claude-turing 3.5.0 → 4.0.0

package/.claude-plugin/plugin.json

@@ -1,7 +1,7 @@
 {
   "name": "turing",
-  "version": "3.5.0",
-  "description": "Autonomous ML research harness — the autoresearch loop as a formal protocol. 60 commands, 2 specialized agents, experiment archaeology (trend + flashback + archive + annotate + search + template + replay), model surgery (prune + quantize + merge + surgery), feature & training intelligence, model debugging, pre-training intelligence, meta-intelligence, scaling & efficiency, model composition, deep analysis, experiment orchestration, literature + paper, model export, profiling, checkpoints, experiment intelligence, statistical rigor, tree-search, cost-performance, model cards, hypothesis database, novelty guard, anti-cheating, taste-leverage loop. Inspired by Karpathy's autoresearch and the scientific method itself.",
+  "version": "4.0.0",
+  "description": "Autonomous ML research harness — the autoresearch loop as a formal protocol. 63 commands, 2 specialized agents, research communication (cite + present + changelog), experiment archaeology (trend + flashback + archive + annotate + search + template + replay), model surgery (prune + quantize + merge + surgery), feature & training intelligence, model debugging, pre-training intelligence, meta-intelligence, scaling & efficiency, model composition, deep analysis, experiment orchestration, literature + paper, model export, profiling, checkpoints, experiment intelligence, statistical rigor, tree-search, cost-performance, model cards, hypothesis database, novelty guard, anti-cheating, taste-leverage loop. Inspired by Karpathy's autoresearch and the scientific method itself.",
   "author": {
     "name": "pragnition"
   },

package/README.md

@@ -371,6 +371,9 @@ The index (`hypotheses.yaml`) is the lightweight queue. The detail files (`hypot
 | `/turing:search <query>` | Natural language experiment search — text + structured filters |
 | `/turing:template <action>` | Experiment template library — save/list/apply reusable configs |
 | `/turing:replay <exp-id>` | Experiment replay — re-run old approach with current infrastructure |
+| `/turing:cite <action>` | Citation & attribution manager — track papers, audit missing citations, generate BibTeX |
+| `/turing:present [--figures]` | Presentation figures — training curves, comparisons, ablation, Pareto, sensitivity |
+| `/turing:changelog [--audience]` | Model changelog — version-grouped improvements for technical or stakeholder audiences |
 
 And for fully hands-off operation:
 
@@ -555,11 +558,11 @@ Each project gets independent config, data, experiments, models, and agent memor
 
