@laitszkin/apollo-toolkit 3.11.6 → 3.11.7

package/AGENTS.md

@@ -38,6 +38,7 @@ This repository enables users to install and run a curated set of reusable agent
 - Users can run a shared submission-readiness pass that synchronizes changelog, project docs, `AGENTS.md`, and completed plan archives before commit, push, PR creation, or release.
 - Users can learn new or improved skills from recent Codex conversation history.
 - Users can audit and maintain the skill catalog itself, including dependency classification and shared-skill extraction decisions.
+- Users can optimize existing agent skills by deriving the intended deliverable, tightening acceptance criteria, and rewriting `SKILL.md` into a leaner structure backed by extracted references.
 - Users can implement approved spec planning sets directly in the current checkout and commit them to the active branch.
 - Users can implement approved spec planning sets inside isolated git worktrees and keep the parent checkout clean.
 - Users can coordinate approved multi-spec implementation batches by assigning each spec directory to an independent worktree-backed subagent with bounded concurrency.

package/CHANGELOG.md

@@ -10,6 +10,18 @@ All notable changes to this repository are documented in this file.
 
 ### Fixed
 
+## [v3.11.7] - 2026-05-12
+
+### Added
+
+- Add `optimise-skill`, a new catalog skill that reads a target skill and its supporting files, derives the intended deliverable and acceptance criteria, and rewrites the skill into a tighter `goal / acceptance criteria / workflow / examples / references` structure for higher-signal agent execution.
+
+### Changed
+
+- Catalog docs now include `optimise-skill`, and its bundled example reference path is normalized to match the shipped file name.
+
+### Fixed
+
 ## [v3.11.6] - 2026-05-12
 
 ### Added

package/README.md

@@ -41,6 +41,7 @@ A curated skill catalog for Codex, OpenClaw, Trae, Agents, and Claude Code with
 - open-source-pr-workflow
 - openai-text-to-image-storyboard
 - openclaw-configuration
+- optimise-skill
 - recover-missing-plan
 - record-spending
 - resolve-review-comments

package/optimise-skill/SKILL.md

@@ -0,0 +1,35 @@
+---
+name: optimise-skill
+description: Use prompt engineering to optimise agent skill. Use it when you need to optimise a `SKILL.md`
+---
+
+## 目標
+在不影響被優化技能整體流程前提下，利用提示詞工程，對技能進行優化，減少冗余表達，增強agent對技能的理解能力以及實際工作中的使用效率。
+
+## 驗收條件
+- 被優化技能的最終交付產物不受影響
+- 被優化技能有顯著冗余削減，且具備精確提示能力，盡最大可能釋放LLM的性能
+
+## 工作流程
+
+1. 識別交付物
+完整閱讀整個技能的`SKILL.md`文檔，以及其引用的所有額檔案，包括但不限於`references/`, `scripts/`。基於獲取到的技能上下文資訊，總結出該技能的最終交付產物。
+
+2. 制定驗收條件
+制定驗收條件，從而確保LLM能夠穩定、可復現地按照驗收條件產出符合要求高質量最終交付物
+
+3. 重寫技能
+將整個技能的`SKILL.md`重寫。重寫後的技能應該只包含以下幾個關鍵組成部分：
+- 技能目標
+- 技能驗收條件
+- 技能工作流程
+- 技能使用範例
+- 技能參考資料索引
+對於技能有幫助的內但不符合上述技能架構規範，則應該被分類放置在`references/`下的markdown檔案。
+
+## 範例
+- "一個專注在提示LLM agent進行自我迭代，並為代碼庫帶來性能優化的技能需要被優化"-> "定義驗收條件為優化後性能相較優化前至少提升X個百分比，並且項目之中不存在任何O(n^2)級別時間複雜度的函式和邏輯，並按照標準架構重寫技能。"
+- "一個有大量前端開發範例被包含在`SKILL.md`之中的前端開發技能需要被優化" -> "定義驗收條件為前端頁面`reference`之中提供的大量建議範例重寫且不包含任何建議示例之中明確拒絕的設計，然後按照技能優化流程對技能進行全面的重寫。"
+
+## 參考資料
+- `references/example_skill.md` - 優化後的技能範例

package/optimise-skill/agents/openai.yaml

@@ -0,0 +1,4 @@
+interface:
+  display_name: "Optimise Skill"
+  short_description: "Rewrite a SKILL.md into a leaner, higher-signal prompt"
+  default_prompt: "Use $optimise-skill to read the target skill and its supporting files, derive the intended deliverable plus acceptance criteria, then rewrite the skill into a tighter goal / acceptance criteria / workflow / examples / references structure without changing the final outcome."

package/optimise-skill/references/example_skill.md

@@ -0,0 +1,35 @@
+---
+name: optimise-skill
+description: Use prompt engineering to optimise agent skill. Use it when you need to optimise a `SKILL.md`
+---
+
+## 目標
+在不影響被優化技能整體流程前提下，利用提示詞工程，對技能進行優化，減少冗余表達，增強agent對技能的理解能力以及實際工作中的使用效率。
+
+## 驗收條件
+- 被優化技能的最終交付產物不受影響
+- 被優化技能有顯著冗余削減，且具備精確提示能力，盡最大可能釋放LLM的性能
+
+## 工作流程
+
+1. 識別交付物
+完整閱讀整個技能的`SKILL.md`文檔，以及其引用的所有額檔案，包括但不限於`references/`, `scripts/`。基於獲取到的技能上下文資訊，總結出該技能的最終交付產物。
+
+2. 制定驗收條件
+制定驗收條件，從而確保LLM能夠穩定、可復現地按照驗收條件產出符合要求高質量最終交付物
+
+3. 重寫技能
+將整個技能的`SKILL.md`重寫。重寫後的技能應該只包含以下幾個關鍵組成部分：
+- 技能目標
+- 技能驗收條件
+- 技能工作流程
+- 技能使用範例
+- 技能參考資料索引
+對於技能有幫助的內但不符合上述技能架構規範，則應該被分類放置在`references/`下的markdown檔案。
+
+## 範例
+- "一個專注在提示LLM agent進行自我迭代，並為代碼庫帶來性能優化的技能需要被優化"-> "定義驗收條件為優化後性能相較優化前至少提升X個百分比，並且項目之中不存在任何O(n^2)級別時間複雜度的函式和邏輯，並按照標準架構重寫技能。"
+- "一個有大量前端開發範例被包含在`SKILL.md`之中的前端開發技能需要被優化" -> "定義驗收條件為前端頁面`reference`之中提供的大量建議範例重寫且不包含任何建議示例之中明確拒絕的設計，然後按照技能優化流程對技能進行全面的重寫。"
+
+## 參考資料
+- `references/example_skill.md` - 優化後的技能範例

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "@laitszkin/apollo-toolkit",
-  "version": "3.11.6",
+  "version": "3.11.7",
   "description": "Apollo Toolkit npm installer for managed skill copying across Codex, OpenClaw, and Trae.",
   "license": "MIT",
   "author": "LaiTszKin",