all publishers

samhvw8

@samhvw8 source repo

17 published skills

  1. ▌
    Mise Expert 2 · samhvw8
    Mise development environment manager (asdf + direnv + make replacement). Capabilities: tool version management (node, python, go, ruby, rust), environment variables, task runners, project-local configs, backend selection (aqua, github, core, cargo, npm, pipx), security verification (cosign, SLSA, GitHub attestations, minisign). Actions: install, manage, configure, run tools/tasks with mise, troubleshoot attestation failures, migrate backends. Keywords: mise, mise.toml, tool version, runtime version, node, python, go, ruby, rust, asdf, direnv, task runner, environment variables, version manager, .tool-versions, mise install, mise use, mise run, mise tasks, project config, global config, aqua backend, github backend, ubi deprecated, MISE_AQUA_COSIGN, MISE_AQUA_GITHUB_ATTESTATIONS, attestation verification failed, cosign, SLSA, uv astral-sh. Use when: installing runtime versions, managing tool versions, setting up dev environments, creating task runners, replacing asdf/direnv/make, configuring project-local tool
    1 install
  2. ▌
    Frontend Audit 2 · samhvw8 bundle
    Visual design verification loop for matching a goal PNG to a live render. Use when the user shares a design mock / goal image and asks to match the UI to it, asks to "iterate on this design" or "match this 1:1", or calls out visual drift in a previous UI iteration. Provides histogram color sampling, shape inspection (radius/border/shadow/bg-mode/fill-vs-context), computed-style checking on the live render, snap, and side-by-side diff. After every UI change the assistant MUST snap the live render and Read the snap with the Read tool before reporting the change done — skipping that is the
    0 installs
  3. ▌
    Frontend Audit · samhvw8 bundle
    Visual design verification loop for matching a goal PNG to a live render. Use when the user shares a design mock / goal image and asks to match the UI to it, asks to "iterate on this design" or "match this 1:1", or calls out visual drift in a previous UI iteration. Provides histogram color sampling, shape inspection (radius/border/shadow/bg-mode/fill-vs-context), computed-style checking on the live render, snap, and side-by-side diff. After every UI change the assistant MUST snap the live render and Read the snap with the Read tool before reporting the change done — skipping that is the
    3 installs
  4. ▌
    Claude Ecosystem · samhvw8 bundle
    ALWAYS invoke this skill when the user asks about Claude Code features, configuration, extensibility, or project setup. ALWAYS invoke when the user wants to create, improve, or refine a Claude Agent Skill — including 'make this a skill', 'turn this into a skill', 'create a skill for X', or asks about SKILL.md authoring, frontmatter, description optimization, progressive disclosure, or triggering strategy. Modules: CLI tool (setup, slash commands, MCP servers, hooks, plugins, CI/CD), extensibility (agents, skills, output styles), CLAUDE.md (project instructions, optimization). Keywords: Claude Code, skill, SKILL.md, agent, hook, plugin, MCP, CLAUDE.md, skill architecture, description optimization, progressive disclosure. For skill body content quality (soul, tensions, mental models), also invoke prompt-architect. Do NOT use for general prompt engineering without a Claude Code context.
    2 installs
  5. ▌
    Debate · samhvw8
    Live multi-agent debate. Spawns named teammates (agent teams) that argue WITH EACH OTHER directly via SendMessage — a real, persistent debate, not one agent simulating both sides in a single reply. Heuristic: use teammates when the agents need to talk to each other (debate, collaborative brainstorm, hand-offs); use parallel subagents when they don't (independent fan-out). Keywords: debate, debate this, argue both sides, pressure-test, pressure test, steelman, devil's advocate, red team, red-team, challenge this, dialectic, adversarial review, two advocates, for and against, attack this idea. Use when: user types /debate, says 'debate this', 'argue both sides', 'pressure-test this decision', or wants a high-stakes call stress-tested by opposing positions that engage each other live. Requires the MAIN session (a subagent cannot spawn teammates) and CLAUDE_CODE_EXPERIMENTAL_AGENT_TEAMS=1. Do NOT use for: simple questions, mechanical tasks, or when one analysis suffices.
