@eigenpal/cli 0.7.2 → 0.8.0

package/dist/skill/reference/cli/agents.md

@@ -1,6 +1,6 @@
 # eigenpal agents
 
-Manage Eigenpal agents: Git source, datasets, runs, experiments, sessions, and releases.
+Manage Eigenpal agents: Git source, datasets, experiments, sessions, and releases.
 
 ## Contents
 
@@ -157,20 +157,20 @@ agents
 | Command                                                         | Description                                                                |
 | --------------------------------------------------------------- | -------------------------------------------------------------------------- |
 | `eigenpal agents dataset list\|ls [options] <agent-id-or-slug>` | List dataset examples for an agent.                                        |
-| `eigenpal agents dataset push [options] <agent-id-or-slug>`     | Upload dataset examples from a local dataset directory.                    |
-| `eigenpal agents dataset pull [options] <agent-id-or-slug>`     | Download an agent dataset directory.                                       |
+| `eigenpal agents dataset push [options] <agent-id-or-slug>`     | Upload dataset examples from a local dataset directory or zip archive.     |
+| `eigenpal agents dataset pull [options] <agent-id-or-slug>`     | Download an agent dataset as a .zip archive.                               |
 | `eigenpal agents dataset validate [options] [path]`             | Validate a local dataset directory against the agent input/output schemas. |
 
 ### Experiment
 
-| Command                                                                             | Description                                     |
-| ----------------------------------------------------------------------------------- | ----------------------------------------------- |
-| `eigenpal agents experiment\|exp run [options] <agent-id-or-slug>`                  | Start an experiment over dataset examples.      |
-| `eigenpal agents experiment\|exp status [options] <agent-id-or-slug> <batch-id>`    | Get experiment status.                          |
-| `eigenpal agents experiment\|exp results [options] <agent-id-or-slug> [batch-id]`   | Print experiment results as JSON or CSV.        |
-| `eigenpal agents experiment\|exp list\|ls [options] <agent-id-or-slug>`             | List experiments.                               |
-| `eigenpal agents experiment\|exp compare\|diff [options] <batch-id-a> <batch-id-b>` | Compare two experiment batches.                 |
-| `eigenpal agents experiment\|exp cancel [options] <agent-id-or-slug> <batch-id>`    | Cancel every active execution in an experiment. |
+| Command                                                                             | Description                                      |
+| ----------------------------------------------------------------------------------- | ------------------------------------------------ |
+| `eigenpal agents experiment\|exp run [options] <agent-id-or-slug>`                  | Start an experiment over dataset examples.       |
+| `eigenpal agents experiment\|exp status [options] <agent-id-or-slug> <batch-id>`    | Get experiment status.                           |
+| `eigenpal agents experiment\|exp results [options] <agent-id-or-slug> [batch-id]`   | Print experiment results as JSON or CSV.         |
+| `eigenpal agents experiment\|exp list\|ls [options] <agent-id-or-slug>`             | List experiments.                                |
+| `eigenpal agents experiment\|exp compare\|diff [options] <batch-id-a> <batch-id-b>` | Diff eval scores between two experiment batches. |
+| `eigenpal agents experiment\|exp cancel [options] <agent-id-or-slug> <batch-id>`    | Cancel every active execution in an experiment.  |
 
 ### Session
 
@@ -572,7 +572,7 @@ List dataset examples for an agent.
 
 ### `eigenpal agents dataset push [options] <agent-id-or-slug>`
 
-Upload dataset examples from a local dataset directory.
+Upload dataset examples from a local dataset directory or zip archive.
 
 ### Arguments
 
@@ -586,13 +586,13 @@ Upload dataset examples from a local dataset directory.
 | -------------------------- | -------- | ---------- | ---------------------------------------------------- |
 | `--base-url <url>`         | no       |            | Server base URL                                      |
 | `--json`                   | no       |            | Output the raw server response as JSON               |
-| `--file <path>`            | yes      |            | Dataset directory                                    |
+| `--file <path>`            | yes      |            | Dataset directory or .zip archive                    |
 | `--mode <append\|replace>` | no       | `"append"` | Upload mode                                          |
 | `--yes`                    | no       |            | Confirm replace mode in non-interactive environments |
 
 ### `eigenpal agents dataset pull [options] <agent-id-or-slug>`
 
-Download an agent dataset directory.
+Download an agent dataset as a .zip archive.
 
