# Homeric Skills

Methodology-grounded product-coaching skills (SVPG / Marty Cagan first principles + Christina Wodtke's Radical Focus), callable from Claude, Claude Code, Cursor, Windsurf, and Atlassian Rovo over the Model Context Protocol.

MCP endpoint: https://mcp.homeric.ai/product-model

## Connect your agent

Add https://mcp.homeric.ai/product-model as a remote MCP server (HTTP transport). On the first tool call your agent opens a browser to sign in with your Homeric account — the server is an OAuth resource server and WorkOS AuthKit issues the tokens.

Example mcpServers config (Claude Code, Cursor, Windsurf):

    {
      "mcpServers": {
        "homeric": {
          "type": "http",
          "url": "https://mcp.homeric.ai/product-model"
        }
      }
    }

## Skills (22)

### homeric_design_assumption_tests
Design Assumption Tests — requires the Product Discovery pack

Maps the assumptions behind a solution idea across the four risk categories, ranks them by importance and evidence, and designs the smallest simulate-the-moment test for the top 1-3 with pass/fail criteria fixed upfront. Continuous Discovery Habits x SVPG's four big risks.

### homeric_assess_dx_core_4
Assess DX Core 4 Practice — requires the Product Engineering pack

Quick assess of how an org measures developer productivity: a 0-100 score against the DX Core 4 framework (getdx.com) with a per-dimension scored table, a warm summary, and 1-2 driving questions. Use dx-core-4-diagnose for a deep read, dx-core-4-improve for an action plan.

### homeric_diagnose_dx_core_4
Diagnose a DX Core 4 Signal — requires the Product Engineering pack

Root-cause diagnosis of one concerning DX Core 4 reading: 3-6 hypotheses across the publicly named DXI drivers and system factors, the drill-down metrics to pull next, and a balancing-metric check for healthy tradeoffs. Diagnosis only — fixes live in dx-core-4-improve.

### homeric_improve_dx_core_4
Plan a DX Core 4 Improvement — requires the Product Engineering pack

Builds an improvement plan from a diagnosed DX Core 4 driver or dimension: 2-4 interventions with balancing metrics, an experiment frame on the quarterly cadence, anti-gaming rollout notes, and a labeled ROI estimate. Diagnosis-first cases go to dx-core-4-diagnose.

### homeric_report_dx_core_4
Build a DX Core 4 Report — requires the Product Engineering pack

Turns DX Core 4 numbers — whatever subset exists — into a stakeholder-ready quarterly report: executive summary for leadership, four dimension sections with 2024 benchmark positions, measurement gaps, and anti-gaming framing. Honest about missing data — never invents numbers.

### homeric_define_dx_metrics
Define DX Core 4 Metrics — requires the Product Engineering pack

Designs an org-fitted DX Core 4 metric set: key metric plus 2-3 secondaries per dimension, each defined precisely (source, cadence, exclusions), a gaming guardrail per metric, and a baseline plan. Use dx-core-4-assess to score an existing measurement practice instead.

### homeric_message_product_coach
Message Product Coach

Message a human Homeric product coach — ask a question, or check for a reply to a previous one.

### homeric_generate_opportunity_trees
Generate an Opportunity Solution Tree — requires the Product Discovery pack

Builds an evidence-traced opportunity solution tree from an outcome plus customer evidence, per Teresa Torres's continuous discovery: opportunity space, target opportunity, 3+ candidate solutions, assumption-test stubs. Use outcome-define first when the outcome needs work.

### homeric_define_outcomes
Define a Product Outcome — requires the Product Discovery pack

Turns a goal, metric, or initiative into a well-formed product outcome per Teresa Torres's Continuous Discovery Habits: classifies what the team brought, derives 1-3 candidate product outcomes with leading/lagging rationale, and flags the eight outcome-definition mistakes.

### homeric_generate_pr_faq
Generate a Press Release & FAQ — requires the Product Strategy pack

Drafts an Amazon Working Backwards Press Release + FAQ from a vision statement, product brief, or rough notes: a ten-field future-dated PR plus an 8-12 item FAQ answering the hardest questions concession-first. Use product-vision-assess to score an existing vision.

