humane plugin
21 design-method skills for people and agents: evidence, prototypes, tokens, typography, semantic interactions, scroll stories, optional sound, reviews, and framework adaptation.
How to install the humane plugin
Run both commands inside Claude Code. The first adds the marketplace once; the second installs the plugin.
/plugin marketplace add glebis/humane-agentic-design
/plugin install humane@humane-agentic-designWhat's inside humane
22 parts read from the plugin's own files.
Agents 1
Call as @agent-humane:name- @agent-humane:synthetic-respondenthaiku
An ordinary person reacting to copy, slogans, brand values, or marketing materials — gut-level, unfiltered, no expertise. Launch it when you want to know how something lands, not whether it is well-argued. Accepts an optional persona brief in the prompt (age, place, work, media diet, relationship to
Skills 21
Claude loads it when the task matches- before-after
Generate emotional Before/After transformation grids for products, lectures, and offers. Chainable from humane:jtbd output. Uses empathy mapping, first-person voice, somatic markers, and valence scoring to produce grids ready for landing pages, slides, and messaging. This skill should be used when the user wants to articulate the transformation their product/service creates, build a before/after grid, or chain from a JTBD interview into emotional copywriting. Triggers on before/after grid, transformation grid, "what's the transformation", landing page transformation section, emotional copywriting, chain from JTBD.
- brand-illustrate
Turn design tokens into a coherent, on-brand illustration set through a short step-by-step questionnaire, then generate with whichever image backend is installed (gpt-image-2 / nano-banana). Assembles the prompt scaffold from the token palette + brand block, merges layout-rules de-slop negatives, requests platform preset sizes, saves a reusable recipe, and hands the batch to review. Use when a project already has a token set and needs images that match it, or when an earlier batch should be re-run from its saved recipe. Triggers on brand illustrations, on-brand images, illustration set, generate images matching my brand, illustrate this section on-brand, contact sheet.
- brandkit
This skill should be used when EXPLORING a brand identity that does not exist yet. Generates premium brand-guidelines boards for competing directions, and hands the WINNING direction off into the design-tokens brand block (confirm-then-write). Upstream of tokens; for producing assets under an EXISTING token contract use brand-illustrate instead. Carries reference direction for minimalist, cinematic, editorial, dark-tech, luxury, cultural, security, gaming, developer-tool, and consumer-app brand systems. Triggers on brand kit, brand board, brand directions, identity candidates, identity direction, logo system, brand guidelines deck, visual identity exploration, визуальные направления бренда.
- design-frameworks
Fit an already-decided interface to an existing design system or UI toolchain through a capability-probed preset, using the system's own CLI, registry, MCP server, manifests, tokens, and checks instead of inventing parallel conventions. Use after the product job, evidence, concept, and prototype are settled enough to implement, or when bringing an existing build back into framework compliance. Not for choosing the product concept, visual brand, or research method. Triggers on design frameworks, design system adapter, use Astryx, use shadcn, use Storybook, fit this to our component library, existing design system, component registry, framework compliance, agent-ready design system, "implement with our design system".
- design-tokens
Sets up, validates, resolves, and exports design tokens per the DTCG (Design Tokens Community Group) Format Module 2025.10 standard, and owns all colour contrast measurement and remediation — every text/background pair on both APCA Lc and the WCAG ratio via `tokens contrast`, with a fix that moves OKLCH lightness only. Use when the user wants to define a design token set globally or per project, compile tokens to CSS variables, layer a project's tokens over a global brand base, check whether a palette is readable, or produce an on-brand context file for other generation skills. Triggers on "set up design tokens", "create a token set", "compile tokens to CSS", "design system variables", "brand tokens", "check contrast", "WCAG", "APCA", "is this text readable", "contrast audit", "проверь контраст".
- jtbd
Terminal-first JTBD engine for founders and product people. Interview fast, kill jargon, capture real switching forces (Push/Pull/Habit/Anxiety), score opportunities, and export structured artifacts (JSON + one-pager + messaging angles + GTM brief). Use when the user says "help me figure out what to build", "analyze these customer reviews", "what are people actually hiring this for", "I need messaging for my product", "turn this interview into insights", "what should I prioritize", or any variation of articulating what a project does, why it matters, who it's for, or converting interview/review/transcript signal into a decision-grade brief. Triggers on "describe my project", "JTBD", "jobs to be done", "switching forces", or "mine these reviews".