 ### Arguments
 
@@ -602,10 +602,10 @@ Download an agent dataset directory.
 
 ### Options
 
-| Flag               | Required | Default     | Description      |
-| ------------------ | -------- | ----------- | ---------------- |
-| `--base-url <url>` | no       |             | Server base URL  |
-| `--out <dir>`      | no       | `"dataset"` | Output directory |
+| Flag               | Required | Default     | Description                             |
+| ------------------ | -------- | ----------- | --------------------------------------- |
+| `--base-url <url>` | no       |             | Server base URL                         |
+| `--out <path>`     | no       | `"dataset"` | Output .zip path (default: dataset.zip) |
 
 ### `eigenpal agents dataset validate [options] [path]`
 
@@ -707,7 +707,7 @@ List experiments.
 
 ### `eigenpal agents experiment|exp compare|diff [options] <batch-id-a> <batch-id-b>`
 
-Compare two experiment batches.
+Diff eval scores between two experiment batches.
 
 ### Arguments
 
@@ -718,12 +718,12 @@ Compare two experiment batches.
 
 ### Options
 
-| Flag                         | Required | Default | Description                                                   |
-| ---------------------------- | -------- | ------- | ------------------------------------------------------------- |
-| `--base-url <url>`           | no       |         | Server base URL                                               |
-| `--json`                     | no       |         | Output the raw server response as JSON                        |
-| `--sort <mode>`              | no       |         | Accepted for compatibility; sorting happens client-side later |
-| `--regression-threshold <n>` | no       |         | Accepted for compatibility                                    |
+| Flag                                                   | Required | Default            | Description                                            |
+| ------------------------------------------------------ | -------- | ------------------ | ------------------------------------------------------ |
+| `--base-url <url>`                                     | no       |                    | Server base URL                                        |
+| `--json`                                               | no       |                    | Output the raw server response as JSON                 |
+| `--sort <abs-delta-desc\|delta-asc\|delta-desc\|name>` | no       | `"abs-delta-desc"` | Row sort order (default: biggest movers first)         |
+| `--regression-threshold <n>`                           | no       | `0.05`             | Δ below this is flagged as a regression (default 0.05) |
 
 ### `eigenpal agents experiment|exp cancel [options] <agent-id-or-slug> <batch-id>`
 

package/dist/skill/reference/cli/runs.md

@@ -15,6 +15,7 @@ Inspect, watch, and manage workflow, agent, and eval runs.
   - [`eigenpal runs get [options] <run-id>`](#eigenpal-runs-get-options-run-id)
   - [`eigenpal runs compare|diff [options] <reference-run-id> <run-id>`](#eigenpal-runs-comparediff-options-reference-run-id-run-id)
   - [`eigenpal runs rerun [options] <run-id>`](#eigenpal-runs-rerun-options-run-id)
+  - [`eigenpal runs promote [options] <run-id>`](#eigenpal-runs-promote-options-run-id)
   - [`eigenpal runs trace [options] <run-id>`](#eigenpal-runs-trace-options-run-id)
   - [`eigenpal runs watch [options] <run-id>`](#eigenpal-runs-watch-options-run-id)
   - [`eigenpal runs cancel [options] <run-id>`](#eigenpal-runs-cancel-options-run-id)
@@ -38,6 +39,7 @@ runs
 ├── get <run-id>
 ├── compare|diff <reference-run-id> <run-id>
 ├── rerun <run-id>
+├── promote <run-id>
 ├── artifacts|artifact
 │   ├── list|ls <run-id>
 │   └── fetch <run-id>
@@ -67,6 +69,7 @@ runs
 | `eigenpal runs get [options] <run-id>`                              | Get one run.                                                                                                     |
 | `eigenpal runs compare\|diff [options] <reference-run-id> <run-id>` | Compare one run against another run. PDF/DOCX text comparison uses pdftotext/python3 and reports byte fallbacks. |
 | `eigenpal runs rerun [options] <run-id>`                            | Create a new run from a previous run's stored input snapshot.                                                    |
+| `eigenpal runs promote [options] <run-id>`                          | Promote a run into a dataset example on the run's automation.                                                    |
 | `eigenpal runs trace [options] <run-id>`                            | Print raw trace.jsonl for a run, or write it with --out.                                                         |
 | `eigenpal runs watch [options] <run-id>`                            | Watch a run until it reaches a terminal status.                                                                  |
 | `eigenpal runs cancel [options] <run-id>`                           | Cancel a run.                                                                                                    |
@@ -198,6 +201,24 @@ Create a new run from a previous run's stored input snapshot.
 | `--interval <seconds>` | no       | `2`     | Polling interval in seconds                                                                                       |
 | `--max-wait <seconds>` | no       | `1800`  | Maximum wait before exiting 2                                                                                     |
 
