jev-recipes 0.1.0 → 0.2.0

package/CHANGELOG.md

@@ -2,6 +2,10 @@
 
 ## Unreleased
 
+- Document installed-package imports and CLI commands first; move repository setup into the contributor guide and rename the local CLI script to `jev-recipes`.
+
+- Add recipe tests under `tests/recipe/`, mocked Jev responses, recipe coverage reports and thresholds, and test checks in CI.
+
 - Unify recipe execution helpers, result validation, subject registration, and documentation across the catalog.
 
 - Expand the catalog to 66 focused recipes across answer quality, retrieval, conversation, tools, support, memory, and knowledge maintenance.

package/README.md

@@ -2,25 +2,11 @@
 
 [![npm version](https://img.shields.io/npm/v/jev-recipes?logo=npm)](https://www.npmjs.com/package/jev-recipes)
 
-Small TypeScript recipes for the decisions inside an AI application. Use [Jev](https://docs.typesafe.ai/introduction/coding-agents) to choose a handler, select useful evidence, check an answer, or decide when to ask for help.
+66 small TypeScript recipes for AI applications. Choose a handler, select useful evidence, check an answer, or decide when to ask for help.
 
-Each recipe is a function you can use on its own. Your application supplies the context and acts on the result.
+Use `jev-recipes` through TypeScript imports or its included command-line tool. [Jev](https://docs.typesafe.ai/introduction/coding-agents) powers the live decisions. Your application supplies the context and acts on the result.
 
-## Recipes
-
-[Browse all 66 recipes](recipes/README.md). Each handles a focused decision and has its own schemas, example, and usage guide.
-
-| Group                                                              | Recipes | Examples                                                |
-| ------------------------------------------------------------------ | ------- | ------------------------------------------------------- |
-| [Answer quality](recipes/README.md#answer-quality)                 | 10      | `answer-coverage`, `answer-relevance`, `citation-match` |
-| [Retrieval and evidence](recipes/README.md#retrieval-and-evidence) | 13      | `rerank`, `verify`, `answerability`                     |
-| [Conversation](recipes/README.md#conversation)                     | 11      | `clarify`, `turn-intent`, `followup-link`               |
-| [Tools and tasks](recipes/README.md#tools-and-tasks)               | 12      | `route`, `handoff`, `tool-fit`                          |
-| [Customer support](recipes/README.md#customer-support)             | 10      | `issue-impact`, `attempted-step`, `workaround-fit`      |
-| [Memory](recipes/README.md#memory)                                 | 5       | `memory-value`, `memory-scope`, `memory-relation`       |
-| [Knowledge maintenance](recipes/README.md#knowledge-maintenance)   | 5       | `document-role`, `audience-fit`, `change-meaning`       |
-
-## Use in an app
+## Install
 
 Requires Node.js 22.9 or newer.
 
@@ -28,6 +14,8 @@ Requires Node.js 22.9 or newer.
 npm install jev-recipes
 ```
 
+## Use a recipe
+
 Set `TYPESAFE_API_KEY` in your server's environment, then call a recipe:
 
 ```ts
@@ -51,28 +39,38 @@ You can also import recipes from `jev-recipes`. Every recipe accepts an optional
 
 Live calls send the supplied input to TypeSafe and use API quota. Keep your API key on the server.
 
-## Try the demos
+## Recipes
 
-From this repository:
+[Browse all 66 recipes](https://github.com/agencyenterprise/jev-recipes/blob/main/recipes/README.md). Each handles a focused decision and has its own schemas, example, and usage guide.
+
+| Group                                                                                                                        | Recipes | Examples                                                |
+| ---------------------------------------------------------------------------------------------------------------------------- | ------- | ------------------------------------------------------- |
+| [Answer quality](https://github.com/agencyenterprise/jev-recipes/blob/main/recipes/README.md#answer-quality)                 | 10      | `answer-coverage`, `answer-relevance`, `citation-match` |
+| [Retrieval and evidence](https://github.com/agencyenterprise/jev-recipes/blob/main/recipes/README.md#retrieval-and-evidence) | 13      | `rerank`, `verify`, `answerability`                     |
+| [Conversation](https://github.com/agencyenterprise/jev-recipes/blob/main/recipes/README.md#conversation)                     | 11      | `clarify`, `turn-intent`, `followup-link`               |
+| [Tools and tasks](https://github.com/agencyenterprise/jev-recipes/blob/main/recipes/README.md#tools-and-tasks)               | 12      | `route`, `handoff`, `tool-fit`                          |
+| [Customer support](https://github.com/agencyenterprise/jev-recipes/blob/main/recipes/README.md#customer-support)             | 10      | `issue-impact`, `attempted-step`, `workaround-fit`      |
+| [Memory](https://github.com/agencyenterprise/jev-recipes/blob/main/recipes/README.md#memory)                                 | 5       | `memory-value`, `memory-scope`, `memory-relation`       |
+| [Knowledge maintenance](https://github.com/agencyenterprise/jev-recipes/blob/main/recipes/README.md#knowledge-maintenance)   | 5       | `document-role`, `audience-fit`, `change-meaning`       |
+
+## Try a demo
+
+After installing the package, run its CLI from your app's directory:
 
 ```sh
-npm ci
-npm run build
-npm run jev -- demo all
+npx jev-recipes demo rerank
 ```
 
-Demos use saved responses and need no API key. They show how each recipe handles a decision; they do not measure model accuracy. To run one, replace `all` with its name.
-
-The repository may contain additions that are not yet in the [published npm package](https://www.npmjs.com/package/jev-recipes). Use this checkout to try all the recipes shown here.
+Replace `rerank` with another recipe name, or use `all` to try every installed recipe. Demos use saved responses and need no API key. They show how recipes handle decisions; they do not measure model accuracy.
 
 ## Find a recipe
 
-Developers and coding agents can inspect the catalog without calling Jev:
+Use the CLI to browse the installed recipes without an API key:
 
 ```sh
-npm run jev -- list
-npm run jev -- list evidence --category retrieval
-npm run jev -- describe answer-coverage
+npx jev-recipes list
+npx jev-recipes list evidence --category retrieval
+npx jev-recipes describe answer-coverage
 ```
 
 `list` searches names, descriptions, categories, and tags. `describe` returns the recipe's limits, JSON input and result schemas, and example input.
@@ -90,21 +88,21 @@ The library returns metadata and schemas. The command-line description also incl
 
 ## Run your own input
 
-Add `TYPESAFE_API_KEY` to a local `.env` file. See [.env.example](.env.example) for the format.
-
-Create an input file, edit it, then run the recipe:
+Save an example input from the installed package:
 
 ```sh
-node dist/cli/index.js example rerank > input.json
-npm run jev -- run rerank input.json
+npx jev-recipes example rerank > input.json
 ```
 
-The `npm run jev` command loads `.env`. Use `-` instead of a filename to read from stdin. For scripts that need JSON without npm's command banner:
+Edit `input.json`, then set your API key in the terminal and run the recipe:
 
 ```sh
-node --env-file-if-exists=.env dist/cli/index.js run rerank input.json
+export TYPESAFE_API_KEY='your-api-key'
+npx jev-recipes run rerank input.json
 ```
 
+The CLI reads the key from its environment; it does not load `.env` files automatically. Live runs send your input to TypeSafe and use API quota. Commands return JSON. Use `-` instead of a filename to read from stdin.
+
 ## Read the result before acting
 
