@dsalazardev/ai-hub-cli 0.0.0-stage → 0.1.0

package/presets/generic-ts/preset.yaml

@@ -0,0 +1,46 @@
+id: generic-ts
+version: 1
+extends: base
+description: TypeScript repository with npm-compatible scripts and a standard test runner.
+detect:
+  files:
+    - package.json
+    - tsconfig.json
+  dependencies:
+    - typescript
+stack:
+  languages:
+    - typescript
+  packageManager: npm
+commands:
+  install: npm ci
+  build: npm run build
+  test: npm test
+  typecheck: npx tsc --noEmit
+  lint: npm run lint
+  verify: npm test
+paths:
+  source:
+    - src
+  tests:
+    - tests
+  docs:
+    - docs
+policy:
+  trunk: auto
+  guardMode: shadow
+  worktrees: true
+  optOuts: []
+rules: []
+agents:
+  publish:
+    - spec-author
+    - implementer-frontend
+    - implementer-backend
+    - reviewer-architecture
+    - reviewer-tests
+    - explorer-domain
+skills:
+  publish: []
+mcp:
+  source: mcp-manifest.yaml

package/presets/python/preset.yaml

@@ -0,0 +1,47 @@
+id: python
+version: 1
+extends: base
+description: Python project with pytest, mypy and ruff.
+detect:
+  files:
+    - pyproject.toml
+    - requirements.txt
+  dependencies:
+    - pytest
+stack:
+  languages:
+    - python
+  packageManager: pip
+commands:
+  install: pip install -e .
+  build: python -m build
+  test: pytest
+  typecheck: mypy .
+  lint: ruff check .
+  verify: pytest
+paths:
+  source:
+    - src
+  tests:
+    - tests
+  docs:
+    - docs
+policy:
+  trunk: auto
+  guardMode: shadow
+  worktrees: true
+  optOuts: []
+rules:
+  - rules/python.md
+agents:
+  publish:
+    - spec-author
+    - implementer-frontend
+    - implementer-backend
+    - reviewer-architecture
+    - reviewer-tests
+    - explorer-domain
+skills:
+  publish: []
+mcp:
+  source: mcp-manifest.yaml

package/presets/python/rules/python.md

@@ -0,0 +1,10 @@
+# Python rules
+
+- Type hints on every public function and module boundary.
+- `pytest` for tests; fixtures over global state.
+- `mypy` and `ruff` are part of the verification command.
+- No bare `except`, no mutable default arguments, no `print` in library code.
+- Use the `src/` layout when the project is a package; keep import roots explicit.
+- Prefer `pathlib` over string paths.
+- Run `ruff check .`, `mypy .` and `pytest` before marking a task complete.
+- Never commit virtual environments, `.pyc` files or local credentials.