 ## Architecture of Turing Itself
 
-60 commands, 2 agents, 10 config files, 79 template scripts, model registry, artifact contract, cost-performance frontier, model cards, tree-search exploration, statistical rigor, experiment intelligence, performance profiling, smart checkpoints, production model export, literature integration, paper section drafting, experiment orchestration (queue + retry + fork), deep analysis (diff + watch + regress), model composition (ensemble + stitch + warm), scaling & efficiency (scale + budget + distill), meta-intelligence (transfer + audit), pre-training intelligence (sanity + baseline + leak), model debugging (xray + sensitivity + calibrate), feature & training intelligence (feature + curriculum), model surgery (prune + quantize + merge + surgery), experiment archaeology (trend + flashback + archive + annotate + search + template + replay), 16 ADRs. See [docs/ARCHITECTURE.md](docs/ARCHITECTURE.md) for the full codemap.
+63 commands, 2 agents, 10 config files, 82 template scripts, model registry, artifact contract, cost-performance frontier, model cards, tree-search exploration, statistical rigor, experiment intelligence, performance profiling, smart checkpoints, production model export, literature integration, paper section drafting, experiment orchestration (queue + retry + fork), deep analysis (diff + watch + regress), model composition (ensemble + stitch + warm), scaling & efficiency (scale + budget + distill), meta-intelligence (transfer + audit), pre-training intelligence (sanity + baseline + leak), model debugging (xray + sensitivity + calibrate), feature & training intelligence (feature + curriculum), model surgery (prune + quantize + merge + surgery), experiment archaeology (trend + flashback + archive + annotate + search + template + replay), research communication (cite + present + changelog), 16 ADRs. See [docs/ARCHITECTURE.md](docs/ARCHITECTURE.md) for the full codemap.
 
 ```
 turing/
-├── commands/              59 skill files (core + taste-leverage + reporting + exploration + statistical rigor + experiment intelligence + performance + deployment + research workflow + orchestration + deep analysis + model composition + scaling & efficiency + meta-intelligence + pre-training intelligence + model debugging + feature & training intelligence + model surgery + experiment archaeology)
+├── commands/              62 skill files (core + taste-leverage + reporting + exploration + statistical rigor + experiment intelligence + performance + deployment + research workflow + orchestration + deep analysis + model composition + scaling & efficiency + meta-intelligence + pre-training intelligence + model debugging + feature & training intelligence + model surgery + experiment archaeology + research communication)
 ├── agents/                2 agents (researcher: read/write, evaluator: read-only)
 ├── config/                8 files (lifecycle, taxonomy, archetypes, novelty aliases)
 ├── templates/             Scaffolded into user projects by /turing:init

package/commands/changelog.md

@@ -0,0 +1,22 @@
+---
+name: changelog
+description: Model changelog generation — auto-generate human-readable progress narrative from experiment history for stakeholders.
+disable-model-invocation: true
+argument-hint: "[--since exp-id|date] [--audience technical|stakeholder]"
+allowed-tools: Read, Bash(*), Grep, Glob
+---
+
+Translate experiment logs into a narrative that PMs and stakeholders can read in 2 minutes.
+
+## Steps
+1. **Activate environment:** `source .venv/bin/activate`
+2. **Run:** `python scripts/generate_changelog.py $ARGUMENTS`
+3. **Audience:** technical (experiment IDs, configs), stakeholder (plain English, percentages)
+4. **Saved output:** `paper/CHANGELOG.md`
+
+## Examples
+```
+/turing:changelog                                # Full changelog
+/turing:changelog --audience stakeholder         # Non-technical summary
+/turing:changelog --since exp-042                # Since specific experiment
+```

package/commands/turing.md

@@ -62,6 +62,9 @@ You are the Turing ML research router. Detect the user's intent and route to the
 | "quantize", "quantization", "int8", "fp16", "reduce precision", "faster inference" | `/turing:quantize` | Optimize |
 | "merge", "model soup", "merge weights", "average models", "TIES", "DARE" | `/turing:merge` | Compose |
 | "surgery", "architecture", "add layer", "widen", "modify model", "swap activation" | `/turing:surgery` | Modify |
+| "cite", "citation", "bibliography", "bibtex", "attribution", "references" | `/turing:cite` | Record |
+| "present", "figures", "slides", "presentation", "charts", "plots" | `/turing:present` | Document |
+| "changelog", "model changelog", "progress summary", "what improved" | `/turing:changelog` | Document |
 | "trend", "trends", "research direction", "improvement rate", "diminishing returns", "what's working" | `/turing:trend` | Analyze |
 | "flashback", "where was I", "context", "resume", "catch up", "what happened" | `/turing:flashback` | Recall |
 | "archive", "cleanup", "compress old", "disk space", "archive experiments" | `/turing:archive` | Manage |
@@ -134,6 +137,9 @@ You are the Turing ML research router. Detect the user's intent and route to the
 | `/turing:search <query>` | Natural language experiment search with structured filters | (inline) |
 | `/turing:template <action>` | Experiment template library: save/list/apply reusable configs across projects | (inline) |
 | `/turing:replay <exp-id>` | Experiment replay: re-run old experiment with current infrastructure | (inline) |
+| `/turing:cite <action>` | Citation manager: add/list/check/bib for papers, datasets, methods | (inline) |
+| `/turing:present [--figures]` | Presentation figures: training curves, comparisons, ablation, Pareto, sensitivity | (inline) |
+| `/turing:changelog [--audience]` | Model changelog: version-grouped improvements for technical or stakeholder audiences | (inline) |
 
 ## Proactive Detection
 

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "claude-turing",
-  "version": "3.5.0",
+  "version": "4.0.0",
   "type": "module",
   "description": "Autonomous ML research harness for Claude Code. The autoresearch loop as a formal protocol — iteratively trains, evaluates, and improves ML models with structured experiment tracking, convergence detection, immutable evaluation infrastructure, and safety guardrails.",
   "bin": {

package/src/install.js

@@ -34,6 +34,7 @@ const SUB_COMMANDS = [
   "feature", "curriculum",
   "prune", "quantize", "merge", "surgery",
   "trend", "flashback", "archive", "annotate", "search", "template", "replay",
+  "cite", "present", "changelog",
 ];
 
 export async function install(opts = {}) {

package/src/verify.js

@@ -74,6 +74,9 @@ const EXPECTED_COMMANDS = [
   "search/SKILL.md",
   "template/SKILL.md",
   "replay/SKILL.md",
+  "cite/SKILL.md",
+  "present/SKILL.md",
+  "changelog/SKILL.md",
 ];
 
 const EXPECTED_AGENTS = ["ml-researcher.md", "ml-evaluator.md"];

package/templates/scripts/scaffold.py

@@ -137,6 +137,9 @@ TEMPLATE_DIRS = {
         "experiment_search.py",
         "experiment_templates.py",
         "experiment_replay.py",
+        "citation_manager.py",
+        "generate_figures.py",
+        "generate_changelog.py",
     ],
     "tests": ["__init__.py", "conftest.py"],
 }
@@ -184,6 +187,8 @@ DIRECTORIES_TO_CREATE = [
     "experiments/archive",
     "experiments/searches",
     "experiments/replays",
+    "experiments/citations",
+    "paper/figures",
     "experiments/logs",
     "models/best",
     "models/archive",