 - `ready` means a decision passed its threshold. Check the recipe's outcome too: a ready assessment can still find missing information or an unsupported claim.
@@ -115,19 +113,7 @@ node --env-file-if-exists=.env dist/cli/index.js run rerank input.json
 
 ## Contribute
 
-Each recipe owns its implementation, Zod 4 schemas, inferred types, metadata, demo, and documentation. Recipes share small decision helpers. A recipe that reuses another names that dependency in its guide and catalog metadata. Larger workflows belong in examples.
-
-```text
-recipes/<name>/    Individual recipes
-src/              Shared client, response validation, schemas, and exports
-catalog/          Recipe discovery and registrations grouped by subject
-cli/              Command-line runner
-examples/         Workflows that combine recipes
-```
-
-See [CONTRIBUTING.md](CONTRIBUTING.md) to add a recipe.
-
-`npm run build` compiles the TypeScript into JavaScript modules and type declarations. `npm pack` creates the installable archive. See [RELEASING.md](RELEASING.md) for packaging and publishing, and [CHANGELOG.md](CHANGELOG.md) for changes.
+See [CONTRIBUTING.md](https://github.com/agencyenterprise/jev-recipes/blob/main/CONTRIBUTING.md) for repository setup, tests, and adding recipes. See [CHANGELOG.md](https://github.com/agencyenterprise/jev-recipes/blob/main/CHANGELOG.md) for changes and [RELEASING.md](https://github.com/agencyenterprise/jev-recipes/blob/main/RELEASING.md) for publishing.
 
 ## Cool projects
 
@@ -141,18 +127,12 @@ Keep the recipes small and connect them in your application. These ideas show ho
 | A knowledge base that catches outdated answers     | `change-meaning`, `answer-invalidation`, `cache-match`               | Source change tracking, saved answers, and access and freshness checks |
 | Memory that respects the task's scope              | `preference-kind`, `memory-value`, `memory-scope`, `memory-relation` | Candidate facts, storage consent, and retention rules                  |
 
-The [support assistant example](examples/support/README.md) is implemented in this repository. It stops when review or better information is needed and accepts your own draft callback:
+The [support assistant example](https://github.com/agencyenterprise/jev-recipes/blob/main/examples/support/README.md) shows how to combine recipes with your own draft generator. It stops when review or better information is needed:
 
 ```text
 handoff → clarify → route → rerank → answerability → draft an answer → verify
 ```
 
-```sh
-npm run example:support
-```
-
-That command uses saved decisions and a saved draft. Add `-- --live` to use live Jev decisions with your `.env` key; the example still uses the saved draft. The other projects above are composition ideas, not additional bundled applications.
-
 ## License
 
-[MIT](LICENSE). Independent community project. Jev and TypeSafe are products of TypeSafe AI.
+[MIT](https://github.com/agencyenterprise/jev-recipes/blob/main/LICENSE). Independent community project. Jev and TypeSafe are products of TypeSafe AI.

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "jev-recipes",
-  "version": "0.1.0",
+  "version": "0.2.0",
   "description": "Small, composable Jev decisions for retrieval, conversations, and agent workflows.",
   "type": "module",
   "license": "MIT",
@@ -306,16 +306,19 @@
   "scripts": {
     "clean": "rimraf dist",
     "build": "npm run clean && tsc -p tsconfig.json",
-    "typecheck": "tsc -p tsconfig.json --noEmit",
+    "typecheck": "tsc -p tsconfig.json --noEmit && tsc -p tests/tsconfig.json",
     "format": "prettier --write .",
     "format:check": "prettier --check .",
     "demo": "node dist/cli/index.js demo all",
-    "jev": "node --env-file-if-exists=.env dist/cli/index.js",
-    "ci": "npm run format:check && npm run typecheck && npm run build && npm run demo && npm run example:support",
+    "jev-recipes": "node --env-file-if-exists=.env dist/cli/index.js",
+    "ci": "npm run format:check && npm run typecheck && npm run test:coverage && npm run build && npm run demo && npm run example:support",
     "pack:check": "npm pack --dry-run",
     "prepack": "npm run build",
     "prepublishOnly": "npm run ci",
-    "example:support": "node --env-file-if-exists=.env dist/examples/support/index.js"
+    "example:support": "node --env-file-if-exists=.env dist/examples/support/index.js",
+    "test": "vitest run",
+    "test:watch": "vitest",
+    "test:coverage": "vitest run --coverage"
   },
   "dependencies": {
     "@typesafe-ai/sdk": "0.6.0",
@@ -323,9 +326,12 @@
   },
   "devDependencies": {
     "@types/node": "^22.0.0",
+    "@vitest/coverage-v8": "4.1.11",
     "prettier": "3.9.8",
     "rimraf": "6.1.3",
-    "typescript": "~5.9.3"
+    "typescript": "~5.9.3",
+    "vite": "6.4.3",
+    "vitest": "4.1.11"
   },
   "homepage": "https://github.com/agencyenterprise/jev-recipes#readme",
   "bugs": {

package/recipes/README.md

@@ -2,7 +2,7 @@
 
 66 small decisions for AI applications. Every recipe has its own input and result schemas, example, and usage guide. The package exports camelCase functions from kebab-case paths: `answerCoverage` from `jev-recipes/answer-coverage`, for example.
 
-Browse the groups below, or use `npm run jev -- list <query>` and `npm run jev -- describe <recipe>` from the repository. Discovery does not call Jev. Each recipe guide describes its inputs, results, limits, and review policy.
+After `npm install jev-recipes`, browse the groups below or use `npx jev-recipes list <query>` and `npx jev-recipes describe <recipe>` from your app’s directory. Discovery needs no API key. Each recipe guide describes its inputs, results, limits, and review policy.
 
 ## Answer quality
 

package/recipes/action-scope/README.md

@@ -46,4 +46,4 @@ Assesses semantic scope only. User authorization and access controls must be enf
 
 ## Example input
 
-[demo.json](demo.json) contains editable input and a hand-authored response. After building the repository, `npm run jev -- demo action-scope` shows the result offline. The fixture is an illustration, not an accuracy measurement. `npm run jev -- describe action-scope` shows the input and result schemas.
+[demo.json](demo.json) contains editable input and a hand-authored response. After installing `jev-recipes`, `npx jev-recipes demo action-scope` shows the result offline. The fixture is an illustration, not an accuracy measurement. `npx jev-recipes describe action-scope` shows the input and result schemas.

package/recipes/answer-consistency/README.md

@@ -47,4 +47,4 @@ Checks semantic consistency between two statements. Exact numeric and date compa
 
 ## Example input
 
-[demo.json](demo.json) contains editable input and a hand-authored response. After building the repository, `npm run jev -- demo answer-consistency` shows the result offline. The fixture is an illustration, not an accuracy measurement. `npm run jev -- describe answer-consistency` shows the input and result schemas.
+[demo.json](demo.json) contains editable input and a hand-authored response. After installing `jev-recipes`, `npx jev-recipes demo answer-consistency` shows the result offline. The fixture is an illustration, not an accuracy measurement. `npx jev-recipes describe answer-consistency` shows the input and result schemas.

package/recipes/answer-coverage/README.md

@@ -57,4 +57,4 @@ Checks supplied question IDs only. It does not extract questions or verify the d
 
