feat(engineering): compile OpenAI's Spinning Up in Deep RL into a knowledge-base plugin

.claude-plugin/marketplace.json

@@ -8,7 +8,7 @@
   "homepage": "https://github.com/alirezarezvani/claude-skills",
   "repository": "https://github.com/alirezarezvani/claude-skills",
   "metadata": {
-    "description": "387 production-ready skills across 20 domains (engineering, engineering-core, marketing, product, c-level, c-level-agents, compliance-os, project management, RA/QM, business growth, finance, productivity, marketing top-level, research, research-ops, business-operations, commercial, markdown-html, loop-library, plus standards). 727 Python tools, 842 reference guides, 117 agents (cs-* + personas), 149 slash commands across 98 marketplace plugins. v2.11.2 vendors engineering/skillopt-sleep — a verbatim copy of microsoft/SkillOpt's stdlib-only skillopt_sleep engine + Claude Code plugin surface, giving a local agent a nightly gated self-improvement cycle (read-only session harvest -> mine -> offline replay -> held-out-gated CLAUDE.md/SKILL.md edits -> staged for explicit /skillopt-sleep adopt). productivity/fable-goal (unreleased, post-v2.11.1) converts a rambling description of a desired outcome into one polished /goal prompt for a fresh autonomous session. v2.11.1 turns product-team and project-management into agent-harness domains: fork-orchestrators with deterministic goal routers, a Jira MCP snapshot bridge (Kanban flow metrics + Monte Carlo forecasting), a delegation-governance loop gate, a continuous-discovery cadence tracker, and an Opportunity Solution Tree linter, with /cs:pm and /cs:product command families. v2.10.3 completes the markdown-html domain with md-slides — slide-deck converter (arrow-key / Space / PgDn / Home/End / P keyboard navigation + presenter mode with split-view clock + speaker notes + next-slide preview + URL-hash deep linking like #3 for direct slide jumps + @media print page-per-slide for browser-native PDF export). Reuses md-document's markdown parser; vanilla JS only (no framework runtime); Prism.js opt-in via --syntax. Joins md-review (v2.10.2 code-review converter), md-document (v2.10.1 long-form converter), and the v2.10.0 foundation (orchestrator + design-system). Compatible with Claude Code, Codex CLI, Gemini CLI, Cursor, OpenClaw, Hermes Agent, Mistral Vibe, and 5 more coding agents.",
+    "description": "388 production-ready skills across 20 domains (engineering, engineering-core, marketing, product, c-level, c-level-agents, compliance-os, project management, RA/QM, business growth, finance, productivity, marketing top-level, research, research-ops, business-operations, commercial, markdown-html, loop-library, plus standards). 727 Python tools, 842 reference guides, 118 agents (cs-* + personas), 150 slash commands across 99 marketplace plugins. v2.11.2 vendors engineering/skillopt-sleep — a verbatim copy of microsoft/SkillOpt's stdlib-only skillopt_sleep engine + Claude Code plugin surface, giving a local agent a nightly gated self-improvement cycle (read-only session harvest -> mine -> offline replay -> held-out-gated CLAUDE.md/SKILL.md edits -> staged for explicit /skillopt-sleep adopt). productivity/fable-goal (unreleased, post-v2.11.1) converts a rambling description of a desired outcome into one polished /goal prompt for a fresh autonomous session. v2.11.1 turns product-team and project-management into agent-harness domains: fork-orchestrators with deterministic goal routers, a Jira MCP snapshot bridge (Kanban flow metrics + Monte Carlo forecasting), a delegation-governance loop gate, a continuous-discovery cadence tracker, and an Opportunity Solution Tree linter, with /cs:pm and /cs:product command families. v2.10.3 completes the markdown-html domain with md-slides — slide-deck converter (arrow-key / Space / PgDn / Home/End / P keyboard navigation + presenter mode with split-view clock + speaker notes + next-slide preview + URL-hash deep linking like #3 for direct slide jumps + @media print page-per-slide for browser-native PDF export). Reuses md-document's markdown parser; vanilla JS only (no framework runtime); Prism.js opt-in via --syntax. Joins md-review (v2.10.2 code-review converter), md-document (v2.10.1 long-form converter), and the v2.10.0 foundation (orchestrator + design-system). Compatible with Claude Code, Codex CLI, Gemini CLI, Cursor, OpenClaw, Hermes Agent, Mistral Vibe, and 5 more coding agents.",
     "version": "2.12.0"
   },
   "plugins": [
@@ -2051,6 +2051,28 @@
       ],
       "category": "development"
     },
+    {
+      "name": "spinning-up-deep-rl",
+      "source": "./engineering/spinning-up-deep-rl",
+      "description": "Knowledge base compiled from OpenAI's Spinning Up in Deep RL (MIT, Joshua Achiam) by engineering/book-to-skill. A resident core carries the RL optimization problem, the model-free taxonomy, the policy-gradient template with its five valid weights, the safe-step family (VPG to TRPO to PPO) and the overestimation family (DDPG to TD3 and SAC); 20 on-demand chapters cover key concepts and MDPs, the algorithm taxonomy and model bias, the policy gradient derivation with the log-derivative trick and EGLP lemma, Achiam's researcher essay, the key-papers topic map, the exercises including the silent DDPG broadcasting bug, the benchmark parity disclosure, one chapter per algorithm, and the logger/MPI/ExperimentGrid utilities. Ships a glossary, a patterns file with 16 techniques, a decision cheatsheet with thresholds, a cs-spinning-up-deep-rl agent and /cs:spinning-up-deep-rl. Structured study notes, not a reproduction of the source.",
+      "version": "1.0.0",
+      "author": {
+        "name": "Alireza Rezvani"
+      },
+      "keywords": [
+        "knowledge-base",
+        "book-to-skill",
+        "reinforcement-learning",
+        "deep-rl",
+        "policy-gradient",
+        "ppo",
+        "sac",
+        "td3",
+        "openai-spinning-up",
+        "engineering"
+      ],
+      "category": "development"
+    },
     {
       "name": "deep-learning-book",
       "source": "./engineering/deep-learning-book",

