eliasstravik
- 18 skills
- 0 followers
- 7 hours ago last updated
- ▌ Codebound · eliasstravik bundleUse when the user asks for Codebound specifically or wants Vercel-native code-first GTM workflows: sales/revops workflows as TypeScript, Supabase-backed GTM data, enrichment providers, run rules, CRM/actions, Eve operators, or Codebound project lifecycle. Do not use for generic Vercel, Supabase, Next.js, or AI SDK questions unless tied to Codebound or GTM workflow execution.
- ▌ Gtm Icp · eliasstravik bundleTriggers when a user asks to create, define, refine, update, delete, or doctor an ideal customer profile file in a connected GTM workspace, including choosing which organization owns it. Not for personas or for creating, importing, deleting, or repairing the workspace repository itself. Not for qualifying or scoring leads/accounts against saved ICPs/personas.
- ▌ Gtm Persona · eliasstravik bundleTriggers when a user asks to create, define, refine, update, delete, or doctor a buyer or stakeholder persona file in a connected GTM workspace, including choosing which organization owns it. Not for ICPs, teammate records, general persona advice, or creating, importing, deleting, or repairing the workspace repository itself. Not for qualifying or scoring leads/accounts against saved ICPs/personas.
- ▌ Gtm Workflow · eliasstravik bundleTriggers when a user asks for /gtm-workflows or wants to create, update, inspect, delete, run, approve, query, schedule, trigger, or deploy a saved GTM workflow, including ordinary steps, agent stages, selected skills and MCP tools, browsing, webhook intake, waits, parallel work, and workflow operations. Not for workspace setup, ICP or persona lifecycle work, or one-off calls that are not saved as workflows.
- ▌ Gtm Workspace · eliasstravik bundleTriggers when the user invokes `/gtm-workspace` or asks to create, import, update, delete, validate, migrate, or repair a GTM workspace repo or folder, including adding members or suborganizations. Not for defining ICPs or personas, or for tasks that merely use an existing workspace without changing or validating it.
- ▌ Gtm Qualify Prospects · eliasstravikTriggers when a user asks to qualify, score, or fit-check supplied leads, accounts, contacts, people, or companies in either supported mode, people against a connected GTM workspace's saved personas or companies against its saved ICPs. Includes "is X a fit for us" requests. Not for creating or editing ICPs or personas, saved or scheduled scoring at volume (use gtm-workflow), intent or engagement scoring, or workspace repair.
- ▌ Demo · eliasstravikThe demo skill owns turning a product concept, release artifact, checklist, or named demo into a convincing, self-contained local try-it experience. It stages only missing product context with deterministic, visibly simulated behavior; builds or revises the focal interaction; serves it on loopback; and verifies the exact preview, restart path, and QA result. It triggers when a user asks to build, revise, activate, or use /demo for a realistic local demo or artifact experience. It does not own feature integration into an existing app router, testing an already-running localhost or dist build, comparing prototype directions or state models, converting Markdown into durable HTML, making demo videos, writing sales scripts, explaining mock design, or reviewing bugs without edits.
- ▌ HTML · eliasstravikThe html skill owns creating and revising durable, standalone HTML artifacts: a complete self-contained index.html saved in a requested or generated artifact directory, with inline dependencies, accessible structure, loopback serving, and exact-file verification. It triggers when a user asks to create, build, turn content or data into, save, revise, or update a “durable HTML artifact,” “one-file dashboard,” “single-page local artifact,” or named HTML artifact, or explicitly says “use /html” or “activate the HTML skill.” It does not trigger for integrating HTML into React or Next.js routing, reviewing or explaining HTML or accessibility, browser-based QA of an existing page, converting Figma designs into reusable components, or merely serving an existing dist directory.
- ▌ Midwit · eliasstravikThe Midwit skill is the user’s ongoing anti-complexity gate for a conversation. It triggers on /midwit or requests to maintain an anti-overengineering mode, keep the user honest across tasks, challenge elaborate infrastructure before work, or propose doing nothing when the goal is already met. It asks for a ruling only when it has a specific simpler or null path, quantifies that path as 10–100x less machinery or effort, and proceeds without relitigation after “do it anyway”; trivial work passes directly. It is not a general code-review, refactoring, architecture-advice, implementation, meme, humor, or image-caption workflow.