package/schema/engine.schema.json

@@ -0,0 +1,73 @@
+{
+  "$schema": "http://json-schema.org/draft-07/schema#",
+  "title": "AiHubEngineV2",
+  "type": "object",
+  "required": ["version", "roles", "commands", "labels", "targets"],
+  "additionalProperties": false,
+  "properties": {
+    "version": { "const": 2 },
+    "roles": {
+      "type": "array",
+      "minItems": 8,
+      "maxItems": 8,
+      "items": {
+        "type": "object",
+        "required": ["id", "canonical", "derived", "can_modify", "cannot_modify", "commands", "gate"],
+        "additionalProperties": false,
+        "properties": {
+          "id": { "type": "string", "pattern": "^[a-z][a-z0-9-]*$" },
+          "canonical": { "type": "string", "minLength": 1 },
+          "derived": { "type": "boolean" },
+          "description": { "type": "string" },
+          "can_modify": { "type": "array", "items": { "type": "string" } },
+          "cannot_modify": { "type": "array", "items": { "type": "string" } },
+          "commands": { "type": "array", "items": { "type": "string" }, "uniqueItems": true },
+          "gate": { "type": "string", "minLength": 1 }
+        }
+      }
+    },
+    "commands": {
+      "type": "array",
+      "minItems": 17,
+      "maxItems": 17,
+      "items": {
+        "type": "object",
+        "required": ["id", "name", "lane", "artifacts", "exit", "role", "skill"],
+        "additionalProperties": false,
+        "properties": {
+          "id": { "type": "string", "pattern": "^[a-z][a-z0-9-]*$" },
+          "name": { "type": "string", "pattern": "^/speckit[.-]" },
+          "lane": { "enum": ["assessment", "feature", "bug"] },
+          "artifacts": { "type": "array", "minItems": 1, "items": { "type": "string" } },
+          "exit": { "type": "array", "minItems": 1, "items": { "type": "string" } },
+          "role": { "type": "string", "minLength": 1 },
+          "co_roles": { "type": "array", "items": { "type": "string" }, "uniqueItems": true },
+          "skill": { "type": "string", "pattern": "^speckit-" }
+        }
+      }
+    },
+    "labels": {
+      "type": "array",
+      "minItems": 7,
+      "maxItems": 7,
+      "uniqueItems": true,
+      "items": {
+        "enum": [
+          "ai::todo",
+          "ai::in-spec",
+          "ai::spec-ready",
+          "ai::in-dev",
+          "ai::in-review",
+          "ai::done",
+          "ai::blocked"
+        ]
+      }
+    },
+    "targets": {
+      "type": "array",
+      "minItems": 5,
+      "uniqueItems": true,
+      "items": { "enum": ["claude", "opencode", "pi", "cursor", "copilot"] }
+    }
+  }
+}

package/schema/manifest.schema.json

@@ -0,0 +1,140 @@
+{
+  "$schema": "http://json-schema.org/draft-07/schema#",
+  "title": "AiHubProjectManifestV2",
+  "type": "object",
+  "required": [
+    "version",
+    "project",
+    "preset",
+    "stack",
+    "commands",
+    "paths",
+    "targets",
+    "policy",
+    "skills",
+    "agents",
+    "rules"
+  ],
+  "additionalProperties": false,
+  "properties": {
+    "version": { "const": 2 },
+    "project": {
+      "type": "object",
+      "required": ["id", "name"],
+      "additionalProperties": false,
+      "properties": {
+        "id": { "type": "string", "pattern": "^[a-z][a-z0-9-]*$" },
+        "name": { "type": "string", "minLength": 1 }
+      }
+    },
+    "preset": {
+      "type": "object",
+      "required": ["id", "version", "source"],
+      "additionalProperties": false,
+      "properties": {