- layout-rules
A battle-tested avoid-list of 39 structural and interaction defect classes for tool/dashboard UIs (structure, footers/metrics, tables, color/contrast, URL state, JS traps, accessibility/touch, i18n/theming, de-slop), distilled from a real build/audit cycle. Use when designing, building, or reviewing any layout, dashboard, data-dense tool UI, viewer, or admin interface. Triggers on "design a layout", "build a dashboard", "make a viewer/tool UI", "review this UI", "какие правила дизайна", or before writing any HTML/CSS for a tool-like interface.
- narrative-scrollytelling
Turn an ordered sequence of ideas into a readable scroll-based story with canonical document order, deliberate step or progress transitions, native scrolling, and static, reduced-motion, keyboard, touch, and no-JavaScript fallbacks. Use when a method, argument, timeline, process, or visual explanation should unfold as the reader scrolls rather than behave like a slide deck. Triggers on scrollytelling, scroll story, narrative scroll, sticky story, scroll-driven narrative, scroll animation, step story, chapter reveal, pinned visual, interactive article.
- nielsen-heuristics
Run a formal heuristic evaluation of a design artifact against Jakob Nielsen's 10 usability heuristics, producing an evidence-backed, severity-scored report with honesty guards. Accepts a screenshot, live URL, codebase/HTML, interface description, or JTBD/spec doc, and adapts its rigor to what is actually observable. Renders as markdown or a Tufte-style HTML report, and can export findings as Linear or Beads tasks after confirmation. Triggers on heuristic evaluation, usability review, Nielsen heuristics check, UX heuristic audit, usability inspection.
- persona-review
Review a document from multiple stakeholder perspectives (personas), collect structured feedback, and optionally update the document. Use when a document should be stress-tested from different viewpoints before sharing — e.g., "review this PRD from an engineer's perspective", "what would a skeptical investor say about this pitch?" Triggers on persona review, review from a stakeholder perspective, what would an engineer say, stress-test this PRD, review this pitch, skeptical investor.
- prototype
Make an idea lookable and clickable at the cheapest fidelity that answers its one open question — an ASCII sketch, a hand-drawn storyboard of moves, an SVG click-dummy with hotspots linking screens, or a self-contained HTML file. Use when the user wants to see or try an idea before committing to structure, tokens, or copy. Triggers on prototype, wireframe, mockup, click-dummy, sketch the screens, storyboard, hand-drawn sketch, sketchy wireframe, "draw the flow", "what would this look like", "mock this up", "show me the flow", "прототип", "макет".
- respondent-panel
Run a panel of independent synthetic respondents against copy, a slogan, brand values, a landing page, or any user-facing text — each in an isolated context, each a different specific person — then read the panel for convergence and divergence. Use when the user asks "how does this land", "what would people think of this", "test this tagline", "get reactions to this copy", "run a panel", or wants gut-level audience reaction rather than expert critique. Complements persona-review, which is expert stakeholder critique of a document. Triggers on respondent panel, how does this land, what would people think, test this tagline, reactions to this copy, gut reaction, audience reaction.
- review
User-invoked review that coordinates the humane review skills — layout-rules, ux-writing, typography, nielsen-heuristics, walkthrough, design-tokens contrast — into one prioritized verdict, and marks the domains it cannot cover instead of improvising them. Supports quick and full modes. Identifies the artifact first and runs a reduced document pipeline for a README, PRD, or docs page rather than stretching a UI pipeline over it. Use when explicitly asked for a holistic review of a screen, flow, feature, product, or document. Triggers on humane review, full review, review the whole thing, holistic UI audit, cross-skill design review, "review this properly", "полный ревью".
- semantic-micro-interactions
Define bounded interface feedback from a real state transition, including accessible visual motion, reduced-motion and input-equivalent behavior, and an optional semantic sound hook without owning audio playback. Use when a control, gesture, validation, progress state, or completion needs meaningful feedback rather than decorative animation. Triggers on micro-interaction, interaction motion, button feedback, state transition, drag settle, satisfying interaction, reduced motion, hover feedback, completion animation, semantic motion.
- setup
Get humane working on this machine — check what the cycle needs, configure the corpus root, token base, image backend, task-export target, language and browser tool, and install the companions and generators that are missing. Diagnoses read-only first, then installs only what the user confirms. Use on a fresh machine, when a skill complains something is missing, or to see how humane is currently configured. Triggers on humane setup, set up humane, configure humane, humane doctor, "what do I need to install", "why can't it find my tokens", "check my humane install", "настрой humane".