- ▌ Automake · eliasstravik bundleAutomake owns a Git-backed ratchet for safely improving a repository through separate optimizer and evaluator roles: it establishes a baseline, proposes and checks candidates, obtains an independent comparison against the current committed state, keeps accepted changes, and restores rejected ones exactly. It triggers when the request is to prepare or execute this bounded improvement workflow, draft or approve its role instructions, set limits or stop conditions, protect local files, initialize the baseline, or invoke `/automake`. It does not trigger when “automake” refers to the GNU build system, when the task is merely a Makefile target or normal bug fix, when the user only wants code review or an explanation, or when the request is generic branch reset or deleted-file restoration.
- ▌ Consultant · eliasstravikUse for persistent, one-question-at-a-time consultation on an ambiguous repository change: inspect supplied territory, save decisions, produce an approved plan, run a scored bounded adversarial review with explicit targets and automatic-review limits, resolve or accept human-owned risks, and hand off to a fresh builder without implementing. Trigger on explicit /consultant or requests for durable consultation, plan approval, adversarial review, or builder handoff; exclude ordinary plan editing, standalone review or brainstorming, PRD writing, implementation, testing, and generic technical advice.
- ▌ Voice Mode · eliasstravikThe voice-mode skill owns the conversation’s delivery and interaction behavior when the user needs to listen instead of look at a display. It triggers on explicit “/voice-mode” or “activate Voice Mode,” and on concrete hands-free context such as “I’m driving,” “I’m away from the screen,” “I’m wearing headphones,” or “keep every reply spoken,” especially when the user requests concise conclusions, verbal numbering, or spoken follow-ups. It remains active until explicit exit, speaks plain prose, and places visual or exact technical material elsewhere. It is not a text-to-speech or audio-file tool, a voice-over-script writer, a conversational-copy editor, an accessibility or VoiceOver fixer, a dictation or microphone setup guide, or a substitute for normal Markdown and visible checklists.
- ▌ Copywriting · eliasstravik bundleTriggers when a request asks for customer- or audience-facing commercial copy for a product, service, or organization, including homepage, landing-page, sales, advertising, launch, social, newsletter, or marketing email copy; excludes internal, personal, editorial, research, strategy, planning, journalist-pitch, and implementation requests.
- ▌ Prototyping · eliasstravik bundleTriggers when a user asks to prototype a decision, compare visible or behavioral options in throwaway pages, keep prototyping through a consultant, grilling, or wayfinder session, or says /prototyping. It builds one loopback session that grows step by step and also handles a one-off "prototype this" request. Not for durable standalone HTML artifacts, polished product demos, browser QA, or integrating selected prototype code into an application.
- ▌ Skill Issue · eliasstravik bundleTriggers when an agent authors, reviews, names, or decides whether to create an agent skill, including requests to write SKILL.md, choose a skill type, evaluate skill-worthy content, or split material into references/scripts. Not for running skill evaluations or description optimization, which belong to skill-creator.
- ▌ Grilling Fix · eliasstravikTriggers alongside the grilling skill whenever the user invokes grilling-fix (e.g. `/grilling /grilling-fix`) or asks to be grilled with lettered options. Overrides only grilling's answer-option format; every question must offer explicit options labeled with letters (A, B, C…), never numbers, plus grilling's usual recommendation, and the user may always answer in their own words. Not for use without grilling, and not a replacement for grilling itself.
- ▌ Autoconsultant · eliasstravikAutoconsultant owns the approval-gated workflow that takes an ambiguous repository change through a persistent Consultant consultation and adversarial plan review, then prepares separately approved, independent Optimizer and Evaluator instructions plus one copy-paste-safe handoff for a fresh agent. It triggers when a request asks to combine consultation or plan approval with Automake or an evaluator-optimizer setup, preserve plan references, resolve ratchet limits or success conditions, or transfer execution to a new context; explicit `/autoconsultant` also triggers it. It does not own Consultant-only planning, Automake execution, prompt drafting without invocation, plan review without setup, implementation, testing, TDD, Git preflight, or generic workflow explanation.
- ▌