+        "id": { "type": "string", "pattern": "^[a-z][a-z0-9-]*$" },
+        "version": { "type": "integer", "minimum": 1 },
+        "source": { "enum": ["package"] }
+      }
+    },
+    "stack": {
+      "type": "object",
+      "required": ["languages"],
+      "additionalProperties": false,
+      "properties": {
+        "languages": { "type": "array", "items": { "type": "string" } },
+        "frontend": { "type": "string" },
+        "backend": { "type": "string" },
+        "packageManager": { "type": "string" }
+      }
+    },
+    "commands": {
+      "type": "object",
+      "additionalProperties": false,
+      "properties": {
+        "install": { "type": "string" },
+        "build": { "type": "string" },
+        "test": { "type": "string" },
+        "typecheck": { "type": "string" },
+        "lint": { "type": "string" },
+        "verify": { "type": "string" }
+      }
+    },
+    "paths": {
+      "type": "object",
+      "required": ["source", "tests", "docs"],
+      "additionalProperties": false,
+      "properties": {
+        "source": { "type": "array", "items": { "type": "string" } },
+        "tests": { "type": "array", "items": { "type": "string" } },
+        "docs": { "type": "array", "items": { "type": "string" } }
+      }
+    },
+    "targets": {
+      "type": "array",
+      "minItems": 1,
+      "uniqueItems": true,
+      "items": { "type": "string", "minLength": 1 }
+    },
+    "policy": {
+      "type": "object",
+      "required": ["trunk", "guardMode", "worktrees", "optOuts"],
+      "additionalProperties": false,
+      "properties": {
+        "trunk": { "enum": ["auto", "closed", "open"] },
+        "guardMode": { "enum": ["shadow", "enforce"] },
+        "worktrees": { "type": "boolean" },
+        "optOuts": { "type": "array", "items": { "type": "string" } },
+        "dangerPatterns": {
+          "type": "array",
+          "items": {
+            "type": "object",
+            "required": ["id", "pattern", "decision", "reason"],
+            "additionalProperties": false,
+            "properties": {
+              "id": { "type": "string", "pattern": "^[a-z][a-z0-9:-]*$" },
+              "pattern": { "type": "string", "minLength": 1 },
+              "decision": { "enum": ["ask", "deny"] },
+              "reason": { "type": "string", "minLength": 10 }
+            }
+          }
+        }
+      }
+    },
+    "skills": {
+      "type": "object",
+      "required": ["source", "publish"],
+      "additionalProperties": false,
+      "properties": {
+        "source": { "type": "string", "minLength": 1 },
+        "publish": { "type": "array", "uniqueItems": true, "items": { "type": "string" } }
+      }
+    },
+    "agents": {
+      "type": "object",
+      "required": ["source", "publish"],
+      "additionalProperties": false,
+      "properties": {
+        "source": { "type": "string", "minLength": 1 },
+        "publish": { "type": "array", "uniqueItems": true, "items": { "type": "string" } }
+      }
+    },
+    "rules": {
+      "type": "object",
+      "required": ["source", "publish"],
+      "additionalProperties": false,
+      "properties": {
+        "source": { "type": "string", "minLength": 1 },
+        "publish": { "type": "array", "uniqueItems": true, "items": { "type": "string" } }
+      }
+    },
+    "mcp": {
+      "type": "object",
+      "required": ["source"],
+      "additionalProperties": false,
+      "properties": {
+        "source": { "type": "string", "minLength": 1 }
+      }
+    }
+  }
+}