+### `eigenpal runs promote [options] <run-id>`
+
+Promote a run into a dataset example on the run's automation.
+
+### Arguments
+
+| Name     | Required | Variadic | Description |
+| -------- | -------- | -------- | ----------- |
+| `run-id` | yes      | no       |             |
+
+### Options
+
+| Flag               | Required | Default | Description                            |
+| ------------------ | -------- | ------- | -------------------------------------- |
+| `--base-url <url>` | no       |         | Server base URL                        |
+| `--json`           | no       |         | Output the raw server response as JSON |
+| `--name <name>`    | no       |         | Name for the created example           |
+
 ### `eigenpal runs trace [options] <run-id>`
 
 Print raw trace.jsonl for a run, or write it with --out.

package/dist/skill/reference/cli/surface.md

@@ -108,6 +108,7 @@ eigenpal
 │   ├── get <run-id>
 │   ├── compare|diff <reference-run-id> <run-id>
 │   ├── rerun <run-id>
+│   ├── promote <run-id>
 │   ├── artifacts|artifact
 │   │   ├── list|ls <run-id>
 │   │   └── fetch <run-id>
@@ -125,8 +126,6 @@ eigenpal
 │   │   └── delete <run-id> <name>
 │   ├── watch <run-id>
 │   └── cancel <run-id>
-├── git [gitArgs...]
-├── completion <shell>
 └── skill
     ├── install
     ├── uninstall [toolIds...]

package/dist/skill/reference/cli/workflow.md

@@ -96,14 +96,14 @@ workflow
 
 ### Core
 
-| Command                                                 | Description                                                                                                                                                                                                                                                                   |
-| ------------------------------------------------------- | ----------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
-| `eigenpal workflow list\|ls [options]`                  | List workflows the caller can read.                                                                                                                                                                                                                                           |
-| `eigenpal workflow pull [options] <workflow-id>`        | Download the YAML definition of the workflow at its current version.                                                                                                                                                                                                          |
-| `eigenpal workflow push [options]`                      | Create or update a workflow from a YAML file.                                                                                                                                                                                                                                 |
-| `eigenpal workflow move [options] <workflow-id>`        | Move a workflow to a folder path, creating folders as needed                                                                                                                                                                                                                  |
-| `eigenpal workflow validate [options] [path]`           | Local-only validation. Without [path]: runs the templated three-way check (./workflow.yaml + ./evaluators.yaml + ./dataset/). With [path] pointing at a YAML file: validates just that workflow.yaml. For per-noun targeting use `evaluators validate` or `dataset validate`. |
-| `eigenpal workflow clear-local [options] [examples...]` | Delete local execution artifacts under ./dataset/examples/. Keeps the latest run per example by default.                                                                                                                                                                      |
+| Command                                                 | Description                                                                                                                                                                                                                                                              |
+| ------------------------------------------------------- | ------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------ |
+| `eigenpal workflow list\|ls [options]`                  | List workflows the caller can read.                                                                                                                                                                                                                                      |
+| `eigenpal workflow pull [options] <workflow-id>`        | Download the YAML definition of the workflow at its current version.                                                                                                                                                                                                     |
+| `eigenpal workflow push [options]`                      | Create or update a workflow from a YAML file.                                                                                                                                                                                                                            |
+| `eigenpal workflow move [options] <workflow-id>`        | Move a workflow to a folder path, creating folders as needed                                                                                                                                                                                                             |
+| `eigenpal workflow validate [options] [path]`           | Local-only validation. Without [path]: runs the templated three-way check (./workflow.yaml + ./evaluators.yaml + ./dataset/). With [path] pointing at a YAML file: validates that workflow.yaml. For per-noun targeting use `evaluators validate` or `dataset validate`. |
+| `eigenpal workflow clear-local [options] [examples...]` | Delete local execution artifacts under ./dataset/examples/. Keeps the latest run per example by default.                                                                                                                                                                 |
 