### homeric_assess_product_okrs
Assess Product OKRs

Quick assess of a product OKR set: a 0-100 score against the SVPG/Wodtke framework with a per-dimension scored table (score, points lost, a one-line nudge), a warm summary, and 1-2 driving questions. Use product-okr-review for a thorough read, product-okr-generate for a rewrite.

### homeric_generate_product_okrs
Generate Product OKRs

Proposes an improved OKR set on top of the user's input (or drafts one from a strategic priority brief) with per-dimension rationale per the SVPG/Wodtke framework. Use `product-okr-assess` for a quick score; use `product-okr-review` for a thorough read without a rewrite.

### homeric_review_product_okrs
Review Product OKRs

Conversational coaching review of a product OKR set against the SVPG/Wodtke framework. Calls out what's working and what to address per dimension, in a warm teammate voice. Use `product-okr-assess` for a quick verdict; use `product-okr-generate` for a rewrite.

### homeric_assess_product_strategy
Assess Product Strategy — requires the Product Strategy pack

Quick assess of a product strategy: a 0-100 score against the Homeric DHM-based framework with a per-dimension scored table and one-line nudges, a warm summary, and 1-2 driving questions. Use product-strategy-review for a thorough read, product-strategy-generate for a draft.

### homeric_generate_product_strategy
Generate a Product Strategy (DHM) — requires the Product Strategy pack

Drafts a DHM-grounded product strategy from the user's context or rough notes: 4-6 hypotheses with delight/hard-to-copy/margin rationale, one proxy metric each, and an SMT one-pager. Use product-strategy-assess for a score, product-strategy-review for a deep read.

### homeric_review_product_strategy
Review Product Strategy — requires the Product Strategy pack

Conversational coaching review of a product strategy against the Homeric Biddle/SVPG framework: what's working, what to address, suggested improvement per dimension — no numeric score. Use product-strategy-assess for a quick verdict, product-strategy-generate for a rewrite.

### homeric_assess_product_vision
Assess Product Vision — requires the Product Strategy pack

Quick assess of a product vision (optionally plus its PR/FAQ): a 0-100 score against the SVPG/Working Backwards framework with a per-dimension scored table (score, points lost, a one-line nudge), a warm summary, and 1-2 driving questions. The front door to the vision skills.

### homeric_generate_prototypes
Generate a Test Prototype (static HTML) — requires the Product Discovery pack

Generates a self-contained static HTML prototype simulating the moment for one assumption test, plus the test script around it: setup, behavior tasks, follow-up questions, measurement, predefined success criteria. Torres's Continuous Discovery Habits with SVPG's four big risks.

### homeric_define_proxy_metrics
Define Proxy Metrics (GEM) — requires the Product Strategy pack

Defines 3-6 proxy metrics for a product strategy, each laddered to a force-ranked GEM priority and held against the six proxy criteria, with gaming risks, guardrails, and a measurement plan. Use product-strategy-assess for a scored read of the strategy itself.

### homeric_request_skills
Request a Homeric Skill

Capture a skill the user wishes Homeric offered. First checks whether a catalog skill already covers the need and points there; otherwise structures the unmet need into a clean request and routes it to the human Homeric coaches.

### homeric_write_specs
Write a Build Spec (for coding agents) — requires the Product Discovery pack

Turns a validated solution and its discovery evidence into a build-ready spec for AI coding agents: outcome and opportunity traceability, given/when/then stories tagged evidence-backed or assumption, explicit scope, instrumentation guardrails, and an ordered task breakdown.

### homeric_facilitate_strategy_meetings
Facilitate a Quarterly Strategy Meeting — requires the Product Strategy pack

Builds a ready-to-run quarterly product strategy meeting kit from the team's strategies, proxy-metric reads, and proposed changes, per Gibson Biddle's meeting mechanics: timed agenda, per-role pre-reads, refreshed SMT one-pager with discussion prompts, follow-up capture.

---
Manage your skills, connections, and activity at https://stratos.homeric.ai