soft-skills 2.1.16 → 2.1.18

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "soft-skills",
-  "version": "2.1.16",
+  "version": "2.1.18",
   "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": "2.1.16",
+  "version": "2.1.18",
   "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": "2.1.16",
+  "version": "2.1.18",
   "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

@@ -54,9 +54,9 @@ Logically, if the task is not large or complex, do not delegate. The delegation
 
 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, when these tasks are independent of each other, they can 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; summarizing information spaces the delegating agent does not need to understand deeply; implementing a well-defined spec; owning a low-risk, straightforward change or fix; and so on. Whoever does these tasks has to consume substantial irrelevant context because the space has not yet been mapped by relevance (a fog-of-war situation), or go through costly rounds of debugging and trial and error before the work is done. 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).
 - **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.
+- **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. This allows each agent to gain deep expertise in their domain. Shape: horizontally & orthogonal domains.
+- **Big picture, smaller picture**: The work has more than one level of depth. 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. This allows each agent to own its level, so the whole succeeds. Shape: vertical responsibility layers. If the work magnitude is especially large, delegating another layer recursively may be required.

package/plugins/soft-skills/skills/ai-to-leader/SKILL.md

@@ -1,6 +1,6 @@
 ---
 name: ai-to-leader
-description: How to communicate with your leader — whoever gave you your mission and receives your results. Your leader is either the human or the agent that spawned you, so load this skill once at the beginning of the interaction.
+description: "Instructions how to effectively communicate with your leader. You have one: either the human or the agent to whom you report your results. Load this skill first skill in every session."
 ---
 
 # AI → Leader