- sound-effects
Generate a small, coherent sound palette for interface moments through interchangeable provider adapters, beginning with ElevenLabs Sound Effects, then hand it to a walkthrough to check that the cues clarify rather than distract. Use when a product needs interaction sounds, feedback cues, micro-sound design, or a retro-futuristic audio layer. Triggers on sound effects, UI sounds, interaction audio, micro sounds, click sound, swipe sound, drag sound, ElevenLabs sound effects, audio feedback, retro-futuristic sound.
- type-specimen
Build a browsable type specimen that sets candidate typefaces in the product's own words, so a font is chosen against real copy rather than "Hamburgefonstiv". Loads families from Google Fonts, shows a weight ladder, prose, a data table, list rows, small caps, glyph coverage and variable axes per family, measures WCAG and APCA for the chosen background/text pair, and lets any specimen text be edited in place — one edit, every family. Use when picking a typeface, comparing shortlisted fonts, checking a font's Cyrillic or symbol coverage, or proving a font works for a specific interface before it enters the token set. Triggers on choose a font, pick a typeface, compare fonts, type specimen, font shortlist, does this font have Cyrillic, font pairing, which font for this dashboard, шрифтовой стенд, выбрать шрифт.
- typography
Review or mechanically format English and Russian text for microtypography, protected word pairs, punctuation and symbol artifacts, and spelling while keeping editorial choices separate from safe corrections. Use when polishing prose or UI copy after the wording is settled, or when an agent-generated draft contains suspicious dashes, symbols, spacing, or Markdown residue. Triggers on typography, microtypography, typographic cleanup, nonbreaking spaces, protected pairs, punctuation cleanup, spelling pass, editorial pass, LLM artifacts, smart quotes, Russian typography, английская типографика, русская типографика, неразрывные пробелы, редактура текста.
- using-humane
Route a design task to the right humane skill, and after any humane skill finishes, name the next one from the declared handoff graph instead of guessing. Reads the `handoffs:` / `accepts:` / `orchestrates:` keys in each skill's frontmatter, so the route is data, not recollection. Use at the start of design work when it is not obvious which skill owns the task, and at the end of any humane skill to find what it hands to. Not for non-design work. Triggers on where do I start, which humane skill, what comes next, what should I run after, humane cycle, design cycle order, "I finished the jtbd interview now what", "какой скилл дальше".
- ux-writing
Write and review the words inside a product — button labels, error messages, empty states, confirmations, settings labels, placeholders, notifications — and the documentation prose around it, including READMEs, docs pages and release notes. Grounds the wording in the JTBD corpus (the anxiety force tells you what a confirmation must defuse) and hands the result to respondent-panel to find out whether strangers read it the way you meant. Use when writing or reviewing any user-facing string. Triggers on UX writing, microcopy, interface copy, button labels, error messages, empty states, placeholder text, settings labels, confirmation dialog, notification copy, README wording, rewrite these docs, release notes copy, "what should this button say", "rewrite this error", "перепиши текст кнопки".
- walkthrough
Task-based evaluation of a real interface — take one job from the JTBD corpus, attempt it step by step as the person who has it, and record where the attempt breaks. Answers "can someone actually complete this?", which inspection and reaction methods do not. Runs a cognitive walkthrough (four questions per step) against a live URL, a prototype, screenshots, or the code, and reports task success against the outcome it was derived from. Use when you have a task and something operable to attempt it on. Triggers on walkthrough, cognitive walkthrough, task analysis, "can a user actually do this", "test this task", "where do people get stuck", "walk through the signup flow", "test this on mobile", "drive it in the browser", "пройди сценарий".
Using humane in Claude Code
Ask for an agent by name:
@agent-humane:synthetic-respondentSkills need no command. Claude reads them when your request matches what they describe.
Update, turn off or remove
- Update the plugin (shell)
- claude plugin update humane@humane-agentic-design
- Refresh the marketplace
- /plugin marketplace update humane-agentic-design
- Turn it off for now
- /plugin disable humane@humane-agentic-design
- Remove it
- /plugin uninstall humane@humane-agentic-design
Skills in humane
- before-afterglebis/humane-agentic-design
Generate emotional Before/After transformation grids for products, lectures, and offers. Chainable from humane:jtbd output. Uses empathy mapping, first-person voice, somatic markers, and valence scoring to produce grids ready for landing pages, slides, and messaging. This skill should be used when the user wants to articulate the transformation their product/service creates, build a before/after grid, or chain from a JTBD interview into emotional copywriting. Triggers on before/after grid, transformation grid, "what's the transformation", landing page transformation section, emotional copywriting, chain from JTBD.
