soft-skills 2.1.15 → 2.1.16

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "soft-skills",
-  "version": "2.1.15",
+  "version": "2.1.16",
   "description": "Communication toolkit for burnt-out humans and collaborative AI's",
   "author": "Gilad Barnea (https://github.com/giladbarnea)",
   "homepage": "https://github.com/giladbarnea/soft-skills",

package/plugins/soft-skills/.claude-plugin/plugin.json

@@ -1,6 +1,6 @@
 {
   "name": "soft-skills",
-  "version": "2.1.15",
+  "version": "2.1.16",
   "description": "Communication toolkit for burnt-out humans and collaborative AI's",
   "author": {
     "name": "Gilad Barnea",

package/plugins/soft-skills/.codex-plugin/plugin.json

@@ -1,6 +1,6 @@
 {
   "name": "soft-skills",
-  "version": "2.1.15",
+  "version": "2.1.16",
   "description": "Communication toolkit for burnt-out humans and collaborative AI's",
   "author": {
     "name": "Gilad Barnea",

package/plugins/soft-skills/skills/ai-to-delegated/planning/when-to-delegate.md

@@ -52,11 +52,11 @@ Logically, if the task is not large or complex, do not delegate. The delegation
 
 > This is not an exhaustive list. Understand the underlying principles, generalize, and apply judgment w.r.t. your actual task.
 
-These are example implementations of the different, justified types of delegation, as described earlier in this file.
+These are justified reasons to delegate. Each reason fits one of the shapes described earlier in this file, or any of them.
 
-- **Dirty work**: The main agent needs the result of a process, not the process itself. Examples include mapping unknown terrain to identify where to dive deeper; finding where things are or whether they exist at all; conducting research; summarizing topics the delegating agent does not need to understand deeply; implementing a well-defined spec; and so on. These tasks require the executor to consume substantial irrelevant context because the space has not yet been mapped by relevance, creating a fog-of-war situation. Someone has to burn through context and deal with the noise. It is better to assign this work to a throwaway agent and keep the main agent’s context high signal-to-noise. Moreover, due to the read-only nature of these tasks, they can potentially be fanned out and run in parallel.
+- **Dirty work**: The main agent needs the result of a process, not the process itself. Examples include mapping unknown terrain to identify where to dive deeper; finding where things are or whether they exist at all; conducting research; summarizing topics the delegating agent does not need to understand deeply; implementing a well-defined spec; and so on. These tasks require the executor to consume substantial irrelevant context because the space has not yet been mapped by relevance, creating a fog-of-war situation. Someone has to burn through context and deal with the noise. It is better to assign this work to a throwaway agent and keep the main agent’s context high signal-to-noise. Moreover, when these tasks are independent of each other, they can be fanned out and run in parallel.
 - **Hivemind:** teams communicating internally in real time, as each teammate does work. Hollywood analogy: elite soldier squad or a team of spies, global channel earpieces, deployed behind enemy lines, each progresses their part, each part essential for completing the mission, global channel earpieces, consistent live updates, uncertainties surfaced to get advice, discussions to make best decisions for mission, path forward of an individual adapts in real time due to new peer finding, HQ available for teammates to surface rare issues that only HQ can or should handle.
 - **De-bias:** A reviewer with a fresh context (either paired with the worker in a live team, or dispatched after the fact), informed only of the intent which birthed the work, can spot blind spots and flaws that the worker could not. Related: sometimes a hypothesis is considered true only after it is confirmed independently by multiple actors (consensus).
-- **Get more done with less time**: horizontally & more of the same. Readonly tasks are often a strong candidate to fan out as such.
-- **Multiple experts over jack(s) of all trades**: horizontally & orthogonal domains.
-- **Big picture, smaller picture**: vertical responsibility layers. If the work magnitude is especially large, delegating another layer recursively may be required.
+- **Too much for one agent**: the work volume is so large that one agent cannot fit it in its context window, or its results degrade (very bloated window). Splitting the work loses some understanding between agents, and here that loss costs less than the degradation. Cut the work into slices of the same kind. A bonus: the slices run in parallel, so the work also finishes sooner. Shape: horizontally & more of the same.
+- **Multiple experts over jack(s) of all trades**: the work spans several cognitive worlds. Give each world its own agent, so each context window stays cohesive. Shape: horizontally & orthogonal domains.
+- **Big picture, smaller picture**: the work has both a wide, shallow level and a narrow, deep level of the same thing. Where multiple experts split the work side by side, this splits it top to bottom: give each level its own agent, stacked one above the other. Shape: vertical responsibility layers. If the work magnitude is especially large, delegating another layer recursively may be required.