 ### Evaluators
 
@@ -233,7 +233,7 @@ Move a workflow to a folder path, creating folders as needed
 
 ### `eigenpal workflow validate [options] [path]`
 
-Local-only validation. Without [path]: runs the templated three-way check (./workflow.yaml + ./evaluators.yaml + ./dataset/). With [path] pointing at a YAML file: validates just that workflow.yaml. For per-noun targeting use `evaluators validate` or `dataset validate`.
+Local-only validation. Without [path]: runs the templated three-way check (./workflow.yaml + ./evaluators.yaml + ./dataset/). With [path] pointing at a YAML file: validates that workflow.yaml. For per-noun targeting use `evaluators validate` or `dataset validate`.
 
 ### Arguments
 
@@ -601,7 +601,7 @@ Poll until terminal, then auto-pull results — replaces `status --watch` + `res
 | `--max-wait <seconds>`      | no       | `1800`   | Hard ceiling in seconds (default 1800 = 30 min)                         |
 | `--pull-on-complete <path>` | no       |          | Destination for the results file. Default: ./results-<batchId>.<format> |
 | `--format <csv\|json>`      | no       | `"json"` | Results export format (default json)                                    |
-| `--no-pull`                 | no       |          | Skip auto-pulling results on terminal (just watch)                      |
+| `--no-pull`                 | no       |          | Skip auto-pulling results on terminal (watch only)                      |
 | `--base-url <url>`          | no       |          | Server base URL                                                         |
 
 ### `eigenpal workflow versions list|ls [options] <workflow-id>`

package/dist/skill/reference/dataset-format.md

@@ -54,8 +54,8 @@ example.
 
 - **Folder names** (example names, argument names, expected document
   keys) must match `[a-z0-9][a-z0-9-_]*`.
-- **`input/arguments.json`** is REQUIRED for every example, even if it's
-  just `{}`. It must be a JSON object (not array, not literal).
+- **`input/arguments.json`** is REQUIRED for every example, even if it is
+  `{}`. It must be a JSON object (not array, not literal).
 - **File-arguments** live in `input/<arg-name>/<filename>`. The
   materialized shape on `triggerInput` is **driven by the workflow YAML's
   `inputs[].type`**, not by the file count:
@@ -201,7 +201,7 @@ The two files are mutually exclusive for the same example (an example
 is either a success-case or a failure-case, never both). The `exact-diff`
 evaluator branches on the envelope shape and reports a clean
 `expectedFailureButSucceeded` or `actualWasUntypedError` reason when
-the actual run doesn't match the expectation.
+the actual run does not match the expectation.
 
 ## Validate before pushing
 
@@ -238,7 +238,7 @@ includes `{ created, expectedSet, … }`:
 
 ## Editing a dataset on the server
 
-To inspect or round-trip what's currently on the server:
+To inspect or round-trip what is currently on the server:
 
 ```bash
 eigenpal workflow dataset list <workflow-id>
@@ -278,7 +278,7 @@ eigenpal workflow dataset example update <workflow-id> <example-id> \
   --expected-file /tmp/correct.json
 ```
 
-`--expected-file -` reads JSON from stdin if you'd rather pipe. Pass
+`--expected-file -` reads JSON from stdin if you would rather pipe. Pass
 empty string to clear an annotation: `--annotation ""`.
 