2 files43stars - brand-illustrateglebis/humane-agentic-design
Turn design tokens into a coherent, on-brand illustration set through a short step-by-step questionnaire, then generate with whichever image backend is installed (gpt-image-2 / nano-banana). Assembles the prompt scaffold from the token palette + brand block, merges layout-rules de-slop negatives, requests platform preset sizes, saves a reusable recipe, and hands the batch to review. Use when a project already has a token set and needs images that match it, or when an earlier batch should be re-run from its saved recipe. Triggers on brand illustrations, on-brand images, illustration set, generate images matching my brand, illustrate this section on-brand, contact sheet.
4 files43stars - brandkitglebis/humane-agentic-design
This skill should be used when EXPLORING a brand identity that does not exist yet. Generates premium brand-guidelines boards for competing directions, and hands the WINNING direction off into the design-tokens brand block (confirm-then-write). Upstream of tokens; for producing assets under an EXISTING token contract use brand-illustrate instead. Carries reference direction for minimalist, cinematic, editorial, dark-tech, luxury, cultural, security, gaming, developer-tool, and consumer-app brand systems. Triggers on brand kit, brand board, brand directions, identity candidates, identity direction, logo system, brand guidelines deck, visual identity exploration, визуальные направления бренда.
8 files43stars - design-frameworksglebis/humane-agentic-design
Fit an already-decided interface to an existing design system or UI toolchain through a capability-probed preset, using the system's own CLI, registry, MCP server, manifests, tokens, and checks instead of inventing parallel conventions. Use after the product job, evidence, concept, and prototype are settled enough to implement, or when bringing an existing build back into framework compliance. Not for choosing the product concept, visual brand, or research method. Triggers on design frameworks, design system adapter, use Astryx, use shadcn, use Storybook, fit this to our component library, existing design system, component registry, framework compliance, agent-ready design system, "implement with our design system".
9 files43stars - design-tokensglebis/humane-agentic-design
Sets up, validates, resolves, and exports design tokens per the DTCG (Design Tokens Community Group) Format Module 2025.10 standard, and owns all colour contrast measurement and remediation — every text/background pair on both APCA Lc and the WCAG ratio via `tokens contrast`, with a fix that moves OKLCH lightness only. Use when the user wants to define a design token set globally or per project, compile tokens to CSS variables, layer a project's tokens over a global brand base, check whether a palette is readable, or produce an on-brand context file for other generation skills. Triggers on "set up design tokens", "create a token set", "compile tokens to CSS", "design system variables", "brand tokens", "check contrast", "WCAG", "APCA", "is this text readable", "contrast audit", "проверь контраст".
104 files43stars - jtbdglebis/humane-agentic-design
Terminal-first JTBD engine for founders and product people. Interview fast, kill jargon, capture real switching forces (Push/Pull/Habit/Anxiety), score opportunities, and export structured artifacts (JSON + one-pager + messaging angles + GTM brief). Use when the user says "help me figure out what to build", "analyze these customer reviews", "what are people actually hiring this for", "I need messaging for my product", "turn this interview into insights", "what should I prioritize", or any variation of articulating what a project does, why it matters, who it's for, or converting interview/review/transcript signal into a decision-grade brief. Triggers on "describe my project", "JTBD", "jobs to be done", "switching forces", or "mine these reviews".
18 files43stars - layout-rulesglebis/humane-agentic-design
A battle-tested avoid-list of 39 structural and interaction defect classes for tool/dashboard UIs (structure, footers/metrics, tables, color/contrast, URL state, JS traps, accessibility/touch, i18n/theming, de-slop), distilled from a real build/audit cycle. Use when designing, building, or reviewing any layout, dashboard, data-dense tool UI, viewer, or admin interface. Triggers on "design a layout", "build a dashboard", "make a viewer/tool UI", "review this UI", "какие правила дизайна", or before writing any HTML/CSS for a tool-like interface.