.codex-plugin/plugin.json

@@ -1,7 +1,7 @@
 {
   "name": "claude-code-skills",
   "version": "2.12.0",
-  "description": "380 production-ready skills across 20 domains — engineering, marketing, product, compliance, C-level advisory, research, business operations, and more. 706 Python tools, 823 reference guides, 114 agents (cs-* + personas), 138 slash commands, 96 marketplace plugins. The largest open-source skills library for AI coding agents.",
+  "description": "388 production-ready skills across 20 domains — engineering, marketing, product, compliance, C-level advisory, research, business operations, and more. 727 Python tools, 842 reference guides, 118 agents (cs-* + personas), 150 slash commands, 99 marketplace plugins. The largest open-source skills library for AI coding agents.",
   "author": {
     "name": "Alireza Rezvani",
     "url": "https://alirezarezvani.com"
@@ -27,8 +27,8 @@
     "type": "cli",
     "composerIcon": "./assets/icon.png",
     "displayName": "Claude Code Skills",
-    "shortDescription": "380 production-ready skills for AI coding agents across 20 domains",
-    "longDescription": "The largest open-source skills library for AI coding agents. 380 skills covering engineering (architecture, DevOps, security, AI/ML, agent tooling), marketing (SEO, AEO, CRO, content), product management, C-level advisory, regulatory compliance (ISO 13485, SOC 2, GDPR), project management, research and research operations, business operations, commercial, finance, and personal productivity. Includes 706 stdlib-only Python CLI tools, 823 reference guides, 114 orchestration agents, and 138 slash commands. Works with Codex, Claude Code, Gemini CLI, Cursor, Hermes Agent, Mistral Vibe, and 7 more tools.",
+    "shortDescription": "388 production-ready skills for AI coding agents across 20 domains",
+    "longDescription": "The largest open-source skills library for AI coding agents. 388 skills covering engineering (architecture, DevOps, security, AI/ML, agent tooling), marketing (SEO, AEO, CRO, content), product management, C-level advisory, regulatory compliance (ISO 13485, SOC 2, GDPR), project management, research and research operations, business operations, commercial, finance, and personal productivity. Includes 727 stdlib-only Python CLI tools, 842 reference guides, 118 orchestration agents, and 150 slash commands. Works with Codex, Claude Code, Gemini CLI, Cursor, Hermes Agent, Mistral Vibe, and 7 more tools.",
     "developerName": "Alireza Rezvani",
     "category": "Coding",
     "capabilities": [

