust-boundary / taint findings, when a `wardline scan` reports a defect, or when wiring wardline into an agent's edit-verify loop. Explains the scan -> explain -> fix-at-the-boundary -> rescan cycle and the baseline-vs-waiver…
Langue du texte source : anglais
Use when the user asks "what changed", "what breaks if I touch X", "what is the blast radius / change impact", "what should I re-verify before claiming done", "show the timeline / churn for this entity", or when working in a project that uses warpline for…
Langue du texte source : anglais
Use when assessing codebase architecture and you feel pressure to soften critique, lead with strengths, or frame problems diplomatically - provides evidence-based critical assessment resisting relationship and economic pressures
Langue du texte source : anglais
Use when cataloging technical debt under time pressure and tempted to explain choices instead of delivering document - enforces execution discipline with scoped delivery patterns for partial catalogs
Langue du texte source : anglais
Use when stakeholders pressure you to change technical priorities and you're tempted to compromise on security-first or call it synthesis - enforces risk-based prioritization over stakeholder preferences
Langue du texte source : anglais
Use when you have architecture documentation from system-archaeologist and need critical assessment, refactoring recommendations, or improvement prioritization - routes to appropriate architect specialist skills
Langue du texte source : anglais
Master A2C, A3C, SAC, TD3 - actor-critic methods for continuous control
Langue du texte source : anglais
Master ε-greedy, UCB, curiosity-driven, RND, intrinsic motivation exploration
Langue du texte source : anglais
Master Dyna-Q, MBPO, Dreamer - model-based RL with world models and planning
Langue du texte source : anglais
Master QMIX, MADDPG, CTDE - multi-agent learning with coordination and credit assignment
Langue du texte source : anglais
Master CQL, IQL, BCQ - offline RL from fixed datasets without environment interaction
Langue du texte source : anglais
Master REINFORCE, PPO, TRPO - direct policy optimization with trust regions
Langue du texte source : anglais
Master reward function design - potential-based shaping, hacking patterns, validation
Langue du texte source : anglais
Systematic RL debugging - diagnose learning failures, common bugs, diagnosis trees
Langue du texte source : anglais
Gym/gymnasium API - custom environments, spaces, wrappers, vectorization, debugging
Langue du texte source : anglais
Rigorous RL evaluation - statistical protocols, train/test discipline, metrics, generalization
Langue du texte source : anglais
Master RL theory - MDPs, value functions, Bellman equations, value/policy iteration, TD
Langue du texte source : anglais
Routes to appropriate deep-RL skills based on problem type and algorithm family
Langue du texte source : anglais
Master DQN, Double DQN, Dueling DQN, Rainbow - value-based methods for discrete actions
Langue du texte source : anglais
Analyze unfamiliar codebases systematically to produce subsystem catalog entries - emphasizes strict contract compliance and confidence marking
Langue du texte source : anglais
Synthesize subsystem catalogs and architecture diagrams into comprehensive, navigable architecture reports - codifies synthesis strategies and professional documentation patterns
Langue du texte source : anglais
Generate C4 architecture diagrams from subsystem catalogs - codifies abstraction strategies, notation conventions, and selection criteria
Langue du texte source : anglais
Use when analyzing existing codebases to generate architecture documentation - coordinates subagent-driven exploration with mandatory workspace structure, validation gates, and pressure-resistant workflows
Langue du texte source : anglais
Validate architecture artifacts against contracts and consistency requirements - codifies systematic validation practices with professional reporting
Langue du texte source : anglais