    1 install
  6. ▌
    Pug UI · samhvw8 bundle
    Generate single-file HTML UIs, reports, dashboards, and landing pages using Pug syntax compiled client-side. Four CSS framework presets (Pico CSS classless default, Bulma, daisyUI, Simple.css minimal) — all pre-themed with Claude Code's warm cream + terra cotta light palette. Reduces LLM output tokens by 70-85% vs raw HTML + Tailwind. ALWAYS invoke when the user asks to create an HTML page, report, dashboard, UI mockup, or single-file web deliverable. Also invoke when user says "make a page", "create a report", "build a dashboard", "html output", "web UI", "single-file HTML", or "pug". Do NOT use for React/Vue/Svelte component development or server-rendered templates.
    1 install
  7. ▌
    Council · samhvw8
    Live collaborative brainstorm. Spawns named teammates (agent teams) that BUILD ON EACH OTHER'S ideas directly via SendMessage — generative cross-pollination ('yes, and…'), not one agent listing ideas alone and not an adversarial debate. Heuristic: use teammates when the agents need to talk to each other (build on ideas, hand-offs, debate); use parallel subagents when they don't (independent fan-out). Keywords: council, collaborative brainstorm, brainstorm together, ideate together, build on ideas, expand ideas, expand on this, riff together, group ideation, how might we, what could we build, team brainstorm. Use when: user types /council, says 'brainstorm together', 'expand on this idea', 'ideate as a team', or wants an open question explored by diverse perspectives that compound each other's ideas live. Requires the MAIN session (a subagent cannot spawn teammates) and CLAUDE_CODE_EXPERIMENTAL_AGENT_TEAMS=1. Do NOT use for: a quick idea list (use solo agents), deciding between options (use /debate), mechanica
    4 installs
  8. ▌
    Deep Gather · samhvw8 bundle
    Deep internet gathering — the search-fetch loop, query templates, multi-source/GitHub patterns, and retrieval tools. ONE job: collect raw sources and data from the internet on an assigned topic/language. Run standalone to deep-gather a topic, or as the GATHER-DATA step of lead-researcher's research loop. Does NOT reason, steer, or synthesize — that is lead-researcher's brain. Triggers: 'deep gather', 'gather sources/data on X', 'collect everything about Y'.
    4 installs
  9. ▌
    Heavy Think · samhvw8 bundle
    Unified heavy thinking orchestrator. Classifies problem type → dispatches to the right parallel thinking pattern. Modes: brainstorm (divergent ideation — solo agents or a collaborative team 'council'), solve (verifiable answers), decompose (break complex problems), unstick (reframe blockages), debate (live agent-team debate — named teammates argue with each other via SendMessage, then YOU synthesize). All modes use parallel agents/teammates with model=opus for maximum reasoning depth, then YOU synthesize. Teammates vs subagents: use agent-team teammates when the agents need to talk to each other (debate, collaborative brainstorm, hand-offs); use parallel subagents when they don't (independent fan-out). Actions: think deeply, brainstorm, council, decompose, solve, unstick, analyze, debate. Keywords: heavy think, heavy thinking, think harder, brainstorm, council, collaborative brainstorm, brainstorm together, build on ideas, expand ideas, ideate together, decompose, break down, stuck, unstick, solve, debate, de
    1 install
  10. ▌
    Github Search · samhvw8
    Search GitHub for repos, code, and usage examples using gh CLI. Capabilities: repo discovery, code search, finding library usage patterns, issue/PR search. Actions: search, find, discover repos/code/examples. Keywords: gh, github, search repos, search code, find examples, how to use library, stars, language filter. Use when: finding repositories, searching code patterns, discovering how libraries are used, exploring open source.
    2 installs
  11. ▌
    Lead Researcher · samhvw8 bundle
    MANDATORY entry point for ALL research tasks. Orchestrates gatherer agents — brain decides agent count, languages, iterations, and depth at runtime based on the actual question. Default languages: EN + ZH + ZH-TW. Triggers: any research request, 'research X', 'what's the best', 'compare X vs Y', 'how should I approach', 'evaluate X', 'deep research', 'comprehensive analysis', 'team research' (live supervised agent-team venue). ALL research goes through lead-researcher first — never spawn gatherer agents directly.