3 files43stars - narrative-scrollytellingglebis/humane-agentic-design
Turn an ordered sequence of ideas into a readable scroll-based story with canonical document order, deliberate step or progress transitions, native scrolling, and static, reduced-motion, keyboard, touch, and no-JavaScript fallbacks. Use when a method, argument, timeline, process, or visual explanation should unfold as the reader scrolls rather than behave like a slide deck. Triggers on scrollytelling, scroll story, narrative scroll, sticky story, scroll-driven narrative, scroll animation, step story, chapter reveal, pinned visual, interactive article.
5 files43stars - nielsen-heuristicsglebis/humane-agentic-design
Run a formal heuristic evaluation of a design artifact against Jakob Nielsen's 10 usability heuristics, producing an evidence-backed, severity-scored report with honesty guards. Accepts a screenshot, live URL, codebase/HTML, interface description, or JTBD/spec doc, and adapts its rigor to what is actually observable. Renders as markdown or a Tufte-style HTML report, and can export findings as Linear or Beads tasks after confirmation. Triggers on heuristic evaluation, usability review, Nielsen heuristics check, UX heuristic audit, usability inspection.
8 files43stars - persona-reviewglebis/humane-agentic-design
Review a document from multiple stakeholder perspectives (personas), collect structured feedback, and optionally update the document. Use when a document should be stress-tested from different viewpoints before sharing — e.g., "review this PRD from an engineer's perspective", "what would a skeptical investor say about this pitch?" Triggers on persona review, review from a stakeholder perspective, what would an engineer say, stress-test this PRD, review this pitch, skeptical investor.
2 files43stars - prototypeglebis/humane-agentic-design
Make an idea lookable and clickable at the cheapest fidelity that answers its one open question — an ASCII sketch, a hand-drawn storyboard of moves, an SVG click-dummy with hotspots linking screens, or a self-contained HTML file. Use when the user wants to see or try an idea before committing to structure, tokens, or copy. Triggers on prototype, wireframe, mockup, click-dummy, sketch the screens, storyboard, hand-drawn sketch, sketchy wireframe, "draw the flow", "what would this look like", "mock this up", "show me the flow", "прототип", "макет".
8 files43stars - respondent-panelglebis/humane-agentic-design
Run a panel of independent synthetic respondents against copy, a slogan, brand values, a landing page, or any user-facing text — each in an isolated context, each a different specific person — then read the panel for convergence and divergence. Use when the user asks "how does this land", "what would people think of this", "test this tagline", "get reactions to this copy", "run a panel", or wants gut-level audience reaction rather than expert critique. Complements persona-review, which is expert stakeholder critique of a document. Triggers on respondent panel, how does this land, what would people think, test this tagline, reactions to this copy, gut reaction, audience reaction.
2 files43stars - reviewglebis/humane-agentic-design
User-invoked review that coordinates the humane review skills — layout-rules, ux-writing, typography, nielsen-heuristics, walkthrough, design-tokens contrast — into one prioritized verdict, and marks the domains it cannot cover instead of improvising them. Supports quick and full modes. Identifies the artifact first and runs a reduced document pipeline for a README, PRD, or docs page rather than stretching a UI pipeline over it. Use when explicitly asked for a holistic review of a screen, flow, feature, product, or document. Triggers on humane review, full review, review the whole thing, holistic UI audit, cross-skill design review, "review this properly", "полный ревью".
3 files43stars - semantic-micro-interactionsglebis/humane-agentic-design
Define bounded interface feedback from a real state transition, including accessible visual motion, reduced-motion and input-equivalent behavior, and an optional semantic sound hook without owning audio playback. Use when a control, gesture, validation, progress state, or completion needs meaningful feedback rather than decorative animation. Triggers on micro-interaction, interaction motion, button feedback, state transition, drag settle, satisfying interaction, reduced motion, hover feedback, completion animation, semantic motion.
5 files43stars - setupglebis/humane-agentic-design
Get humane working on this machine — check what the cycle needs, configure the corpus root, token base, image backend, task-export target, language and browser tool, and install the companions and generators that are missing. Diagnoses read-only first, then installs only what the user confirms. Use on a fresh machine, when a skill complains something is missing, or to see how humane is currently configured. Triggers on humane setup, set up humane, configure humane, humane doctor, "what do I need to install", "why can't it find my tokens", "check my humane install", "настрой humane".