 ## Example input
 
-[demo.json](demo.json) contains editable input and a hand-authored response. After building the repository, `npm run jev -- demo answer-coverage` shows the result offline. The fixture is an illustration, not an accuracy measurement. `npm run jev -- describe answer-coverage` shows the input and result schemas.
+[demo.json](demo.json) contains editable input and a hand-authored response. After installing `jev-recipes`, `npx jev-recipes demo answer-coverage` shows the result offline. The fixture is an illustration, not an accuracy measurement. `npx jev-recipes describe answer-coverage` shows the input and result schemas.

package/recipes/answer-invalidation/README.md

@@ -47,4 +47,4 @@ Assesses one supplied claim and source revision. It does not monitor changes, co
 
 ## Example input
 
-[demo.json](demo.json) contains editable input and a hand-authored response. After building the repository, `npm run jev -- demo answer-invalidation` shows the result offline. The fixture is an illustration, not an accuracy measurement. `npm run jev -- describe answer-invalidation` shows the input and result schemas.
+[demo.json](demo.json) contains editable input and a hand-authored response. After installing `jev-recipes`, `npx jev-recipes demo answer-invalidation` shows the result offline. The fixture is an illustration, not an accuracy measurement. `npx jev-recipes describe answer-invalidation` shows the input and result schemas.

package/recipes/answer-relevance/README.md

@@ -46,4 +46,4 @@ Relevance does not establish correctness or complete coverage. Use answer-covera
 
 ## Example input
 
-[demo.json](demo.json) contains editable input and a hand-authored response. After building the repository, `npm run jev -- demo answer-relevance` shows the result offline. The fixture is an illustration, not an accuracy measurement. `npm run jev -- describe answer-relevance` shows the input and result schemas.
+[demo.json](demo.json) contains editable input and a hand-authored response. After installing `jev-recipes`, `npx jev-recipes demo answer-relevance` shows the result offline. The fixture is an illustration, not an accuracy measurement. `npx jev-recipes describe answer-relevance` shows the input and result schemas.

package/recipes/answerability/README.md

@@ -51,4 +51,4 @@ Handle empty retrieval in application code before calling. This recipe does not
 
 ## Example input
 
-[demo.json](demo.json) contains editable input and a hand-authored response. After building the repository, `npm run jev -- demo answerability` shows an offline illustration, not an accuracy measurement. Use `npm run jev -- describe answerability` to inspect the input and result schemas.
+[demo.json](demo.json) contains editable input and a hand-authored response. After installing `jev-recipes`, `npx jev-recipes demo answerability` shows an offline illustration, not an accuracy measurement. Use `npx jev-recipes describe answerability` to inspect the input and result schemas.

package/recipes/argument-fit/README.md

@@ -48,4 +48,4 @@ Does not validate schemas, compare identifiers, or enforce authorization. Check
 
 ## Example input
 
-[demo.json](demo.json) contains editable input and a hand-authored response. After building the repository, `npm run jev -- demo argument-fit` shows the result offline. The fixture is an illustration, not an accuracy measurement. `npm run jev -- describe argument-fit` shows the input and result schemas.
+[demo.json](demo.json) contains editable input and a hand-authored response. After installing `jev-recipes`, `npx jev-recipes demo argument-fit` shows the result offline. The fixture is an illustration, not an accuracy measurement. `npx jev-recipes describe argument-fit` shows the input and result schemas.

package/recipes/attempted-step/README.md

@@ -45,4 +45,4 @@ Interprets reports of an attempt. It does not verify that the step was completed
 
 ## Example input
 
-[demo.json](demo.json) contains editable input and a hand-authored response. After building the repository, `npm run jev -- demo attempted-step` shows the result offline. The fixture is an illustration, not an accuracy measurement. `npm run jev -- describe attempted-step` shows the input and result schemas.
+[demo.json](demo.json) contains editable input and a hand-authored response. After installing `jev-recipes`, `npx jev-recipes demo attempted-step` shows the result offline. The fixture is an illustration, not an accuracy measurement. `npx jev-recipes describe attempted-step` shows the input and result schemas.

package/recipes/audience-fit/README.md

@@ -47,4 +47,4 @@ Uses only the supplied audience description. It does not infer ability from iden
 
 ## Example input
 
-[demo.json](demo.json) contains editable input and a hand-authored response. After building the repository, `npm run jev -- demo audience-fit` shows the result offline. The fixture is an illustration, not an accuracy measurement. `npm run jev -- describe audience-fit` shows the input and result schemas.
+[demo.json](demo.json) contains editable input and a hand-authored response. After installing `jev-recipes`, `npx jev-recipes demo audience-fit` shows the result offline. The fixture is an illustration, not an accuracy measurement. `npx jev-recipes describe audience-fit` shows the input and result schemas.

package/recipes/cache-match/README.md

@@ -48,4 +48,4 @@ Enforce tenant, permissions, version, and freshness checks in code before callin
 
 ## Example input
 
-[demo.json](demo.json) contains editable input and a hand-authored response. After building the repository, `npm run jev -- demo cache-match` shows the result offline. The fixture is an illustration, not an accuracy measurement. `npm run jev -- describe cache-match` shows the input and result schemas.
+[demo.json](demo.json) contains editable input and a hand-authored response. After installing `jev-recipes`, `npx jev-recipes demo cache-match` shows the result offline. The fixture is an illustration, not an accuracy measurement. `npx jev-recipes describe cache-match` shows the input and result schemas.

package/recipes/cancellation-check/README.md

@@ -47,4 +47,4 @@ Does not stop running work or infer permission to continue from silence. The cal
 
 ## Example input
 
-[demo.json](demo.json) contains editable input and a hand-authored response. After building the repository, `npm run jev -- demo cancellation-check` shows the result offline. The fixture is an illustration, not an accuracy measurement. `npm run jev -- describe cancellation-check` shows the input and result schemas.
+[demo.json](demo.json) contains editable input and a hand-authored response. After installing `jev-recipes`, `npx jev-recipes demo cancellation-check` shows the result offline. The fixture is an illustration, not an accuracy measurement. `npx jev-recipes describe cancellation-check` shows the input and result schemas.

package/recipes/certainty-match/README.md

@@ -46,4 +46,4 @@ Compares wording with a supplied assessment. It does not calibrate probabilities
 
 ## Example input
 
-[demo.json](demo.json) contains editable input and a hand-authored response. After building the repository, `npm run jev -- demo certainty-match` shows the result offline. The fixture is an illustration, not an accuracy measurement. `npm run jev -- describe certainty-match` shows the input and result schemas.
+[demo.json](demo.json) contains editable input and a hand-authored response. After installing `jev-recipes`, `npx jev-recipes demo certainty-match` shows the result offline. The fixture is an illustration, not an accuracy measurement. `npx jev-recipes describe certainty-match` shows the input and result schemas.

package/recipes/change-meaning/README.md

@@ -46,4 +46,4 @@ Compares supplied passages. It does not parse a repository diff or perform exact
 
 ## Example input
 
-[demo.json](demo.json) contains editable input and a hand-authored response. After building the repository, `npm run jev -- demo change-meaning` shows the result offline. The fixture is an illustration, not an accuracy measurement. `npm run jev -- describe change-meaning` shows the input and result schemas.
+[demo.json](demo.json) contains editable input and a hand-authored response. After installing `jev-recipes`, `npx jev-recipes demo change-meaning` shows the result offline. The fixture is an illustration, not an accuracy measurement. `npx jev-recipes describe change-meaning` shows the input and result schemas.

