hellsan631-skills

Plugin hellsan631-skills from marketplace hellsan631 in hellsan631/skills. Commands read from the repo's manifest — yesterday.

Skills (35)

• game-ui-design

  Use when designing or redesigning game HUDs, menus, inventories, character screens, maps, progression screens, or results screens; when making text-heavy game UI more visual; when creating composition, art direction, visual hierarchy, and interaction storyboards.

• game-visual-identity

  Develops a recognizable visual identity for video game characters, icons, items, and related art. Use to align global game design pillars with local asset-family pillars, explore art directions, interpret visual references, or extend an established asset family. Focuses on asset appearance and consi

• midjourney-prompting

  Use when the user requests Midjourney prompts, reference and model setup, guided image generation, or revisions based on generated results. Adapts prompts to the selected model and prepares them for user submission, then critiques returned images.

• principal-game-designer

  Use when drafting a game system's design, revising one, critiquing a design document, or checking whether a spec is buildable.

• visual-identity-grilling

  Use when the user wants to quickly iterate on game visual identity through challenging questions and rendered comparisons, or asks to combine grilling with character, icon, or asset-family design.

• blast-radius

  Use for 'blast radius of X', 'what could this break', or when reviewing a small diff you do not trust. Trace breakage beyond the diff and prove the fact the change's safety depends on by running real code.

• codebase-design

  Use when designing or improving a module's interface, when deciding where a seam goes, when code needs to be more testable or navigable, or when another skill needs the deep-module vocabulary of depth, seams, adapters, leverage, and locality.

• domain-modeling

  Use when codebase terminology is in dispute, when writing or editing a CONTEXT.md, or when recording an ADR. Builds and sharpens the project's domain model as terms settle.

• how

  Use for \"how does X work\", subsystem architecture, runtime flow, onboarding mental models, code walkthroughs before changing something, architectural critique, and placement / ownership / layering questions (\"where should this live\", \"which package owns this\", \"is this the right layer\"). Use

• improve-codebase-architecture

  Use when a codebase has architectural friction and the user wants refactoring options. Finds deepening opportunities, presents them in a visual HTML report, then explores the selected candidate through the grilling decision tree.

• prototype

  Use when you need to sanity-check a state model or interaction before building it, or when you need to decide what a UI should look like. Builds a throwaway prototype to answer the question.

• research

  Use when a topic needs researching, when docs or API facts need gathering, or when reading legwork should go to a background agent. Investigates against primary sources and leaves the findings in the repo.

• setup-engineering-skills

  Configure this repo for the engineering skills: set up its issue tracker, triage label vocabulary, and domain doc layout. Run once before first use of the other engineering skills.

• why

  Use for 'why does X work this way', 'why we picked Y', design rationale, regressions, postmortems, or data-backed thresholds. Discovers available MCPs and searches each evidence category (source control, issue tracker, long-form docs, real-time chat, infrastructure observability, error tracking, pro

• wizard

  Use when provisioning infrastructure, setting up credentials or CI secrets, walking an unfamiliar third-party dashboard, or running a one-off migration or cutover. Generates an interactive bash wizard for the steps only a human can do.

• principle-boundary-discipline

  Apply when wiring validation, error handling, or framework adapters. Put guards at system boundaries such as the CLI, config, network, and external APIs. Trust internal types, and keep business logic in pure functions.

• principle-build-the-lever

  Apply to any non-trivial work, whether one-off or bulk, including edits, migrations, analyses, and checks. Build a codemod, script, generator, or skill for subagents that does or proves the work. The resulting file gives reviewers something they can rerun.

• principle-encode-lessons-in-structure

  Apply when you write the same instruction a second time or notice a recurring correction. Replace repeated text with a lint, metadata flag, runtime check, or script.

• principle-experience-first

  Apply when product, UX, or feature-scope tradeoffs arise. Favor user delight when it conflicts with implementation convenience. Ship fewer features at a polished level.

• principle-guard-the-context-window

  Apply when large outputs, long files, repeated reads, or fan-out planning fill the context. Send bulk material to subagents. Keep summaries in the main thread and raw payloads out.

• principle-laziness-protocol

  Apply while refactoring, evaluating diff size, or considering adding abstractions, layers, or signal threading. Prefer deletion and make the smallest change that solves the problem.

• principle-outcome-oriented-execution

  Apply during planned rewrites and migrations with explicit phase boundaries. Accept intermediate breakage only after planning and scoping it and confirming that you can reverse it. Move toward the target architecture without adding throwaway compatibility code to smooth those phases.

• principle-prove-it-works

  Apply after completing a task and before declaring it done. Verify the real artifact by running the feature, reading the actual value, or inspecting the diff. Proxies, self-reports, and successful compilation do not prove the task works.

• principle-redesign-from-first-principles

  Apply when integrating a new requirement into an existing design. Rework the design under the assumption that the requirement existed on day one.

• principle-separate-before-serializing-shared-state

  Apply when concurrent actors might write to the same file, branch, key, or state object. First remove the shared write target. Serialize structurally only when one shared writer is a real invariant.

• arena

  Spawn N parallel candidates for the same task, pick a base, and graft the strongest parts of the others into it. Use for /arena, 'arena this', 'throw it in the arena', or when one attempt at a non-trivial artifact could lock in the wrong shape.

• brainstorm-skill-ideas

  Use when the user asks for skill ideas drawn from a chat history, the current conversation, or past chats. Proposes up to five skills, each with the moment that suggests it, how it would help, and how to make it better.

• bro

  Use when a reply is dense, jargon-heavy, or hard to follow. Restates the last message in plain language.

• grill-with-docs

  Use when a plan needs stress-testing and you need to record each answer as it arrives. Runs the grilling interview and records its answers as ADRs and glossary entries.

• grilling

  Use when a plan, decision, or idea needs stress-testing, or when the user asks you to grill them. Challenges its assumptions and decisions to expose their weak points.

• show-me-your-work

  Use for /show-me-your-work, autonomous or multi-phase runs, long-running or unattended work, or work a human reviews after stepping away. Keeps a TSV decision log with one row per decision covering what, why, evidence, and result. Leaves the log local by default and commits it when a reviewer needs

• wayfinder

  Use when a piece of work is too large for one agent session to hold. Plans the work as a shared map of decision tickets on the issue tracker, then resolves them one at a time until the route is clear.

• humanize

  Use when asked to humanize or de-slop text, and before delivering a draft anyone will publish or share. Strips AI tells from prose and verifies the result with a deterministic checker.

• unslop

  Use while writing any prose, in a chat reply or a file. Always applies.

• writing-for-agents

  Use when creating or editing a skill, or when modifying AGENTS.md or CLAUDE.md.

Similar plugins