claude-turing 3.3.0 → 3.5.0

package/.claude-plugin/plugin.json

@@ -1,7 +1,7 @@
 {
   "name": "turing",
-  "version": "3.3.0",
-  "description": "Autonomous ML research harness — the autoresearch loop as a formal protocol. 49 commands, 2 specialized agents, feature & training intelligence (feature selection + curriculum optimization), model debugging (xray + sensitivity + calibration), pre-training intelligence (sanity checks + baseline generation + leakage detection), meta-intelligence (cross-project knowledge transfer + methodology audit), scaling & efficiency (scaling laws + compute budget + model distillation), model composition (ensemble + pipeline stitch + warm-start), deep analysis (experiment diff + live training monitor + regression gate), experiment orchestration (batch queue + smart retry + branching), literature integration + paper drafting, production model export, performance profiling, smart checkpoints, experiment intelligence, statistical rigor, tree-search hypothesis exploration, cost-performance frontier, model cards, model registry, hypothesis database with novelty guard, anti-cheating guardrails, and the taste-leverage loop. Inspired by Karpathy's autoresearch and the scientific method itself.",
+  "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.",
   "author": {
     "name": "pragnition"
   },

package/README.md

@@ -360,6 +360,17 @@ The index (`hypotheses.yaml`) is the lightweight queue. The detail files (`hypot
 | `/turing:calibrate [exp-id]` | Probability calibration — ECE/MCE, reliability diagrams, Platt/isotonic/temperature scaling |
 | `/turing:feature [--method]` | Automated feature selection — multi-method consensus ranking, redundancy, interactions |
 | `/turing:curriculum [exp-id]` | Training curriculum optimization — difficulty scoring, strategy comparison, mislabeled sample detection |
+| `/turing:prune <exp-id>` | Weight pruning — magnitude/structured/lottery, sparsity sweep, knee point detection |
+| `/turing:quantize <exp-id>` | Post-training quantization — FP16/INT8, accuracy-latency comparison |
+| `/turing:merge <exp-ids...>` | Model merging — uniform/greedy soup, TIES, DARE, zero latency cost |
+| `/turing:surgery <exp-id>` | Architecture modification — add/remove layer, widen/narrow, swap activation |
+| `/turing:trend` | Long-term trend analysis — improvement velocity, family ROI, diminishing returns |
+| `/turing:flashback` | Session context restoration — "where was I?" after days away |
+| `/turing:archive` | Experiment lifecycle cleanup — compress old artifacts, summary index |
+| `/turing:annotate <exp-id>` | Retrospective annotations — human notes and tags on experiments |
+| `/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 |
 
 And for fully hands-off operation:
 
@@ -544,11 +555,11 @@ Each project gets independent config, data, experiments, models, and agent memor
 