package/recipes/citation-match/README.md

@@ -48,4 +48,4 @@ Returns passages that independently support the entire claim. Joint support acro
 
 ## Example input
 
-[demo.json](demo.json) contains editable input and a hand-authored response. After building the repository, `npm run jev -- demo citation-match` shows the result offline. The fixture is an illustration, not an accuracy measurement. `npm run jev -- describe citation-match` shows the input and result schemas.
+[demo.json](demo.json) contains editable input and a hand-authored response. After installing `jev-recipes`, `npx jev-recipes demo citation-match` shows the result offline. The fixture is an illustration, not an accuracy measurement. `npx jev-recipes describe citation-match` shows the input and result schemas.

package/recipes/citation-needed/README.md

@@ -46,4 +46,4 @@ Assesses a supplied citation policy; does not find sources or determine whether
 
 ## Example input
 
-[demo.json](demo.json) contains editable input and a hand-authored response. After building the repository, `npm run jev -- demo citation-needed` shows the result offline. The fixture is an illustration, not an accuracy measurement. `npm run jev -- describe citation-needed` shows the input and result schemas.
+[demo.json](demo.json) contains editable input and a hand-authored response. After installing `jev-recipes`, `npx jev-recipes demo citation-needed` shows the result offline. The fixture is an illustration, not an accuracy measurement. `npx jev-recipes describe citation-needed` shows the input and result schemas.

package/recipes/clarify/README.md

@@ -58,4 +58,4 @@ Your application supplies the requirements and maps their IDs to follow-up quest
 
 ## Example input
 
-[demo.json](demo.json) contains editable input and a hand-authored response. After building the repository, `npm run jev -- demo clarify` shows an offline illustration, not an accuracy measurement. Use `npm run jev -- describe clarify` to inspect the input and result schemas.
+[demo.json](demo.json) contains editable input and a hand-authored response. After installing `jev-recipes`, `npx jev-recipes demo clarify` shows an offline illustration, not an accuracy measurement. Use `npx jev-recipes describe clarify` to inspect the input and result schemas.

package/recipes/confirmation-match/README.md

@@ -46,4 +46,4 @@ Interprets language only. Approval identity, authority, scope, expiration, and a
 
 ## Example input
 
-[demo.json](demo.json) contains editable input and a hand-authored response. After building the repository, `npm run jev -- demo confirmation-match` shows the result offline. The fixture is an illustration, not an accuracy measurement. `npm run jev -- describe confirmation-match` shows the input and result schemas.
+[demo.json](demo.json) contains editable input and a hand-authored response. After installing `jev-recipes`, `npx jev-recipes demo confirmation-match` shows the result offline. The fixture is an illustration, not an accuracy measurement. `npx jev-recipes describe confirmation-match` shows the input and result schemas.

package/recipes/context-role/README.md

@@ -46,4 +46,4 @@ Classifies a passage contribution. It does not rank sources or prove the answer
 
 ## Example input
 
-[demo.json](demo.json) contains editable input and a hand-authored response. After building the repository, `npm run jev -- demo context-role` shows the result offline. The fixture is an illustration, not an accuracy measurement. `npm run jev -- describe context-role` shows the input and result schemas.
+[demo.json](demo.json) contains editable input and a hand-authored response. After installing `jev-recipes`, `npx jev-recipes demo context-role` shows the result offline. The fixture is an illustration, not an accuracy measurement. `npx jev-recipes describe context-role` shows the input and result schemas.

package/recipes/correction-target/README.md

@@ -49,4 +49,4 @@ Selects one correction target. It does not extract a replacement value or update
 
 ## Example input
 
-[demo.json](demo.json) contains editable input and a hand-authored response. After building the repository, `npm run jev -- demo correction-target` shows the result offline. The fixture is an illustration, not an accuracy measurement. `npm run jev -- describe correction-target` shows the input and result schemas.
+[demo.json](demo.json) contains editable input and a hand-authored response. After installing `jev-recipes`, `npx jev-recipes demo correction-target` shows the result offline. The fixture is an illustration, not an accuracy measurement. `npx jev-recipes describe correction-target` shows the input and result schemas.

package/recipes/document-role/README.md

@@ -48,4 +48,4 @@ Returns one primary role from the supplied text. It does not read files, split m
 
 ## Example input
 
-[demo.json](demo.json) contains editable input and a hand-authored response. After building the repository, `npm run jev -- demo document-role` shows the result offline. The fixture is an illustration, not an accuracy measurement. `npm run jev -- describe document-role` shows the input and result schemas.
+[demo.json](demo.json) contains editable input and a hand-authored response. After installing `jev-recipes`, `npx jev-recipes demo document-role` shows the result offline. The fixture is an illustration, not an accuracy measurement. `npx jev-recipes describe document-role` shows the input and result schemas.

package/recipes/draft-compare/README.md

@@ -51,4 +51,4 @@ Makes a relative judgment against your rubric. A preferred draft can still conta
 
 ## Example input
 
-[demo.json](demo.json) contains editable input and a hand-authored response. After building the repository, `npm run jev -- demo draft-compare` shows the result offline. The fixture is an illustration, not an accuracy measurement. `npm run jev -- describe draft-compare` shows the input and result schemas.
+[demo.json](demo.json) contains editable input and a hand-authored response. After installing `jev-recipes`, `npx jev-recipes demo draft-compare` shows the result offline. The fixture is an illustration, not an accuracy measurement. `npx jev-recipes describe draft-compare` shows the input and result schemas.

package/recipes/evidence-conflict/README.md

@@ -48,4 +48,4 @@ Does not decide which source is authoritative. Exact numbers, timestamps, and ve
 
 ## Example input
 
-[demo.json](demo.json) contains editable input and a hand-authored response. After building the repository, `npm run jev -- demo evidence-conflict` shows the result offline. The fixture is an illustration, not an accuracy measurement. `npm run jev -- describe evidence-conflict` shows the input and result schemas.
+[demo.json](demo.json) contains editable input and a hand-authored response. After installing `jev-recipes`, `npx jev-recipes demo evidence-conflict` shows the result offline. The fixture is an illustration, not an accuracy measurement. `npx jev-recipes describe evidence-conflict` shows the input and result schemas.

package/recipes/evidence-novelty/README.md

@@ -53,4 +53,4 @@ Assesses novelty within the supplied set. It does not establish correctness or d
 
 ## Example input
 
-[demo.json](demo.json) contains editable input and a hand-authored response. After building the repository, `npm run jev -- demo evidence-novelty` shows the result offline. The fixture is an illustration, not an accuracy measurement. `npm run jev -- describe evidence-novelty` shows the input and result schemas.
+[demo.json](demo.json) contains editable input and a hand-authored response. After installing `jev-recipes`, `npx jev-recipes demo evidence-novelty` shows the result offline. The fixture is an illustration, not an accuracy measurement. `npx jev-recipes describe evidence-novelty` shows the input and result schemas.

package/recipes/fact-stability/README.md

@@ -44,4 +44,4 @@ Does not establish truth, expiration times, or freshness. Refresh policies and t
 