package/schema/preset.schema.json

@@ -0,0 +1,98 @@
+{
+  "$schema": "http://json-schema.org/draft-07/schema#",
+  "title": "AiHubPresetV1",
+  "type": "object",
+  "required": ["id", "version", "description"],
+  "additionalProperties": false,
+  "properties": {
+    "id": { "type": "string", "pattern": "^[a-z][a-z0-9-]*$" },
+    "version": { "type": "integer", "minimum": 1 },
+    "extends": { "type": "string", "pattern": "^[a-z][a-z0-9-]*$" },
+    "description": { "type": "string", "minLength": 10 },
+    "detect": {
+      "type": "object",
+      "additionalProperties": false,
+      "properties": {
+        "files": { "type": "array", "items": { "type": "string" } },
+        "dependencies": { "type": "array", "items": { "type": "string" } }
+      }
+    },
+    "stack": {
+      "type": "object",
+      "additionalProperties": false,
+      "properties": {
+        "languages": { "type": "array", "items": { "type": "string" } },
+        "frontend": { "type": "string" },
+        "backend": { "type": "string" },
+        "packageManager": { "type": "string" }
+      }
+    },
+    "commands": {
+      "type": "object",
+      "additionalProperties": false,
+      "properties": {
+        "install": { "type": "string" },
+        "build": { "type": "string" },
+        "test": { "type": "string" },
+        "typecheck": { "type": "string" },
+        "lint": { "type": "string" },
+        "verify": { "type": "string" }
+      }
+    },
+    "paths": {
+      "type": "object",
+      "additionalProperties": false,
+      "properties": {
+        "source": { "type": "array", "items": { "type": "string" } },
+        "tests": { "type": "array", "items": { "type": "string" } },
+        "docs": { "type": "array", "items": { "type": "string" } }
+      }
+    },
+    "policy": {
+      "type": "object",
+      "additionalProperties": false,
+      "properties": {
+        "trunk": { "enum": ["auto", "closed", "open"] },
+        "guardMode": { "enum": ["shadow", "enforce"] },
+        "worktrees": { "type": "boolean" },
+        "optOuts": { "type": "array", "items": { "type": "string" } },
+        "dangerPatterns": {
+          "type": "array",
+          "items": {
+            "type": "object",
+            "required": ["id", "pattern", "decision", "reason"],
+            "additionalProperties": false,
+            "properties": {
+              "id": { "type": "string", "pattern": "^[a-z][a-z0-9:-]*$" },
+              "pattern": { "type": "string", "minLength": 1 },
+              "decision": { "enum": ["ask", "deny"] },
+              "reason": { "type": "string", "minLength": 10 }
+            }
+          }
+        }
+      }
+    },
+    "rules": { "type": "array", "items": { "type": "string" } },
+    "agents": {
+      "type": "object",
+      "additionalProperties": false,
+      "properties": {
+        "publish": { "type": "array", "items": { "type": "string" } }
+      }
+    },
+    "skills": {
+      "type": "object",
+      "additionalProperties": false,
+      "properties": {
+        "publish": { "type": "array", "items": { "type": "string" } }
+      }
+    },
+    "mcp": {
+      "type": "object",
+      "additionalProperties": false,
+      "properties": {
+        "source": { "type": "string" }
+      }
+    }
+  }
+}