 ### Add one new example
@@ -292,7 +292,7 @@ eigenpal workflow dataset example create <workflow-id> \
 ```
 
 `--input-json` / `--expected-json` accept inline JSON literals; the
-`-file` variants read from disk (or `-` for stdin). They're mutually
+`-file` variants read from disk (or `-` for stdin). They are mutually
 exclusive — pass one or the other, not both.
 
 File-arg uploads still go through `dataset push`; CRUD only handles

package/dist/skill/reference/debugging.md

@@ -54,7 +54,7 @@ The grouped run payload includes:
     substitution. Lets you see what the LLM actually got, what URL
     HTTP actually hit, what items the script actually saw. Populated
     for `ai.*` / `transform.*` / `action.*`. Null for `control.*`
-    (orchestration steps don't have a meaningful resolved config).
+    (orchestration steps do not have a meaningful resolved config).
   - `output` — what the step returned
   - `error` — error message + code when `status: 'failed'`
   - `durationMs`
@@ -108,7 +108,7 @@ no network or filesystem, so most timeouts are infinite-loop bugs.
 
 ### `step_type_unknown`
 
-`workflow.yaml` references a `type:` that the deployment doesn't know
+`workflow.yaml` references a `type:` that the deployment does not know
 about. Common after a typo or a step type that was renamed.
 
 ```bash
@@ -219,7 +219,7 @@ broken. If you see:
   Set EIGENPAL_BASE_URL or pass --base-url <url>.
 ```
 
-That's a **connection** error — the URL is wrong, the server is down,
+That is a **connection** error — the URL is wrong, the server is down,
 or your network is blocked. The URL the CLI tried is echoed back so a
 stale `EIGENPAL_BASE_URL` is immediately obvious.
 
@@ -230,13 +230,13 @@ If instead you see:
   Run `eigenpal auth login`, or set EIGENPAL_API_KEY in your env.
 ```
 
-That's an **auth** error — the URL works but your key is missing /
+That is an **auth** error — the URL works but your key is missing /
 expired / scoped to the wrong tenant. Run `auth list` to see configured
 profiles, or `auth use <name>` to switch.
 
 ## 8. Override a flaky step in eval mode
 
-If a step calls an external system that's unreliable (an external API, a
+If a step calls an external system that is unreliable (an external API, a
 private API, a rate-limited connector), short-circuit it for evals via
 the example's `meta.json`:
 

package/dist/skill/reference/evaluators.md

@@ -106,7 +106,7 @@ paths; you do not need a separate evaluator for failure cases.
       Pick the label that best matches the tone of the response.
 ```
 
-`promptExtension` is the only required field — it's appended to the harness
+`promptExtension` is the only required field — it is appended to the harness
 prompt and tells the judge what "good" looks like for this workflow. The
 harness handles JSON parsing, retries, and feeds the judge `actual`,
 `expected`, and example metadata. In `discrete` mode the judge MUST return
@@ -140,7 +140,7 @@ verbatim, same text the dashboard editor shows. The `: number` return-type annot
 enforced at parse time. The dashboard seeds new evaluators with a
 `WorkflowOutput` type alias derived from the workflow's `output:`
 declaration, plus `Expected` / `Actual` aliases for compatibility. Plain
-`unknown` works too if you don't want a typed signature.
+`unknown` works too if you do not want a typed signature.
 
 The signature shape is **locked**:
 
@@ -151,7 +151,7 @@ The signature shape is **locked**:
   and scored as 0).
 
 `workflow validate` and `workflow evaluators validate` flag YAML where
-the function fails to parse, the signature doesn't match, or the body
+the function fails to parse, the signature does not match, or the body
 contains neither `return` nor `throw` — so a hand-edited config errors
 before it reaches the worker.
 
@@ -224,7 +224,7 @@ eigenpal workflow experiment results <workflow-id> <batch-id> \
   --format csv --out results.csv
 ```
 
-The signed-URL pattern means large result sets don't go through the CLI
+The signed-URL pattern means large result sets do not go through the CLI
 process — `--out` writes the file directly from the server's storage.
 