    5 installs
  12. ▌
    Prompt Architect · samhvw8 bundle
    Create and enhance prompts, system instructions, SKILL.md content, and principle files. Capabilities: transform verbose prompts, add patterns/heuristics, optimize token usage, write skill body content (soul, tensions, mental models, anti-patterns), structure CLAUDE.md principles, improve agent/persona definitions, apply prompt engineering techniques (CoT, few-shot, ReAct), context engineering. Actions: create, enhance, optimize, refactor, compress prompts and skill instructions. Keywords: prompt engineering, system prompt, CLAUDE.md, SKILL.md, skill content, principle files, agent prompt, persona prompt, soul, tensions, dialectic, mental models, anti-patterns, context engineering, progressive disclosure. Use when: creating prompts, writing SKILL.md body content, enhancing principle files, defining agent behaviors, engineering context strategies.
    0 installs
  13. ▌
    Guizang Ppt Skill · samhvw8 bundle
    Generate single-file HTML horizontal-swipe presentation decks with WebGL backgrounds and Motion entrance animations. Two styles — "Digital Magazine × E-Ink" (serif + fluid shader + warm tones) and "Swiss International Style" (sans-serif + dot grid + IKB/yellow/green/orange accent). ALWAYS invoke when the user wants a web-based presentation, slide deck, or PPT as HTML. Triggers — "make me a deck", "create slides", "presentation", "PPT", "web slides", "horizontal swipe", "magazine-style", "Swiss Style", "Helvetica deck", "single-file slides", "launch deck", "demo day slides", "keynote as HTML", or any request for browser-based slides. NOT for PowerPoint/Keynote/Google Slides editing or Slidev/Marp.
    4 installs
  14. ▌
    Impeccable · samhvw8 bundle
    Use when the user wants to design, redesign, shape, critique, audit, polish, clarify, distill, harden, optimize, adapt, animate, colorize, extract, or otherwise improve a frontend interface. Covers websites, landing pages, dashboards, product UI, app shells, components, forms, settings, onboarding, and empty states. Handles UX review, visual hierarchy, information architecture, cognitive load, accessibility, performance, responsive behavior, theming, anti-patterns, typography, fonts, spacing, layout, alignment, color, motion, micro-interactions, UX copy, error states, edge cases, i18n, and reusable design systems or tokens. Also use for bland designs that need to become bolder or more delightful, loud designs that should become quieter, live browser iteration on UI elements, or ambitious visual effects that should feel technically extraordinary. Not for backend-only or non-UI tasks.
    0 installs
  15. ▌
    Research · samhvw8
    Technical research methodology with YAGNI/KISS/DRY principles. Phases: scope definition, information gathering, analysis, synthesis, recommendation. Capabilities: technology evaluation, architecture analysis, best practices research, trade-off assessment, solution design. Actions: research, analyze, evaluate, compare, recommend technical solutions. Keywords: research, technology evaluation, best practices, architecture analysis, trade-offs, scalability, security, maintainability, YAGNI, KISS, DRY, technical analysis, solution design, competitive analysis, feasibility study. Use when: researching technologies, evaluating architectures, analyzing best practices, comparing solutions, assessing technical trade-offs, planning scalable/secure systems.
    1 install
  16. ▌
    Mise Expert · samhvw8
    Mise development environment manager (asdf + direnv + make replacement). Capabilities: tool version management (node, python, go, ruby, rust), environment variables, task runners, project-local configs. Actions: install, manage, configure, run tools/tasks with mise. Keywords: mise, mise.toml, tool version, runtime version, node, python, go, ruby, rust, asdf, direnv, task runner, environment variables, version manager, .tool-versions, mise install, mise use, mise run, mise tasks, project config, global config. Use when: installing runtime versions, managing tool versions, setting up dev environments, creating task runners, replacing asdf/direnv/make, configuring project-local tools.
    3 installs
  17. ▌
    Git Workflow · samhvw8
    Git workflow management with atomic commit principles. Capabilities: commit organization, branching strategies, merge/rebase workflows, PR management, history cleanup, staged change analysis, single-responsibility commits. Actions: commit, push, pull, merge, rebase, branch, stage, stash git operations. Keywords: git commit, git push, git pull, git merge, git rebase, git branch, git stash, atomic commit, commit message, conventional commits, branching strategy, GitFlow, trunk-based, PR, pull request, code review, git history, cherry-pick, squash, amend, interactive rebase, staged changes. Use when: organizing commits, creating branches, merging code, rebasing, writing commit messages, managing PRs, cleaning git history, analyzing staged changes.
    4 installs