package/schema/state.schema.json

@@ -0,0 +1,27 @@
+{
+  "$schema": "http://json-schema.org/draft-07/schema#",
+  "title": "ProjectState",
+  "type": "object",
+  "required": ["version", "project", "preset", "activeChange", "phase", "tasks", "updatedAt"],
+  "additionalProperties": false,
+  "properties": {
+    "version": { "const": 1 },
+    "project": { "type": "string", "minLength": 1 },
+    "preset": { "type": "string", "minLength": 1 },
+    "activeChange": { "type": ["string", "null"] },
+    "lane": { "enum": ["assessment", "feature", "bug", null] },
+    "phase": { "type": "string", "minLength": 1 },
+    "tasks": {
+      "type": "object",
+      "required": ["total", "done"],
+      "additionalProperties": false,
+      "properties": {
+        "total": { "type": "integer", "minimum": 0 },
+        "done": { "type": "integer", "minimum": 0 }
+      }
+    },
+    "branch": { "type": ["string", "null"] },
+    "worktree": { "type": ["string", "null"] },
+    "updatedAt": { "type": "string", "minLength": 1 }
+  }
+}

package/skills/shared/ab-testing/SKILL.md

@@ -0,0 +1,159 @@
+---
+name: ab-testing
+description: "Use when designing or analyzing a controlled experiment — falsifiable hypothesis, sample size from an MDE, reading significance/CI/power, CUPED, or rescuing tests that won't go significant. NOT recurring metric tracking (that is `analytics`), NOT north-star/KPI trees (that is `kpi-framework`), NOT projecting metrics forward (that is `forecasting`)."
+tags: [ab-testing, experimentation, statistics, cuped, sample-size, hypothesis-testing]
+recommends: [analytics, kpi-framework, forecasting, data-cleaning, python, reporting]
+origin: ai-hub
+---
+
+# A/B testing — design and read a defensible experiment
+
+An experiment without a pre-committed sample size and a single primary metric is not an experiment.
+It is a dashboard you stare at until it tells you what you wanted to hear. The discipline lives almost
+entirely *before* traffic ships: a falsifiable hypothesis, one primary metric, a sample size derived
+from the smallest effect worth detecting, and a stop rule you cannot renegotiate at 2pm on day four.
+
+## Pre-test checklist — every line true before any traffic
+
+Each one is a place experiments die silently.
+
+- [ ] A **falsifiable hypothesis** — names the change, the direction, and the metric it moves.
+- [ ] Exactly **ONE primary metric**. More than one primary = multiple comparisons = inflated false positives.
+- [ ] **Guardrail metrics** — what you refuse to harm (latency, refunds, unsubscribes) even for a win.
+- [ ] The **randomization unit = the analysis unit** (usually the user). Mixing them is pseudoreplication.
+- [ ] An **MDE** — the smallest lift that would change a decision. Not "any difference."
+- [ ] A **computed sample size** and the **duration** it implies at your real daily eligible traffic.
+- [ ] A **fixed stop rule** — a date or an n you commit to before launch. No "we'll see how it looks."
+
+## Step 1 — Hypothesis and metrics
+
+State a null you can reject. "The new checkout button changes purchase conversion" with H0: conversion
+equal across arms, H1: it differs. Vague aspirations ("improve the funnel") have no rejection region.
+
+Pick one primary metric and freeze it. Why: every extra primary metric is another coin flip at α, so
+three "primary" metrics turn a 5% false-positive rate into roughly 14%. Demote the rest to secondary.
+
+Randomize on the same unit you analyze on. If a user sees the variant on every visit, randomize by user,
+not by session — analyzing 50k sessions from 8k users treats correlated observations as independent and
+fabricates significance.
+
+```text
+Bad:  "We think the redesign will improve engagement and revenue and retention."  (no null, 3 primaries, no number)
+Good: "H0: 30-day purchase conversion is equal between control and the new one-click button.
+       H1: it differs. Primary: purchase conversion. Guardrails: refund rate, p95 checkout latency.
+       Randomize by user_id. MDE: +1.5pp absolute on a 12% baseline."
+```
+
+## Step 2 — Sample size from MDE, baseline, and power
+
+Defaults: power 0.80, α 0.05 (two-sided). The MDE is yours to choose — it is the smallest effect that
+would actually change what you do.
+
+Rule: required n scales with ~1/MDE². Why: halving the smallest effect you care to detect roughly
+**quadruples** the traffic and time. This is the single most expensive decision in the design, so set the
+MDE to a business threshold, never to "whatever is small."
+
+For a conversion rate (proportion):
+
+```python
+from statsmodels.stats.power import NormalIndPower
+from statsmodels.stats.proportion import proportion_effectsize
+
+p1, p2 = 0.12, 0.135                       # baseline, baseline + MDE (1.5pp)
+h = proportion_effectsize(p1, p2)          # Cohen's h (arcsine transform)
+n = NormalIndPower().solve_power(effect_size=h, alpha=0.05, power=0.80, ratio=1.0)
+print(int(-(-n // 1)))                      # n PER ARM, rounded up
+```
+
+For a continuous metric (revenue per user, time on page) use Welch-style sizing:
+
+```python
+from statsmodels.stats.power import TTestIndPower
+
+effect = mde_in_units / pooled_std         # Cohen's d
+n = TTestIndPower().solve_power(effect_size=effect, alpha=0.05, power=0.80, ratio=1.0)
+```
+
+Then convert n to a calendar plan: `days = ceil((n_per_arm * num_arms) / daily_eligible_users)`. If that
+is 9 days, run a clean **two full weeks** anyway — weekday/weekend mix is part of the population, and a
