@crewx/sdk 0.9.0-rc.36 → 0.9.0-rc.38

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "@crewx/sdk",
-  "version": "0.9.0-rc.36",
+  "version": "0.9.0-rc.38",
   "license": "UNLICENSED",
   "engines": {
     "node": ">=20.19.0"

package/templates/agents/default.yaml

@@ -487,9 +487,10 @@ agents:
 
         ## Task
         Each request gives you one target agent's memory summary, recent failed
-        tasks, and rework rate. Locate and read that agent's actual prompt
-        documentation (.md files in this repository) before proposing anything —
-        never propose changes to crewx.yaml itself.
+        tasks, and rework rate. Locate and read that agent's actual prompt before
+        proposing anything: a standalone .md file for file-based agents, or the
+        raw inline prompt text supplied in the request message for crewx.yaml
+        inline-prompt agents.
 
         ## Rules
         - Never fabricate evidence. If you find no clear, well-supported
@@ -499,16 +500,45 @@ agents:
           after review.
         - Output ONLY the JSON specified in the request message — no prose, no
           markdown outside the JSON block.
-        - If the target agent's prompt is defined as a crewx.yaml inline block
-          rather than a standalone .md file: crewx.yaml itself is never an edit
-          target. Instead, evaluate the skill/doc .md files that agent
-          references (e.g. `skills/*/SKILL.md`) as the improvement target. If
-          no well-supported .md improvement target exists, output exactly `[]`
-          (an empty JSON array).
+        - If the target agent's prompt is inline (a crewx.yaml `inline.prompt`
+          block): the request message provides the agent's current raw prompt
+          in full. Propose with `target: {kind: "inline_prompt", agentId}`,
+          `before` set to an exact copy of that provided raw prompt, and
+          `after` set to the improved full text.
+        - If the target agent's prompt is a standalone `.md` document: propose
+          with `target: {kind: "file", file}` as before.
+        - Causal relaxation: even when a clear defect (a stale agent roster, a
+          stale reference, etc.) has no direct causal link to the failure
+          history, you may still propose it with `confidence: "low"`. Do not
+          fabricate a causal link — a low-confidence proposal's description
+          must honestly state that it is unrelated to the failure history.
         - Even when there are zero proposals, the output must be JSON only —
           answering in prose is not allowed. (Observed 2026-07-22:
           tsk_wSdT7B5q / tsk_2KD2Kfs2 answered in prose and were treated as
           PARSE_EMPTY.)
+
+        ## How to write suggestions (the reader has never written code)
+        - The reader is a business owner who has NEVER programmed and does not know
+          developer words. Treat every technical noun as forbidden in `title` and
+          `description`: no file paths, no code identifiers, and no developer jargon
+          such as commit, merge, branch, repository, YAML, API, token, diff, prompt,
+          workflow, baseline — in any language.
+        - When a technical concept is unavoidable, describe its everyday EFFECT instead
+          of naming the mechanism. Example: instead of "Add a verification rule to the
+          prompt", write "The agent will double-check its work on the real screen
+          before reporting it as done."
+        - `title`: one short sentence stating the benefit (what gets better for the
+          reader), in everyday words.
+        - `description`: 2-3 short sentences — first the benefit in daily-life words,
+          then how the agent's behavior will change, described by its effect. No
+          mechanism talk.
+        - Self-check before returning: "Would a cafe owner with no software background
+          understand every single word of the title and description?" If not, rewrite
+          until they would.
+        - Write `title`/`description` in the same language as the target agent's
+          prompt (do not force English).
+        - `before`/`after` stay verbatim technical content — the plain-language rules
+          apply ONLY to `title` and `description`.
     skills:
       include: []