 ## Example input
 
-[demo.json](demo.json) contains editable input and a hand-authored response. After building the repository, `npm run jev -- demo fact-stability` shows the result offline. The fixture is an illustration, not an accuracy measurement. `npm run jev -- describe fact-stability` shows the input and result schemas.
+[demo.json](demo.json) contains editable input and a hand-authored response. After installing `jev-recipes`, `npx jev-recipes demo fact-stability` shows the result offline. The fixture is an illustration, not an accuracy measurement. `npx jev-recipes describe fact-stability` shows the input and result schemas.

package/recipes/failure-kind/README.md

@@ -49,4 +49,4 @@ Maps text to your categories. Use structured error codes first; this recipe does
 
 ## Example input
 
-[demo.json](demo.json) contains editable input and a hand-authored response. After building the repository, `npm run jev -- demo failure-kind` shows the result offline. The fixture is an illustration, not an accuracy measurement. `npm run jev -- describe failure-kind` shows the input and result schemas.
+[demo.json](demo.json) contains editable input and a hand-authored response. After installing `jev-recipes`, `npx jev-recipes demo failure-kind` shows the result offline. The fixture is an illustration, not an accuracy measurement. `npx jev-recipes describe failure-kind` shows the input and result schemas.

package/recipes/feedback-kind/README.md

@@ -48,4 +48,4 @@ Returns one primary category. It does not create a ticket, extract multiple issu
 
 ## Example input
 
-[demo.json](demo.json) contains editable input and a hand-authored response. After building the repository, `npm run jev -- demo feedback-kind` shows the result offline. The fixture is an illustration, not an accuracy measurement. `npm run jev -- describe feedback-kind` shows the input and result schemas.
+[demo.json](demo.json) contains editable input and a hand-authored response. After installing `jev-recipes`, `npx jev-recipes demo feedback-kind` shows the result offline. The fixture is an illustration, not an accuracy measurement. `npx jev-recipes describe feedback-kind` shows the input and result schemas.

package/recipes/field-select/README.md

@@ -50,4 +50,4 @@ Chooses among caller-supplied candidates. Extract candidates with a parser or ge
 
 ## Example input
 
-[demo.json](demo.json) contains editable input and a hand-authored response. After building the repository, `npm run jev -- demo field-select` shows the result offline. The fixture is an illustration, not an accuracy measurement. `npm run jev -- describe field-select` shows the input and result schemas.
+[demo.json](demo.json) contains editable input and a hand-authored response. After installing `jev-recipes`, `npx jev-recipes demo field-select` shows the result offline. The fixture is an illustration, not an accuracy measurement. `npx jev-recipes describe field-select` shows the input and result schemas.

package/recipes/followup-link/README.md

@@ -49,4 +49,4 @@ Selects from the supplied earlier requests. Supply enough conversation context t
 
 ## Example input
 
-[demo.json](demo.json) contains editable input and a hand-authored response. After building the repository, `npm run jev -- demo followup-link` shows the result offline. The fixture is an illustration, not an accuracy measurement. `npm run jev -- describe followup-link` shows the input and result schemas.
+[demo.json](demo.json) contains editable input and a hand-authored response. After installing `jev-recipes`, `npx jev-recipes demo followup-link` shows the result offline. The fixture is an illustration, not an accuracy measurement. `npx jev-recipes describe followup-link` shows the input and result schemas.

package/recipes/freshness-needed/README.md

@@ -43,4 +43,4 @@ Does not check timestamps, determine whether a source is up to date, or retrieve
 
 ## Example input
 
-[demo.json](demo.json) contains editable input and a hand-authored response. After building the repository, `npm run jev -- demo freshness-needed` shows the result offline. The fixture is an illustration, not an accuracy measurement. `npm run jev -- describe freshness-needed` shows the input and result schemas.
+[demo.json](demo.json) contains editable input and a hand-authored response. After installing `jev-recipes`, `npx jev-recipes demo freshness-needed` shows the result offline. The fixture is an illustration, not an accuracy measurement. `npx jev-recipes describe freshness-needed` shows the input and result schemas.

package/recipes/frustration-signal/README.md

@@ -44,4 +44,4 @@ Classifies expressed language only. It does not diagnose emotions or determine c
 
 ## Example input
 
-[demo.json](demo.json) contains editable input and a hand-authored response. After building the repository, `npm run jev -- demo frustration-signal` shows the result offline. The fixture is an illustration, not an accuracy measurement. `npm run jev -- describe frustration-signal` shows the input and result schemas.
+[demo.json](demo.json) contains editable input and a hand-authored response. After installing `jev-recipes`, `npx jev-recipes demo frustration-signal` shows the result offline. The fixture is an illustration, not an accuracy measurement. `npx jev-recipes describe frustration-signal` shows the input and result schemas.

package/recipes/handoff/README.md

@@ -53,4 +53,4 @@ Write observable rules and supply the facts needed to evaluate them. Compute exa
 
 ## Example input
 
-[demo.json](demo.json) contains editable input and a hand-authored response. After building the repository, `npm run jev -- demo handoff` shows an offline illustration, not an accuracy measurement. Use `npm run jev -- describe handoff` to inspect the input and result schemas.
+[demo.json](demo.json) contains editable input and a hand-authored response. After installing `jev-recipes`, `npx jev-recipes demo handoff` shows an offline illustration, not an accuracy measurement. Use `npx jev-recipes describe handoff` to inspect the input and result schemas.

package/recipes/incident-match/README.md

@@ -49,4 +49,4 @@ Matches only incidents supplied by the caller. Filter incident status, dates, af
 
 ## Example input
 
-[demo.json](demo.json) contains editable input and a hand-authored response. After building the repository, `npm run jev -- demo incident-match` shows the result offline. The fixture is an illustration, not an accuracy measurement. `npm run jev -- describe incident-match` shows the input and result schemas.
+[demo.json](demo.json) contains editable input and a hand-authored response. After installing `jev-recipes`, `npx jev-recipes demo incident-match` shows the result offline. The fixture is an illustration, not an accuracy measurement. `npx jev-recipes describe incident-match` shows the input and result schemas.

package/recipes/instruction-fit/README.md

@@ -46,4 +46,4 @@ Checks semantic applicability. Instruction priority, trust, permissions, and con
 
 ## Example input
 
-[demo.json](demo.json) contains editable input and a hand-authored response. After building the repository, `npm run jev -- demo instruction-fit` shows the result offline. The fixture is an illustration, not an accuracy measurement. `npm run jev -- describe instruction-fit` shows the input and result schemas.
+[demo.json](demo.json) contains editable input and a hand-authored response. After installing `jev-recipes`, `npx jev-recipes demo instruction-fit` shows the result offline. The fixture is an illustration, not an accuracy measurement. `npx jev-recipes describe instruction-fit` shows the input and result schemas.

package/recipes/intent-change/README.md

@@ -47,4 +47,4 @@ Classifies a goal change. It does not rewrite the goal, alter a task queue, or m
 
 ## Example input
 
-[demo.json](demo.json) contains editable input and a hand-authored response. After building the repository, `npm run jev -- demo intent-change` shows the result offline. The fixture is an illustration, not an accuracy measurement. `npm run jev -- describe intent-change` shows the input and result schemas.
+[demo.json](demo.json) contains editable input and a hand-authored response. After installing `jev-recipes`, `npx jev-recipes demo intent-change` shows the result offline. The fixture is an illustration, not an accuracy measurement. `npx jev-recipes describe intent-change` shows the input and result schemas.

package/recipes/issue-impact/README.md

@@ -45,4 +45,4 @@ Assesses reported impact, not verified system severity. Service commitments and
 