+6-day test oversamples whoever shows up Tuesday. Full worked example (12% baseline, +1.5pp MDE, 80%
+power) plus runnable sizing, n→duration, CUPED θ and SRM snippets: `references/sample-size-and-cuped.md`.
+
+## Step 3 — Run discipline
+
+**Fixed horizon is the default.** Commit to the n/date from Step 2 and read the result once, at the end.
+
+**Do not peek and stop at first significance.** Why: checking repeatedly and stopping the moment p < 0.05
+inflates the Type-I error far above 5% — with enough looks, a null test crosses 0.05 most of the time.
+If you genuinely need to stop early, use a *sequential / always-valid* method (confidence sequences,
+e.g. Netflix's anytime-valid CIs) that holds Type-I error under continuous monitoring. Sequential is
+strong for **killing losers early** and weak for **calling winners early** — for a confident win, the
+fixed-horizon read is tighter.
+
+**Gate on SRM before you trust anything.** Compute a chi-square test on the observed split versus the
+intended ratio. If p < 0.001 the assignment or logging is broken — a bot filter dropping one arm, a
+redirect, a caching bug. Fix the instrumentation and rerun; do not "adjust for it."
+
+The peeking Type-I math, sequential/always-valid options, SRM diagnosis, novelty/primacy effects,
+Simpson's paradox in segments and HARKing all live in `references/pitfalls.md`.
+
+## Step 4 — Analyze
+
+Pick the test by metric type:
+
+| Metric type | Test |
+|---|---|
+| Binary conversion (proportion) | Two-proportion z-test (`statsmodels.stats.proportion.proportions_ztest`) |
+| Continuous, roughly normal / large n | Welch's t-test (`scipy.stats.ttest_ind(..., equal_var=False)`) |
+| Continuous, heavy-tailed / skewed (revenue) | Mann-Whitney U, or t-test on a log/winsorized metric |
+
+Report **lift + confidence interval + p-value together**. Never p alone. Why: p < 0.05 with a CI of
+[+0.1pp, +5pp] is "statistically there, practically a coin toss" — the CI tells you the size, p only
+tells you it is not exactly zero. **Practical significance** = compare the CI to your MDE: if the whole
+interval sits above the MDE, ship; if it straddles the MDE, you detected *something* too small to matter.
+
+**Multiple comparisons.** Two regimes:
+- Small set of pre-declared **decision** metrics → **Bonferroni** (divide α by the count). Conservative, simple.
+- Large **exploratory** scan of many metrics/segments → **Benjamini-Hochberg (FDR)**. It keeps far more
+  power than Bonferroni on big scans (in a 20-effect example, ~17 detected vs ~12 under Bonferroni).
+
+## Step 5 — CUPED variance reduction
+
+CUPED (Controlled-experiment Using Pre-Experiment Data) subtracts predictable pre-period noise so the
+same traffic buys more power — or the same power needs less traffic. The adjusted metric:
+
+```text
+Y_cuped = Y − θ · (X − E[X])        where  θ = Cov(Y, X) / Var(X)
+```
+
+Estimate θ by regressing the in-experiment metric `Y` on the **pre-experiment** covariate `X` (e.g. each
+user's spend in the 4 weeks before the test), then analyze `Y_cuped` with the same test as Step 4.
+
+When it pays: recurring users with a strong pre-period signal. Reported wins — Netflix ~40% variance
+reduction on engagement, Statsig 50%+ on common metrics → significance in roughly half the time/traffic.
+
+When it does **nothing** — do not bother: brand-new users (no pre-period data), a covariate uncorrelated
+with the outcome, or — the cardinal sin — a covariate measured *after* assignment, which biases the
+estimate. The covariate MUST be pre-treatment and independent of which arm a user lands in. Runnable
+θ-via-OLS snippet in `references/sample-size-and-cuped.md`.
+
+## Anti-patterns
+
+| Bad | Why it is wrong | Do instead |
+|---|---|---|
+| Peek daily, stop the day p < 0.05 | Repeated looks inflate Type-I error far above α | Fix n/date up front; or a sequential method that holds α |
+| No sample size set before launch | You will stop on noise and call it a win | Compute n from MDE/baseline/power in Step 2 |
+| Several "primary" metrics | Each is a coin flip at α; 3 metrics ≈ 14% false-positive | One frozen primary; the rest are secondary |
+| Ignore the observed split | An SRM means assignment/logging is broken; results are garbage | Chi-square SRM gate before reading anything |
+| Report only the p-value | Hides effect size — p < 0.05 can be practically zero | Always lift + CI + p; compare CI to MDE |
+| CUPED on a post-assignment covariate | Covariate correlated with the arm biases θ | Use only pre-treatment, assignment-independent covariates |
+| Call a winner from an underpowered test | "Not significant" then ≠ "no effect"; you lacked power | Reach planned n, or report the CI and say "inconclusive, here is the range" |
+| Decide the hypothesis after seeing results (HARKing) | Turns the whole analysis into a fishing expedition | Pre-register hypothesis + primary metric before launch |
+| Run 6 days because it "looks significant" | Oversamples one weekday slice of the population | Run full weeks; honor the fixed horizon |
+
+## Checkable artifact
+
+When this skill emits a Python sizing/analysis script or an experiment-design doc, run
+`scripts/verify.sh` from your project root. It confirms the script executes under `python3` and prints a
+numeric sample size, and that any design doc names a primary metric, an MDE, and power/alpha. It is
+read-only and soft-passes when no artifact is present (a design-only conversation).