 ## Architecture of Turing Itself
 
-49 commands, 2 agents, 10 config files, 68 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), 16 ADRs. See [docs/ARCHITECTURE.md](docs/ARCHITECTURE.md) for the full codemap.
+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.
 
 ```
 turing/
-├── commands/              48 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)
+├── 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)
 ├── 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/annotate.md

@@ -0,0 +1,23 @@
+---
+name: annotate
+description: Retrospective experiment annotations — add human notes, tags, and context that automated metrics can't capture.
+disable-model-invocation: true
+argument-hint: "<exp-id> \"note\" [--tag fragile] | --list | --search \"keyword\""
+allowed-tools: Read, Bash(*), Grep, Glob
+---
+
+Add context that experiment logs can't capture. "This only worked because the data was pre-sorted."
+
+## Steps
+1. **Activate environment:** `source .venv/bin/activate`
+2. **Run:** `python scripts/experiment_annotations.py $ARGUMENTS`
+3. **Operations:** add (text + tags), list (per-experiment or all), search (keyword or tag)
+4. **Stored in:** `experiments/annotations.yaml`
+
+## Examples
+```
+/turing:annotate exp-042 "Fragile — only works with specific preprocessing"
+/turing:annotate exp-042 "Reviewer 2 requested this" --tag reviewer-requested
+/turing:annotate --list
+/turing:annotate --search "fragile"
+```

package/commands/archive.md

@@ -0,0 +1,23 @@
+---
+name: archive
+description: Experiment lifecycle cleanup — compress old artifacts, prune checkpoints, create queryable summary index. Reclaim disk space.
+disable-model-invocation: true
+argument-hint: "[--older-than 30d] [--keep-best 10] [--dry-run]"
+allowed-tools: Read, Bash(*), Grep, Glob
+---
+
+Keep your project directory manageable after 200+ experiments.
+
+## Steps
+1. **Activate environment:** `source .venv/bin/activate`
+2. **Run:** `python scripts/experiment_archive.py $ARGUMENTS`
+3. **Protected experiments:** Pareto-optimal, current best, recent, top-N by metric
+4. **Report:** archived count, preserved count, space reclaimed
+5. **Saved output:** `experiments/archive/index.yaml`
+
+## Examples
+```
+/turing:archive --dry-run                    # Preview what would be archived
+/turing:archive --older-than 30 --keep-best 10  # Archive old, keep top 10
+/turing:archive                              # Default: 30 days, keep 10
+```

package/commands/cite.md

@@ -0,0 +1,23 @@
+---
+name: cite
+description: Citation & attribution manager — track papers, datasets, methods. Audit for missing citations, generate BibTeX.
+disable-model-invocation: true
+argument-hint: "<add|list|check|bib> [--key Chen2016 --title XGBoost --url ...]"
+allowed-tools: Read, Bash(*), Grep, Glob
+---
+
+Track which papers and methods influenced each experiment. Catch missing citations before submission.
+
+## Steps
+1. **Activate environment:** `source .venv/bin/activate`
+2. **Run:** `python scripts/citation_manager.py $ARGUMENTS`
+3. **Operations:** add (associate citation with experiment), list (group by type), check (audit missing), bib (BibTeX)
+4. **Stored in:** `experiments/citations.yaml`
+
+## Examples
+```
+/turing:cite add exp-042 --key Chen2016 --title "XGBoost" --type method --url "https://arxiv.org/abs/1603.02754"
+/turing:cite list
+/turing:cite check                    # Audit for missing citations
+/turing:cite bib                      # Generate BibTeX
+```

package/commands/flashback.md

@@ -0,0 +1,22 @@
+---
+name: flashback
+description: Session context restoration — "where was I?" summary after days away. Current best, pending hypotheses, last session, annotations.
+disable-model-invocation: true
+argument-hint: "[--days 7] [--last 10]"
+allowed-tools: Read, Bash(*), Grep, Glob
+---
+
+Come back to a project after a week and start working in 10 seconds instead of 30 minutes.
+
+## Steps
+1. **Activate environment:** `source .venv/bin/activate`
+2. **Run:** `python scripts/session_flashback.py $ARGUMENTS`
+3. **Report:** current best, last session experiments, pending hypotheses, annotations, budget, suggested next action
+4. **Saved output:** `experiments/flashbacks/flashback-*.yaml`
+
+## Examples
+```
+/turing:flashback                    # Default: last 7 days
+/turing:flashback --days 14          # 2-week lookback
+/turing:flashback --last 5           # Last 5 experiments
+```

package/commands/merge.md

@@ -0,0 +1,24 @@
+---
+name: merge