CHANGELOG.md

@@ -7,6 +7,49 @@ and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0
 
 ## [Unreleased]
 
+### Added — engineering/spinning-up-deep-rl: the first book compiled by book-to-skill
+
+Knowledge-base plugin compiled end-to-end by `engineering/book-to-skill` from OpenAI's
+[Spinning Up in Deep RL](https://spinningup.openai.com/) (MIT, Copyright (c) 2018 OpenAI;
+primarily developed by Joshua Achiam). 20 chapters, a glossary, a patterns file and a
+decision cheatsheet, behind a 2,101-token resident core.
+
+- **The full pipeline, not a hand-write.** `openai/spinningup` cloned, its `docs/`
+  reStructuredText tree (38 files, ~37k words, ~49K tokens) run through
+  `extract_document.py --mode technical` → analysis → chapter files → supporting files →
+  master `SKILL.md` → `book_skill_validator.py` → `skill_plugin_emitter.py`. The validator
+  passes clean in `--strict` mode and every file is inside budget.
+- **Rights basis `open-license`, stated and honoured.** The emitter's Step-11 gate refuses a
+  shareable package without one. MIT permits derivative distribution; upstream's notice is
+  reproduced in full in the plugin's `LICENSE` beside this package's own, and `README.md`
+  names the source, the author and the source's frozen version.
+- **Structure follows the source's own `toctree`.** User documentation (ch01-06), Introduction
+  to RL Parts 1-3 (ch07-09), resources — the researcher essay, key papers, exercises,
+  benchmarks (ch10-13), one chapter per algorithm in lineage order (ch14-19: VPG → TRPO → PPO,
+  DDPG → TD3 → SAC), and the logger / MPI / ExperimentGrid utilities (ch20).
+- **The cheatsheet carries the judgment a glossary cannot** — the under-5-minute debug
+  turnaround, the 3-seed minimum (10+ to be thorough), family-specific benchmark network
+  defaults, and Spinning Up's own parity disclosure: DDPG/TD3/SAC are research-grade,
+  VPG/TRPO/PPO are not, and the docs say to use OpenAI Baselines for those.
+- **Counters:** skills 387 → 388; agents 117 → 118; commands 149 → 150; plugins 98 → 99.
+  Tools and references unchanged by this plugin — a compiled knowledge base ships notes, not
+  scripts. (These sit on top of `deep-learning-book`, which merged into `dev` first; the
+  derived totals are 388 skills / 727 tools / 842 references / 118 agents / 150 commands /
+  99 plugins.)
+
+### Fixed — book-to-skill's plugin emitter produced manifests this repo's CI rejects
+
+`skill_plugin_emitter.py` wrote its whole `source` provenance block into `plugin.json`, with an
+inline comment asserting that `source` and `attribution` were approved extension fields. That had
+been true and no longer was: Claude Code rejects an entire manifest on any unrecognized key
+(issue #954), and `scripts/check_plugin_json.py` hard-fails such a manifest, pointing at
+`.claude-plugin/authoring-notes.json` instead. Every package the emitter produced therefore failed
+the blocking CI gate the moment it was committed — a defect at the very last step of the pipeline,
+which is why it had gone unnoticed. `_plugin_manifest()` now emits spec fields only and a new
+`_authoring_notes()` writes the sidecar. Recorded as deviation 26 in
+`engineering/book-to-skill/README.md`. The printed `marketplace.json` snippet is unchanged: `source`
+is a valid key there, which is how it leaked into the manifest originally.
+
 ### Added — engineering/deep-learning-book: a companion to the free Deep Learning textbook
 
 New `engineering/deep-learning-book/` plugin: a study companion for *Deep Learning* by