@actionway/cli 0.13.17 → 0.15.0

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "@actionway/cli",
-  "version": "0.13.17",
+  "version": "0.15.0",
   "description": "Actionway CLI for local coding agents.",
   "type": "module",
   "homepage": "https://actionway.ai/onboarding",

package/skills/actionway/SKILL.md

@@ -1,6 +1,7 @@
 ---
 name: actionway
 description: Use the local Actionway CLI for supported image, video, audio, transcription, search, analysis, and media-processing work. Trigger when a task may be completed with an installed `actionway` command, when an Actionway asynchronous `job_ref` must be completed, or when the user asks to use Actionway capabilities from a local Agent.
+version: 0.0.0-dev
 ---
 
 # Actionway
@@ -11,10 +12,11 @@ Use the installed `actionway` CLI as the capability source of truth. Do not memo
 
 1. Run Actionway commands with network and OS credential-store access. If a sandboxed command returns `E_CREDENTIAL_STORE_UNAVAILABLE`, rerun that same command with host permission. Do not start login again.
 2. If the user supplied an existing pending `job_ref`, skip updating and run `actionway wait --job-ref=<uuid>`.
-3. Otherwise, once per Agent session, run `actionway update --check`. The CLI caches this registry check for 24 hours. If the check fails, continue with the installed CLI and do not block the user's task. If `update_available` is true, run `actionway update`, then use the new CLI starting with the next command.
-4. Run `actionway whoami`. On `E_NOT_AUTHENTICATED`, run `actionway init --agent=codex` from Codex or `actionway init --agent=claude` from Claude. Tell the user only to approve access in the browser. Never ask them to paste credentials into chat.
-5. Run `actionway --help` to find an appropriate capability. Before first use, inspect `actionway <command> --help` and, when offered, `actionway <command> --print-schema`.
-6. Validate required local files. If the request is complete, execute it directly; ask only for genuinely missing task inputs.
+3. Otherwise, once per Agent session, run `actionway update --check`. The CLI caches this check for 24 hours and routine command responses keep the cache warm. If the check fails, continue with the installed CLI and do not block the user's task. If `update_available` is true, run `actionway update`, then use the new CLI starting with the next command and refresh this skill as described in step 4.
+4. Keep this skill in sync with the CLI. Every successful `actionway` command output carries `cli_version` and `skill_source`. If this skill's frontmatter `version` differs from `cli_version`, reinstall this skill: copy the skill from the local `skill_source` path into your agent's skill directory, replacing the previous copy, and tell the user once that the updated instructions apply from the next session. Then continue the current task. Also read any `notes` entries in command outputs — they carry update prompts, including when the installed CLI is below the minimum supported version and must be updated before continuing.
+5. Run `actionway whoami`. On `E_NOT_AUTHENTICATED`, run `actionway init`. Tell the user only to approve access in the browser. Never ask them to paste credentials into chat. After init, install the skill from the `skill.source` path in its output into your agent's skill directory if it is not installed yet.
+6. Run `actionway --help` to find an appropriate capability. Before first use, inspect `actionway <command> --help` and, when offered, `actionway <command> --print-schema`.
+7. Validate required local files. If the request is complete, execute it directly; ask only for genuinely missing task inputs.
 
 ## Execute