eliasstravik

Triggers when a user invokes /consulting or asks for a consultation on an ambiguous change: to be interviewed one question at a time, shown the options visually on a page before deciding, have decisions saved across sittings, and end with a written plan, a…

Autoconsultant 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…

Use 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…

Triggers 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…

Automake 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…

The 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…

The 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…

The 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…

Triggers when a user wants one or many evidence-backed account briefs, company research, research-priority triage, fit or timing analysis, sales personalization, or handling of a request to save account research, using supplied sources or web access. Not for…

Triggers when a user wants strong-fit, good-fit, weak-fit, or no-fit assigned to companies that already have ICP labels. Not for segmentation, enrichment, account research, lead workflows, scoring-model design, arithmetic, or context setup.

Triggers when a user asks to classify, segment, route, or bucket companies against ICPs in a connected GTM context. Not for scoring already-labeled accounts, researching or enriching companies, defining ICPs, segmenting leads, or managing the context…

Triggers when the user invokes `/gtm-context` or asks to create, import, update, delete, validate, or repair a GTM context repo or folder, including adding teammates or suborganizations. Not for defining ICPs or personas, segmenting or scoring accounts, or…

Triggers when a user asks to create, define, refine, update, delete, or doctor an ideal customer profile file in a connected GTM context, including choosing which organization owns it. Not for personas, segmentation, scoring, account or lead research, or…

Triggers when a user wants one or many evidence-backed person briefs, lead research, role or timing analysis, outreach preparation, or handling of a request to save lead research, using supplied sources or web access. Not for persona-label assignment,…

Triggers when a user wants strong-fit, good-fit, weak-fit, or no-fit assigned to people who already have persona labels. Not for segmentation, enrichment, lead research, account workflows, scoring-model design, arithmetic, or context setup.

Triggers when a user asks to classify, segment, route, bucket, or qualify individual leads or contacts against personas in a connected GTM context. Not for scoring already-labeled leads, researching people, defining personas, segmenting companies, or managing…

Triggers when a user asks to build, create, update, run, test, schedule, deploy, host, upgrade, inspect, open the inspection UI, or delete a saved GTM workflow, its result table, runs, or diagram in a GTM workspace, with phrasings like "build a workflow that…

Triggers when a user asks about, deploys, sets up, gets running, connects, checks, repairs, or upgrades GTM Agent (the Slack GTM agent that runs these skills on Vercel) for an organization, including questions before any setup about whether they could set it…

Triggers when someone new to GTM Skills asks where to begin, with phrasings like "how do I get started", "what do I do first", "where do I begin with gtm", or /gtm-get-started. Looks at what the workspace already has and takes the user through each missing…

Triggers when a user asks to create, update, delete, or check an ideal customer profile, or ICP, in a GTM workspace, with phrasings like "create an ICP for lean B2B SaaS", "our ICP should require HubSpot", "delete the SaaS ICP", or "check the ICPs". Owns the…

Triggers when a user asks to create, update, delete, or check a buyer or stakeholder persona in a GTM workspace, with phrasings like "create a persona for revenue leaders", "the persona should speak English", "delete the CMO persona", or "check the personas".…

Triggers when a user asks whether a named person or company, or a pasted list of them, fits the GTM workspace's personas or ICPs, with phrasings like "is this a fit", "check quillhr.com against our ICP", "score these leads", or "qualify this list". Owns…

Triggers when a user asks to create, set up, import, open, check, repair, or share a GTM workspace for an organization, or to add, change, or remove its members or company facts, with phrasings like "set up a GTM workspace for Acme", "add Priya to the team",…

Runs a reviewed improvement ratchet inside a herdr-projects coordinator: each iteration a maker thread commits one candidate, a fresh reviewer thread judges that exact commit against a rubric the maker never sees, BETTER candidates land through herdr's thread…

Use 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…