package/skills/shared/ab-testing/evals/README.md

@@ -0,0 +1,8 @@
+# Evals — ab-testing
+
+These cases are routing and capability checks for the catalog harness, not an automated test runner.
+`should_trigger` and `should_not_trigger` are judged by feeding each prompt to the router and confirming
+it lands on `ab-testing` (or, for the negatives, on the named sibling such as `analytics` or
+`forecasting`). The single `capability` case is graded by hand or with the catalog's eval script: run the
+scenario through the skill and check the produced design/analysis against every line in `must_include` —
+a pass needs all of them present, not just most. There is no `pytest` here; the rubric is the spec.

package/skills/shared/ab-testing/evals/cases.yaml

@@ -0,0 +1,49 @@
+skill: ab-testing
+
+should_trigger:
+  - prompt: "How many users per arm do I need to detect a 2% lift on a 10% baseline conversion?"
+    why: Core sample-size sizing from baseline + MDE + power — the central pre-test calculation this skill owns.
+  - prompt: "Is this A/B result statistically significant? Control converted 540/10000, variant 590/10000."
+    why: Read-out of a finished proportion test — two-proportion z-test, lift, CI, p-value together.
+  - prompt: "Our test has run two weeks and still isn't significant, what do we do now?"
+    why: Non-obvious. "Inconclusive" almost always means underpowered, peeked, or an SRM — a design diagnosis, not a re-run.
+  - prompt: "Can we use CUPED to get faster results on our checkout experiment?"
+    why: Variance reduction via a pre-experiment covariate — when it helps, the formula, and when it does nothing.
+  - prompt: "We keep peeking at the dashboard and stopping the moment it hits p<0.05 — is that a problem?"
+    why: Non-obvious optional-stopping trap; peeking inflates Type-I error far above alpha. Fixed horizon or always-valid inference.
+  - prompt: "El experiment de la landing no surt significatiu, com el dissenyo bé des de zero?"
+    why: Catalan trigger — rescue an inconclusive experiment by redesigning the hypothesis/MDE/sample-size up front.
+  - prompt: "Cuántos usuarios necesito para detectar un 1.5pp de mejora con 80% de potencia?"
+    why: Spanish trigger for sample-size computation from MDE and power.
+
+should_not_trigger:
+  - prompt: "Build a dashboard tracking weekly signups and churn over time."
+    route_to: analytics
+    why: Recurring metric tracking and event instrumentation, not a controlled experiment with a hypothesis.
+  - prompt: "Define our north-star metric and the KPI tree underneath it."
+    route_to: kpi-framework
+    why: Deciding which metrics matter, not designing or analyzing a test of a change.
+  - prompt: "Forecast next quarter's revenue from the last 24 months of data."
+    route_to: forecasting
+    why: Time-series projection into the future, not a randomized comparison of two arms.
+  - prompt: "Clean and dedupe this messy events CSV before any analysis."
+    route_to: data-cleaning
+    why: Data preparation, not experiment design or read-out.
+  - prompt: "Turn last month's experiment results into a stakeholder slide deck."
+    route_to: reporting
+    why: Periodic stakeholder communication of results, not the statistical design/analysis itself.
+
+capability:
+  - scenario: >
+      Design, size, and plan the analysis for a test of a new one-click checkout button. Baseline
+      purchase conversion is 12%; the team wants to detect a +1.5pp absolute lift at 80% power and
+      alpha 0.05, with about 1,800 eligible users per day. Include a plan to speed it up with CUPED.
+    must_include:
+      - A falsifiable hypothesis with H0/H1 and exactly one primary metric (purchase conversion), plus guardrail metrics
+      - Randomization unit equals analysis unit (by user), not by session
+      - Sample-size calculation naming statsmodels proportion_effectsize and NormalIndPower / solve_power
+      - Converting n per arm to a duration in days from daily eligible traffic, rounded up to whole weeks
+      - A fixed-horizon stop rule and an explicit no-peeking warning (Type-I inflation)
+      - An SRM chi-square check before trusting the result
+      - CUPED plan with a pre-treatment covariate and the formula Y_cuped = Y - theta*(X - E[X])
+      - Reporting the result as lift + confidence interval + p-value, compared against the MDE for practical significance