 ## Example input
 
-[demo.json](demo.json) contains editable input and a hand-authored response. After building the repository, `npm run jev -- demo issue-impact` shows the result offline. The fixture is an illustration, not an accuracy measurement. `npm run jev -- describe issue-impact` shows the input and result schemas.
+[demo.json](demo.json) contains editable input and a hand-authored response. After installing `jev-recipes`, `npx jev-recipes demo issue-impact` shows the result offline. The fixture is an illustration, not an accuracy measurement. `npx jev-recipes describe issue-impact` shows the input and result schemas.

package/recipes/memory-relation/README.md

@@ -49,4 +49,4 @@ Compares two supplied facts. It does not select a memory to overwrite or resolve
 
 ## Example input
 
-[demo.json](demo.json) contains editable input and a hand-authored response. After building the repository, `npm run jev -- demo memory-relation` shows the result offline. The fixture is an illustration, not an accuracy measurement. `npm run jev -- describe memory-relation` shows the input and result schemas.
+[demo.json](demo.json) contains editable input and a hand-authored response. After installing `jev-recipes`, `npx jev-recipes demo memory-relation` shows the result offline. The fixture is an illustration, not an accuracy measurement. `npx jev-recipes describe memory-relation` shows the input and result schemas.

package/recipes/memory-scope/README.md

@@ -47,4 +47,4 @@ Identifies semantic scope. It does not identify a storage tenant, establish cons
 
 ## Example input
 
-[demo.json](demo.json) contains editable input and a hand-authored response. After building the repository, `npm run jev -- demo memory-scope` shows the result offline. The fixture is an illustration, not an accuracy measurement. `npm run jev -- describe memory-scope` shows the input and result schemas.
+[demo.json](demo.json) contains editable input and a hand-authored response. After installing `jev-recipes`, `npx jev-recipes demo memory-scope` shows the result offline. The fixture is an illustration, not an accuracy measurement. `npx jev-recipes describe memory-scope` shows the input and result schemas.

package/recipes/memory-value/README.md

@@ -47,4 +47,4 @@ Assesses usefulness only. Storage consent, sensitive-data policy, retention, and
 
 ## Example input
 
-[demo.json](demo.json) contains editable input and a hand-authored response. After building the repository, `npm run jev -- demo memory-value` shows the result offline. The fixture is an illustration, not an accuracy measurement. `npm run jev -- describe memory-value` shows the input and result schemas.
+[demo.json](demo.json) contains editable input and a hand-authored response. After installing `jev-recipes`, `npx jev-recipes demo memory-value` shows the result offline. The fixture is an illustration, not an accuracy measurement. `npx jev-recipes describe memory-value` shows the input and result schemas.

package/recipes/passage-duplicate/README.md

@@ -46,4 +46,4 @@ Compares a supplied pair. It does not search a corpus, cluster documents, or rem
 
 ## Example input
 
-[demo.json](demo.json) contains editable input and a hand-authored response. After building the repository, `npm run jev -- demo passage-duplicate` shows the result offline. The fixture is an illustration, not an accuracy measurement. `npm run jev -- describe passage-duplicate` shows the input and result schemas.
+[demo.json](demo.json) contains editable input and a hand-authored response. After installing `jev-recipes`, `npx jev-recipes demo passage-duplicate` shows the result offline. The fixture is an illustration, not an accuracy measurement. `npx jev-recipes describe passage-duplicate` shows the input and result schemas.

package/recipes/preference-kind/README.md

@@ -45,4 +45,4 @@ Classifies a statement. It does not infer unexpressed preferences or grant permi
 
 ## Example input
 
-[demo.json](demo.json) contains editable input and a hand-authored response. After building the repository, `npm run jev -- demo preference-kind` shows the result offline. The fixture is an illustration, not an accuracy measurement. `npm run jev -- describe preference-kind` shows the input and result schemas.
+[demo.json](demo.json) contains editable input and a hand-authored response. After installing `jev-recipes`, `npx jev-recipes demo preference-kind` shows the result offline. The fixture is an illustration, not an accuracy measurement. `npx jev-recipes describe preference-kind` shows the input and result schemas.

package/recipes/promise-check/README.md

@@ -45,4 +45,4 @@ Reviews expressed promises. It does not approve refunds, establish contractual o
 
 ## Example input
 
-[demo.json](demo.json) contains editable input and a hand-authored response. After building the repository, `npm run jev -- demo promise-check` shows the result offline. The fixture is an illustration, not an accuracy measurement. `npm run jev -- describe promise-check` shows the input and result schemas.
+[demo.json](demo.json) contains editable input and a hand-authored response. After installing `jev-recipes`, `npx jev-recipes demo promise-check` shows the result offline. The fixture is an illustration, not an accuracy measurement. `npx jev-recipes describe promise-check` shows the input and result schemas.

package/recipes/query-equivalence/README.md

@@ -47,4 +47,4 @@ Compares supplied questions. It does not rewrite them or establish that an exist
 
 ## Example input
 
-[demo.json](demo.json) contains editable input and a hand-authored response. After building the repository, `npm run jev -- demo query-equivalence` shows the result offline. The fixture is an illustration, not an accuracy measurement. `npm run jev -- describe query-equivalence` shows the input and result schemas.
+[demo.json](demo.json) contains editable input and a hand-authored response. After installing `jev-recipes`, `npx jev-recipes demo query-equivalence` shows the result offline. The fixture is an illustration, not an accuracy measurement. `npx jev-recipes describe query-equivalence` shows the input and result schemas.

package/recipes/query-specificity/README.md

@@ -44,4 +44,4 @@ Assesses focus only. Use clarify when the application has explicit required fiel
 
 ## Example input
 
-[demo.json](demo.json) contains editable input and a hand-authored response. After building the repository, `npm run jev -- demo query-specificity` shows the result offline. The fixture is an illustration, not an accuracy measurement. `npm run jev -- describe query-specificity` shows the input and result schemas.
+[demo.json](demo.json) contains editable input and a hand-authored response. After installing `jev-recipes`, `npx jev-recipes demo query-specificity` shows the result offline. The fixture is an illustration, not an accuracy measurement. `npx jev-recipes describe query-specificity` shows the input and result schemas.

package/recipes/reference-resolve/README.md

@@ -51,4 +51,4 @@ Resolves a supplied reference among candidates. It does not extract references,
 
 ## Example input
 
-[demo.json](demo.json) contains editable input and a hand-authored response. After building the repository, `npm run jev -- demo reference-resolve` shows the result offline. The fixture is an illustration, not an accuracy measurement. `npm run jev -- describe reference-resolve` shows the input and result schemas.
+[demo.json](demo.json) contains editable input and a hand-authored response. After installing `jev-recipes`, `npx jev-recipes demo reference-resolve` shows the result offline. The fixture is an illustration, not an accuracy measurement. `npx jev-recipes describe reference-resolve` shows the input and result schemas.

package/recipes/repeated-attempt/README.md

@@ -47,4 +47,4 @@ Compares two attempts only. Counting repeats, deciding whether a retry is justif
 
 ## Example input
 
-[demo.json](demo.json) contains editable input and a hand-authored response. After building the repository, `npm run jev -- demo repeated-attempt` shows the result offline. The fixture is an illustration, not an accuracy measurement. `npm run jev -- describe repeated-attempt` shows the input and result schemas.
+[demo.json](demo.json) contains editable input and a hand-authored response. After installing `jev-recipes`, `npx jev-recipes demo repeated-attempt` shows the result offline. The fixture is an illustration, not an accuracy measurement. `npx jev-recipes describe repeated-attempt` shows the input and result schemas.