+description: Model merging — average weights from multiple checkpoints into a single model (soups, TIES, DARE). Free accuracy, zero latency cost.
+disable-model-invocation: true
+argument-hint: "<exp-ids...> [--method uniform|greedy|ties|dare]"
+allowed-tools: Read, Bash(*), Grep, Glob
+---
+
+Combine model weights (not predictions) into a single, better model with no latency overhead.
+
+## Steps
+
+1. **Activate environment:** `source .venv/bin/activate`
+2. **Run:** `python scripts/model_merger.py $ARGUMENTS`
+3. **Methods:** uniform soup (simple average), greedy soup (include only if improves), TIES (trim+elect+merge), DARE (drop+rescale)
+4. **Report:** compatibility check, per-model metrics, method comparison, improvement delta
+5. **Saved output:** `experiments/merges/merge-*.yaml`
+
+## Examples
+
+```
+/turing:merge exp-042 exp-053 exp-067              # All methods
+/turing:merge exp-042 exp-053 --method greedy      # Greedy soup only
+```

package/commands/present.md

@@ -0,0 +1,23 @@
+---
+name: present
+description: Presentation figure generation — training curves, comparison charts, ablation tables, Pareto plots, sensitivity heatmaps.
+disable-model-invocation: true
+argument-hint: "[--figures training,comparison] [--style light|dark|poster]"
+allowed-tools: Read, Bash(*), Grep, Glob
+---
+
+Generate presentation-ready figure specifications from experiment data in seconds.
+
+## Steps
+1. **Activate environment:** `source .venv/bin/activate`
+2. **Run:** `python scripts/generate_figures.py $ARGUMENTS`
+3. **Figure types:** training, comparison, ablation, pareto, sensitivity
+4. **Styles:** light (papers), dark (demos), poster (large fonts)
+5. **Saved output:** `paper/figures/`
+
+## Examples
+```
+/turing:present                                  # All figures
+/turing:present --figures training,comparison    # Specific figures
+/turing:present --style dark                     # Dark theme
+```

package/commands/prune.md

@@ -0,0 +1,26 @@
+---
+name: prune
+description: Weight pruning — measure accuracy at different sparsity levels, find the knee point, produce a smaller/faster model.
+disable-model-invocation: true
+argument-hint: "<exp-id> [--sparsity 0.5,0.75,0.9] [--method magnitude|structured|lottery]"
+allowed-tools: Read, Bash(*), Grep, Glob
+---
+
+Remove redundant weights for faster inference and smaller models.
+
+## Steps
+
+1. **Activate environment:** `source .venv/bin/activate`
+2. **Run:** `python scripts/model_pruning.py $ARGUMENTS`
+3. **Methods:** magnitude (zero small weights), structured (remove neurons), lottery (iterative with rewind)
+4. **For tree models:** progressively reduces n_estimators
+5. **Report:** sparsity sweep table, knee point, recommended sparsity
+6. **Saved output:** `experiments/pruning/<exp-id>-pruning.yaml`
+
+## Examples
+
+```
+/turing:prune exp-042                              # Default: magnitude, 5 levels
+/turing:prune exp-042 --method structured          # Remove entire neurons
+/turing:prune exp-042 --sparsity 0.5,0.75,0.9     # Custom levels
+```

package/commands/quantize.md

@@ -0,0 +1,24 @@
+---
+name: quantize
+description: Post-training quantization — FP32→INT8/FP16, measure accuracy loss, 2-4x speedup with <0.5% accuracy loss.
+disable-model-invocation: true
+argument-hint: "<exp-id> [--precision int8|fp16|dynamic]"
+allowed-tools: Read, Bash(*), Grep, Glob
+---
+
+Quantize for production. Lowest-effort optimization: 2-4x speedup, 2-4x memory reduction.
+
+## Steps
+
+1. **Activate environment:** `source .venv/bin/activate`
+2. **Run:** `python scripts/model_quantization.py $ARGUMENTS`
+3. **Precision levels:** FP32 (baseline), FP16 (GPU), INT8 dynamic (simplest), INT8 static (best accuracy)
+4. **Report:** precision comparison table, recommended level, QAT suggestion if needed
+5. **Saved output:** `experiments/quantization/<exp-id>-quantization.yaml`
+
+## Examples
+
+```
+/turing:quantize exp-042                    # Compare all precision levels
+/turing:quantize exp-042 --precision int8   # INT8 specifically
+```

package/commands/replay.md

@@ -0,0 +1,23 @@
+---
+name: replay
+description: Experiment replay — re-run a historical experiment with current infrastructure to test if old approaches do better now.
+disable-model-invocation: true
+argument-hint: "<exp-id> [--with-current-data] [--with-current-preprocessing]"
+allowed-tools: Read, Bash(*), Grep, Glob
+---
+
+Should you revisit old ideas? Infrastructure changes may make failed approaches work now.
+
+## Steps