 ## Stabilizing flaky judges
@@ -264,9 +264,9 @@ _Generated from `EvalConfigYamlSchema` in `@eigenpal/types/src/eval/evaluator-co
 | Field | Type | Required | Default | Description |
 | --- | --- | --- | --- | --- |
 | `numericTolerance` | number | no | `0.000001` | Maximum absolute difference between numeric values that still counts as equal. Use 1e-6 for floats, 0 for exact integer match. |
-| `allowExtraFields` | boolean | no | `true` | When on, extra fields in the actual output don't fail the diff. Off = actual must match expected exactly. |
+| `allowExtraFields` | boolean | no | `true` | When on, extra fields in the actual output do not fail the diff. Off = actual must match expected exactly. |
 | `passThreshold` | number | no | `1` | Minimum diff score this evaluator must reach for a run to pass. 1.0 = perfect match required. |
-| `paths` | array<string> | no |  | Dot-paths to scope the diff to a subset of the expected tree. Empty = diff entire expected. Syntax: `header.id`, `lineItems[].total`, `lineItems[0].sku`. Use this when expected has noisy sections you don't want to score. |
+| `paths` | array<string> | no |  | Dot-paths to scope the diff to a subset of the expected tree. Empty = diff entire expected. Syntax: `header.id`, `lineItems[].total`, `lineItems[0].sku`. Use this when expected has noisy sections you do not want to score. |
 
 
 ### `llm-judge` — LLM-as-judge scoring
@@ -286,7 +286,7 @@ _Generated from `EvalConfigYamlSchema` in `@eigenpal/types/src/eval/evaluator-co
 | Field | Type | Required | Default | Description |
 | --- | --- | --- | --- | --- |
 | `function` | string | yes |  | Full TypeScript source for optional `type` aliases plus `function scoreScript(expected, actual): number { ... }`. Receives `expected` (the example's expected output) and `actual` (the workflow's actual output), returns a number in [0, 1] (the `: number` annotation is required). The `: number` return-type annotation is required and enforced at parse time. Throws are caught and scored as 0. |
-| `timeoutMs` | integer | no | `5000` | Maximum wall-clock time the script can run before it's killed and the run is marked failed. |
+| `timeoutMs` | integer | no | `5000` | Maximum wall-clock time the script can run before it is killed and the run is marked failed. |
 | `memoryLimitMb` | integer | no | `10` | Maximum memory the sandbox may allocate. Increase if the script processes large arrays or strings. |
 | `passThreshold` | number | no | `1` | Minimum script score this evaluator must reach for a run to pass. |
 <!-- GENERATED:EVALUATOR_CATALOG END -->

package/dist/skill/reference/step-exec.md

@@ -7,7 +7,7 @@
 > retries, no tracing, no credit metering, no tenant-default LLM, no
 > strict-mode response_format) and assumed shell env state
 > (`WORKER_LLM_*`) that real CLI users — who authenticate via
-> `EIGENPAL_API_KEY` — don't have.
+> `EIGENPAL_API_KEY` — do not have.
 >
 > Calling `eigenpal workflow step exec <type>` today exits 2 with a
 > redirect message. The server-side replacement is tracked in EIG-104:
@@ -30,7 +30,7 @@ eigenpal workflow experiment status <workflow-id> <batchId> --watch
 ```
 
 For `--example-id`, the human slug works too (`ex-01-koifer-97zf`),
-not just the `evx_…` id — added as part of the same iteration.
+not the `evx_…` id — added as part of the same iteration.
 
 To inspect what a step actually produced (input / output / resolved
 config), use:

package/dist/skill/reference/step-types.md

@@ -1,7 +1,7 @@
 # Step types
 
 The catalog is generated from `STEP_SCHEMAS` in
-`@eigenpal/types/src/workflow/step-configs.ts`. **Don't memorize fields
+`@eigenpal/types/src/workflow/step-configs.ts`. **Do not memorize fields
 — introspect.** The CLI reads the live schema:
 
 ```bash
@@ -106,7 +106,7 @@ Reference user-supplied schema fields the same way:
 
 `control.parallel`, `control.parallel_map`, `control.foreach`, `control.if`,
 and `control.block` contain nested steps. The auto-generated catalog below
-can't render that shape, so the YAML form lives here. Same for the scoping
+cannot render that shape, so the YAML form lives here. Same for the scoping
 rules — important because the runtime treats nested steps differently from
 top-level ones, and getting the access path wrong silently returns
 `undefined` (no error).
@@ -114,7 +114,7 @@ top-level ones, and getting the access path wrong silently returns
 ### `control.parallel` — independent branches
 