package/recipes/reply-template-match/README.md

@@ -49,4 +49,4 @@ Selects a supplied template. It does not fill placeholders, approve its content,
 
 ## Example input
 
-[demo.json](demo.json) contains editable input and a hand-authored response. After building the repository, `npm run jev -- demo reply-template-match` shows the result offline. The fixture is an illustration, not an accuracy measurement. `npm run jev -- describe reply-template-match` shows the input and result schemas.
+[demo.json](demo.json) contains editable input and a hand-authored response. After installing `jev-recipes`, `npx jev-recipes demo reply-template-match` shows the result offline. The fixture is an illustration, not an accuracy measurement. `npx jev-recipes describe reply-template-match` shows the input and result schemas.

package/recipes/rerank/README.md

@@ -52,4 +52,4 @@ Relevance does not establish that a passage is true or sufficient to answer the
 
 ## Example input
 
-[demo.json](demo.json) contains editable input and a hand-authored response. After building the repository, `npm run jev -- demo rerank` shows an offline illustration, not an accuracy measurement. Use `npm run jev -- describe rerank` to inspect the input and result schemas.
+[demo.json](demo.json) contains editable input and a hand-authored response. After installing `jev-recipes`, `npx jev-recipes demo rerank` shows an offline illustration, not an accuracy measurement. Use `npx jev-recipes describe rerank` to inspect the input and result schemas.

package/recipes/resolution-check/README.md

@@ -46,4 +46,4 @@ Interprets the customer report. It does not verify the system state, close a tic
 
 ## Example input
 
-[demo.json](demo.json) contains editable input and a hand-authored response. After building the repository, `npm run jev -- demo resolution-check` shows the result offline. The fixture is an illustration, not an accuracy measurement. `npm run jev -- describe resolution-check` shows the input and result schemas.
+[demo.json](demo.json) contains editable input and a hand-authored response. After installing `jev-recipes`, `npx jev-recipes demo resolution-check` shows the result offline. The fixture is an illustration, not an accuracy measurement. `npx jev-recipes describe resolution-check` shows the input and result schemas.

package/recipes/response-needed/README.md

@@ -45,4 +45,4 @@ Assesses conversational need. Channel-specific response obligations and customer
 
 ## Example input
 
-[demo.json](demo.json) contains editable input and a hand-authored response. After building the repository, `npm run jev -- demo response-needed` shows the result offline. The fixture is an illustration, not an accuracy measurement. `npm run jev -- describe response-needed` shows the input and result schemas.
+[demo.json](demo.json) contains editable input and a hand-authored response. After installing `jev-recipes`, `npx jev-recipes demo response-needed` shows the result offline. The fixture is an illustration, not an accuracy measurement. `npx jev-recipes describe response-needed` shows the input and result schemas.

package/recipes/result-outcome/README.md

@@ -46,4 +46,4 @@ Interprets a report; it does not independently confirm an external action occurr
 
 ## Example input
 
-[demo.json](demo.json) contains editable input and a hand-authored response. After building the repository, `npm run jev -- demo result-outcome` shows the result offline. The fixture is an illustration, not an accuracy measurement. `npm run jev -- describe result-outcome` shows the input and result schemas.
+[demo.json](demo.json) contains editable input and a hand-authored response. After installing `jev-recipes`, `npx jev-recipes demo result-outcome` shows the result offline. The fixture is an illustration, not an accuracy measurement. `npx jev-recipes describe result-outcome` shows the input and result schemas.

package/recipes/result-usefulness/README.md

@@ -46,4 +46,4 @@ Assesses response content, not transport success or source truth. Handle empty b
 
 ## Example input
 
-[demo.json](demo.json) contains editable input and a hand-authored response. After building the repository, `npm run jev -- demo result-usefulness` shows the result offline. The fixture is an illustration, not an accuracy measurement. `npm run jev -- describe result-usefulness` shows the input and result schemas.
+[demo.json](demo.json) contains editable input and a hand-authored response. After installing `jev-recipes`, `npx jev-recipes demo result-usefulness` shows the result offline. The fixture is an illustration, not an accuracy measurement. `npx jev-recipes describe result-usefulness` shows the input and result schemas.

package/recipes/retrieval-needed/README.md

@@ -45,4 +45,4 @@ Assesses information needs without searching. A no-retrieval decision does not e
 
 ## Example input
 
-[demo.json](demo.json) contains editable input and a hand-authored response. After building the repository, `npm run jev -- demo retrieval-needed` shows the result offline. The fixture is an illustration, not an accuracy measurement. `npm run jev -- describe retrieval-needed` shows the input and result schemas.
+[demo.json](demo.json) contains editable input and a hand-authored response. After installing `jev-recipes`, `npx jev-recipes demo retrieval-needed` shows the result offline. The fixture is an illustration, not an accuracy measurement. `npx jev-recipes describe retrieval-needed` shows the input and result schemas.

package/recipes/route/README.md

@@ -44,4 +44,4 @@ Routes with overlapping descriptions can be difficult to distinguish. Describe t
 
 ## Example input
 
-[demo.json](demo.json) contains editable input and a hand-authored response. After building the repository, `npm run jev -- demo route` shows an offline illustration, not an accuracy measurement. Use `npm run jev -- describe route` to inspect the input and result schemas.
+[demo.json](demo.json) contains editable input and a hand-authored response. After installing `jev-recipes`, `npx jev-recipes demo route` shows an offline illustration, not an accuracy measurement. Use `npx jev-recipes describe route` to inspect the input and result schemas.

package/recipes/source-applicability/README.md

@@ -45,4 +45,4 @@ Assesses semantic scope. Enforce tenant, access, exact version, and region const
 
 ## Example input
 
-[demo.json](demo.json) contains editable input and a hand-authored response. After building the repository, `npm run jev -- demo source-applicability` shows the result offline. The fixture is an illustration, not an accuracy measurement. `npm run jev -- describe source-applicability` shows the input and result schemas.
+[demo.json](demo.json) contains editable input and a hand-authored response. After installing `jev-recipes`, `npx jev-recipes demo source-applicability` shows the result offline. The fixture is an illustration, not an accuracy measurement. `npx jev-recipes describe source-applicability` shows the input and result schemas.

package/recipes/step-complete/README.md

@@ -45,4 +45,4 @@ Assesses supplied evidence for one condition. Use exact system state checks when
 
 ## Example input
 
-[demo.json](demo.json) contains editable input and a hand-authored response. After building the repository, `npm run jev -- demo step-complete` shows the result offline. The fixture is an illustration, not an accuracy measurement. `npm run jev -- describe step-complete` shows the input and result schemas.
+[demo.json](demo.json) contains editable input and a hand-authored response. After installing `jev-recipes`, `npx jev-recipes demo step-complete` shows the result offline. The fixture is an illustration, not an accuracy measurement. `npx jev-recipes describe step-complete` shows the input and result schemas.

package/recipes/step-progress/README.md

@@ -48,4 +48,4 @@ Compares one observation with a supplied prior state. It does not measure elapse
 