6 files43stars - sound-effectsglebis/humane-agentic-design
Generate a small, coherent sound palette for interface moments through interchangeable provider adapters, beginning with ElevenLabs Sound Effects, then hand it to a walkthrough to check that the cues clarify rather than distract. Use when a product needs interaction sounds, feedback cues, micro-sound design, or a retro-futuristic audio layer. Triggers on sound effects, UI sounds, interaction audio, micro sounds, click sound, swipe sound, drag sound, ElevenLabs sound effects, audio feedback, retro-futuristic sound.
6 files43stars - type-specimenglebis/humane-agentic-design
Build a browsable type specimen that sets candidate typefaces in the product's own words, so a font is chosen against real copy rather than "Hamburgefonstiv". Loads families from Google Fonts, shows a weight ladder, prose, a data table, list rows, small caps, glyph coverage and variable axes per family, measures WCAG and APCA for the chosen background/text pair, and lets any specimen text be edited in place — one edit, every family. Use when picking a typeface, comparing shortlisted fonts, checking a font's Cyrillic or symbol coverage, or proving a font works for a specific interface before it enters the token set. Triggers on choose a font, pick a typeface, compare fonts, type specimen, font shortlist, does this font have Cyrillic, font pairing, which font for this dashboard, шрифтовой стенд, выбрать шрифт.
9 files43stars - typographyglebis/humane-agentic-design
Review or mechanically format English and Russian text for microtypography, protected word pairs, punctuation and symbol artifacts, and spelling while keeping editorial choices separate from safe corrections. Use when polishing prose or UI copy after the wording is settled, or when an agent-generated draft contains suspicious dashes, symbols, spacing, or Markdown residue. Triggers on typography, microtypography, typographic cleanup, nonbreaking spaces, protected pairs, punctuation cleanup, spelling pass, editorial pass, LLM artifacts, smart quotes, Russian typography, английская типографика, русская типографика, неразрывные пробелы, редактура текста.
6 files43stars - using-humaneglebis/humane-agentic-design
Route a design task to the right humane skill, and after any humane skill finishes, name the next one from the declared handoff graph instead of guessing. Reads the `handoffs:` / `accepts:` / `orchestrates:` keys in each skill's frontmatter, so the route is data, not recollection. Use at the start of design work when it is not obvious which skill owns the task, and at the end of any humane skill to find what it hands to. Not for non-design work. Triggers on where do I start, which humane skill, what comes next, what should I run after, humane cycle, design cycle order, "I finished the jtbd interview now what", "какой скилл дальше".
2 files43stars - ux-writingglebis/humane-agentic-design
Write and review the words inside a product — button labels, error messages, empty states, confirmations, settings labels, placeholders, notifications — and the documentation prose around it, including READMEs, docs pages and release notes. Grounds the wording in the JTBD corpus (the anxiety force tells you what a confirmation must defuse) and hands the result to respondent-panel to find out whether strangers read it the way you meant. Use when writing or reviewing any user-facing string. Triggers on UX writing, microcopy, interface copy, button labels, error messages, empty states, placeholder text, settings labels, confirmation dialog, notification copy, README wording, rewrite these docs, release notes copy, "what should this button say", "rewrite this error", "перепиши текст кнопки".
3 files43stars - walkthroughglebis/humane-agentic-design
Task-based evaluation of a real interface — take one job from the JTBD corpus, attempt it step by step as the person who has it, and record where the attempt breaks. Answers "can someone actually complete this?", which inspection and reaction methods do not. Runs a cognitive walkthrough (four questions per step) against a live URL, a prototype, screenshots, or the code, and reports task success against the outcome it was derived from. Use when you have a task and something operable to attempt it on. Triggers on walkthrough, cognitive walkthrough, task analysis, "can a user actually do this", "test this task", "where do people get stuck", "walk through the signup flow", "test this on mobile", "drive it in the browser", "пройди сценарий".
3 files43stars
humane plugin questions
How do I install the humane plugin?
In Claude Code run /plugin marketplace add glebis/humane-agentic-design, then /plugin install humane@humane-agentic-design.
What does the humane plugin include?
humane bundles 1 agent, 21 skills.
Which agents come with humane?
synthetic-respondent. Call one with @agent-humane:synthetic-respondent.
How do I update or remove the humane plugin?
Update it with claude plugin update humane@humane-agentic-design in your shell, or from the Installed tab of /plugin. Remove it with /plugin uninstall humane@humane-agentic-design.