 Runs each branch concurrently. Use when several pieces of work share input
-but don't depend on each other.
+but do not depend on each other.
 
 ```yaml
 - name: enrich
@@ -242,7 +242,7 @@ to preserve intermediate outputs).
 
 > ⚠️ Foreach does NOT isolate scopes — the last iteration's inner step
 > outputs technically persist on the top-level `steps` map and `steps.<inner>.output.x`
-> resolves at runtime. That's an only-the-last-row footgun; the autocomplete
+> resolves at runtime. That is an only-the-last-row hazard; the autocomplete
 > hides these names and you should treat `steps.<foreach>.output.items[]`
 > as the only correct access.
 
@@ -304,7 +304,7 @@ not visible — the block runs in an isolated scope.
 `ai.classify` + `control.fail` together let a workflow reject bad inputs
 fast with a typed HTTP-style status code that callers (and evals) can
 match against. The classifier picks one label from a closed set; the
-fail step terminates the run when the label is one you don't want to
+fail step terminates the run when the label is one you do not want to
 process.
 
 ```yaml

package/dist/skill/reference/workflow-yaml.md

@@ -326,7 +326,7 @@ same per-page representation.
 Description-writing tips (mirrors Reducto's guidance):
 
 - Use the document's own terminology — a Slovak contract calls it `Príloha`,
-  not "annex". List the multilingual variants you've seen.
+  not "annex". List the multilingual variants you have seen.
 - Mention stable visual cues if any — a centered title-page header, a
   signature line, the start of a specific table.
 - Be specific. "The collateral schedule table at the start of Príloha 2"
@@ -442,11 +442,11 @@ eigenpal workflow push --file workflow.yaml --workflow-id wf_… --bump patch
 `--bump` requires `--workflow-id` (it bumps from the current server
 version). `--set-version` works with or without `--workflow-id`. The
 YAML's top-level `version:` field is the fallback when neither flag is
-passed — server rejects pushes whose version doesn't strictly increase.
+passed — server rejects pushes whose version does not strictly increase.
 
 ## Discover step + evaluator types
 
-Don't memorize fields — introspect:
+Do not memorize fields — introspect:
 
 ```bash
 eigenpal workflow step-type      list                 # full step catalog
@@ -456,7 +456,7 @@ eigenpal workflow evaluator-type get <type>           # config schema for one ev
 ```
 
 Both catalogs are generated from the canonical Zod schemas in
-`@eigenpal/types`, so they're always in sync with what the deployment
+`@eigenpal/types`, so they are always in sync with what the deployment
 supports.
 
 <!-- GENERATED:WORKFLOW_REFERENCE START -->

package/dist/templates/blank/README.md

@@ -15,7 +15,7 @@ Add more examples under `dataset/examples/<name>/`. Each example needs an
 `input/arguments.json`; `expected/output.json` and `meta.json` are optional.
 File arguments live in `input/<arg-name>/<filename>`.
 
-When you're ready to push this workflow to the server:
+When you are ready to push this workflow to the server:
 
 ```bash
 eigenpal workflow push --file workflow.yaml

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "@eigenpal/cli",
-  "version": "0.7.2",
+  "version": "0.8.0",
   "description": "Eigenpal CLI — author and run document workflows from your terminal. Agent-ready.",
   "keywords": [
     "eigenpal",

package/dist/skill/reference/cli/completion.md

@@ -1,9 +0,0 @@
-# eigenpal completion
-
-Print a shell completion script to stdout (supported shells: bash, zsh, fish). Pipe into the appropriate completion file for your shell — see the script header for install instructions.
-
-### Arguments
-
-| Name    | Required | Variadic | Description |
-| ------- | -------- | -------- | ----------- |
-| `shell` | yes      | no       |             |

package/dist/skill/reference/cli/git.md

@@ -1,9 +0,0 @@
-# eigenpal git
-
-Passthrough to git with organization remote auth and committer identity.
-
-### Arguments
-
-| Name      | Required | Variadic | Description            |
-| --------- | -------- | -------- | ---------------------- |
-| `gitArgs` | no       | yes      | Git arguments after -- |