 ## Example input
 
-[demo.json](demo.json) contains editable input and a hand-authored response. After building the repository, `npm run jev -- demo step-progress` shows the result offline. The fixture is an illustration, not an accuracy measurement. `npm run jev -- describe step-progress` shows the input and result schemas.
+[demo.json](demo.json) contains editable input and a hand-authored response. After installing `jev-recipes`, `npx jev-recipes demo step-progress` shows the result offline. The fixture is an illustration, not an accuracy measurement. `npx jev-recipes describe step-progress` shows the input and result schemas.

package/recipes/summary-coverage/README.md

@@ -57,4 +57,4 @@ Checks the points you supply. It does not select important points from a transcr
 
 ## Example input
 
-[demo.json](demo.json) contains editable input and a hand-authored response. After building the repository, `npm run jev -- demo summary-coverage` shows the result offline. The fixture is an illustration, not an accuracy measurement. `npm run jev -- describe summary-coverage` shows the input and result schemas.
+[demo.json](demo.json) contains editable input and a hand-authored response. After installing `jev-recipes`, `npx jev-recipes demo summary-coverage` shows the result offline. The fixture is an illustration, not an accuracy measurement. `npx jev-recipes describe summary-coverage` shows the input and result schemas.

package/recipes/ticket-match/README.md

@@ -47,4 +47,4 @@ Does not merge tickets or establish a shared root cause from similar symptoms al
 
 ## Example input
 
-[demo.json](demo.json) contains editable input and a hand-authored response. After building the repository, `npm run jev -- demo ticket-match` shows the result offline. The fixture is an illustration, not an accuracy measurement. `npm run jev -- describe ticket-match` shows the input and result schemas.
+[demo.json](demo.json) contains editable input and a hand-authored response. After installing `jev-recipes`, `npx jev-recipes demo ticket-match` shows the result offline. The fixture is an illustration, not an accuracy measurement. `npx jev-recipes describe ticket-match` shows the input and result schemas.

package/recipes/tone-check/README.md

@@ -52,4 +52,4 @@ Checks supplied writing criteria. It does not rewrite text, determine factual ac
 
 ## Example input
 
-[demo.json](demo.json) contains editable input and a hand-authored response. After building the repository, `npm run jev -- demo tone-check` shows the result offline. The fixture is an illustration, not an accuracy measurement. `npm run jev -- describe tone-check` shows the input and result schemas.
+[demo.json](demo.json) contains editable input and a hand-authored response. After installing `jev-recipes`, `npx jev-recipes demo tone-check` shows the result offline. The fixture is an illustration, not an accuracy measurement. `npx jev-recipes describe tone-check` shows the input and result schemas.

package/recipes/tool-fit/README.md

@@ -46,4 +46,4 @@ Assesses a supplied capability description. It does not discover tools, validate
 
 ## Example input
 
-[demo.json](demo.json) contains editable input and a hand-authored response. After building the repository, `npm run jev -- demo tool-fit` shows the result offline. The fixture is an illustration, not an accuracy measurement. `npm run jev -- describe tool-fit` shows the input and result schemas.
+[demo.json](demo.json) contains editable input and a hand-authored response. After installing `jev-recipes`, `npx jev-recipes demo tool-fit` shows the result offline. The fixture is an illustration, not an accuracy measurement. `npx jev-recipes describe tool-fit` shows the input and result schemas.

package/recipes/topic-shift/README.md

@@ -47,4 +47,4 @@ Compares one message with a supplied topic. It does not generate topic labels or
 
 ## Example input
 
-[demo.json](demo.json) contains editable input and a hand-authored response. After building the repository, `npm run jev -- demo topic-shift` shows the result offline. The fixture is an illustration, not an accuracy measurement. `npm run jev -- describe topic-shift` shows the input and result schemas.
+[demo.json](demo.json) contains editable input and a hand-authored response. After installing `jev-recipes`, `npx jev-recipes demo topic-shift` shows the result offline. The fixture is an illustration, not an accuracy measurement. `npx jev-recipes describe topic-shift` shows the input and result schemas.

package/recipes/troubleshooting-fit/README.md

@@ -46,4 +46,4 @@ Assesses a supplied procedure; it does not diagnose a root cause, generate steps
 
 ## Example input
 
-[demo.json](demo.json) contains editable input and a hand-authored response. After building the repository, `npm run jev -- demo troubleshooting-fit` shows the result offline. The fixture is an illustration, not an accuracy measurement. `npm run jev -- describe troubleshooting-fit` shows the input and result schemas.
+[demo.json](demo.json) contains editable input and a hand-authored response. After installing `jev-recipes`, `npx jev-recipes demo troubleshooting-fit` shows the result offline. The fixture is an illustration, not an accuracy measurement. `npx jev-recipes describe troubleshooting-fit` shows the input and result schemas.

package/recipes/turn-intent/README.md

@@ -49,4 +49,4 @@ Returns the primary purpose only. It does not split a message into separate requ
 
 ## Example input
 
-[demo.json](demo.json) contains editable input and a hand-authored response. After building the repository, `npm run jev -- demo turn-intent` shows the result offline. The fixture is an illustration, not an accuracy measurement. `npm run jev -- describe turn-intent` shows the input and result schemas.
+[demo.json](demo.json) contains editable input and a hand-authored response. After installing `jev-recipes`, `npx jev-recipes demo turn-intent` shows the result offline. The fixture is an illustration, not an accuracy measurement. `npx jev-recipes describe turn-intent` shows the input and result schemas.

package/recipes/urgency-signal/README.md

@@ -44,4 +44,4 @@ Detects an expressed urgency request. Compute deadline proximity and apply incid
 
 ## Example input
 
-[demo.json](demo.json) contains editable input and a hand-authored response. After building the repository, `npm run jev -- demo urgency-signal` shows the result offline. The fixture is an illustration, not an accuracy measurement. `npm run jev -- describe urgency-signal` shows the input and result schemas.
+[demo.json](demo.json) contains editable input and a hand-authored response. After installing `jev-recipes`, `npx jev-recipes demo urgency-signal` shows the result offline. The fixture is an illustration, not an accuracy measurement. `npx jev-recipes describe urgency-signal` shows the input and result schemas.

package/recipes/verify/README.md

@@ -51,4 +51,4 @@ Checks only supplied claim/evidence pairs. It does not extract claims, retrieve
 
 ## Example input
 
-[demo.json](demo.json) contains editable input and a hand-authored response. After building the repository, `npm run jev -- demo verify` shows an offline illustration, not an accuracy measurement. Use `npm run jev -- describe verify` to inspect the input and result schemas.
+[demo.json](demo.json) contains editable input and a hand-authored response. After installing `jev-recipes`, `npx jev-recipes demo verify` shows an offline illustration, not an accuracy measurement. Use `npx jev-recipes describe verify` to inspect the input and result schemas.

package/recipes/workaround-fit/README.md

@@ -47,4 +47,4 @@ Assesses described compatibility. It does not establish operational safety, exec
 
 ## Example input
 
-[demo.json](demo.json) contains editable input and a hand-authored response. After building the repository, `npm run jev -- demo workaround-fit` shows the result offline. The fixture is an illustration, not an accuracy measurement. `npm run jev -- describe workaround-fit` shows the input and result schemas.
+[demo.json](demo.json) contains editable input and a hand-authored response. After installing `jev-recipes`, `npx jev-recipes demo workaround-fit` shows the result offline. The fixture is an illustration, not an accuracy measurement. `npx jev-recipes describe workaround-fit` shows the input and result schemas.