+1. **Activate environment:** `source .venv/bin/activate`
+2. **Run:** `python scripts/experiment_replay.py $ARGUMENTS`
+3. **Modes:** default (current code+data), --with-current-data, --with-current-preprocessing
+4. **Report:** original vs replayed metrics, delta, verdict
+5. **Saved output:** `experiments/replays/`
+
+## Examples
+```
+/turing:replay exp-023                              # Replay with current infrastructure
+/turing:replay exp-023 --with-current-data          # Current data, old code
+/turing:replay --list                               # List replayable experiments
+```

package/commands/search.md

@@ -0,0 +1,22 @@
+---
+name: search
+description: Natural language experiment search — query with text + structured filters over 200+ experiments.
+disable-model-invocation: true
+argument-hint: "<query> [--filter \"accuracy>0.85\"] [--limit 10]"
+allowed-tools: Read, Bash(*), Grep, Glob
+---
+
+Find specific experiments in a large history with natural language and structured filters.
+
+## Steps
+1. **Activate environment:** `source .venv/bin/activate`
+2. **Run:** `python scripts/experiment_search.py $ARGUMENTS`
+3. **Filters:** `accuracy>0.85`, `status:kept`, `family:baseline`, `date:last-week`
+4. **Report:** ranked table of matching experiments
+
+## Examples
+```
+/turing:search "LightGBM high accuracy" --filter "accuracy>0.85"
+/turing:search "failed neural net" --filter "status:discarded"
+/turing:search "last week" --limit 5
+```

package/commands/surgery.md

@@ -0,0 +1,27 @@
+---
+name: surgery
+description: Architecture modification — add/remove layers, widen/narrow, swap activations, inject skip connections. Specify what to change, system handles how.
+disable-model-invocation: true
+argument-hint: "<exp-id> --op <operation> [args...]"
+allowed-tools: Read, Bash(*), Grep, Glob
+---
+
+Programmatic architecture changes with auto warm-start from existing weights.
+
+## Steps
+
+1. **Activate environment:** `source .venv/bin/activate`
+2. **Run:** `python scripts/architecture_surgery.py $ARGUMENTS`
+3. **Operations:** add-layer, remove-layer, widen, narrow, swap-activation, add-skip, add-norm, deepen, swap-objective
+4. **For tree models:** deepen (increase max_depth), widen (more estimators), swap-objective
+5. **Report:** operation details, config changes, parameter count delta, warm-start source
+6. **Saved output:** `experiments/surgery/<exp-id>-<op>.yaml`
+
+## Examples
+
+```
+/turing:surgery exp-042 --op widen 2             # 2x wider hidden layers
+/turing:surgery exp-042 --op add-layer           # Insert a layer
+/turing:surgery exp-042 --op swap-activation relu gelu  # ReLU → GELU
+/turing:surgery exp-042 --op deepen              # Deeper trees
+```

package/commands/template.md

@@ -0,0 +1,22 @@
+---
+name: template
+description: Experiment template library — save winning configs as reusable templates, apply to new projects.
+disable-model-invocation: true
+argument-hint: "<save|list|apply|share> [--name name] [--from exp-id]"
+allowed-tools: Read, Bash(*), Grep, Glob
+---
+
+Turn your best experiment configs into reusable recipes that persist across projects.
+
+## Steps
+1. **Activate environment:** `source .venv/bin/activate`
+2. **Run:** `python scripts/experiment_templates.py $ARGUMENTS`
+3. **Operations:** save (from experiment), list (all templates), apply (to current project), share (export)
+4. **Stored at:** `~/.turing/templates/` (cross-project)
+
+## Examples
+```
+/turing:template save --from exp-042 --name "tabular-xgboost-v2"
+/turing:template list
+/turing:template apply tabular-xgboost-v2
+```

package/commands/trend.md

@@ -0,0 +1,21 @@
+---
+name: trend
+description: Long-term trend analysis — improvement velocity, family ROI, diminishing returns detection, strategic research direction.
+disable-model-invocation: true
+argument-hint: "[--window 30d] [--metric accuracy]"
+allowed-tools: Read, Bash(*), Grep, Glob
+---
+
+See the arc of your research, not just the latest results. Strategic view over 100+ experiments.
+
+## Steps
+1. **Activate environment:** `source .venv/bin/activate`
+2. **Run:** `python scripts/trend_analysis.py $ARGUMENTS`
+3. **Report:** improvement velocity over time windows, family ROI ranking, diminishing returns prediction, phase transitions
+4. **Saved output:** `experiments/trends/trend-*.yaml`
+
+## Examples
+```
+/turing:trend                        # Full trend analysis
+/turing:trend --window 14d           # Last 2 weeks
+```

package/commands/turing.md

@@ -58,6 +58,17 @@ You are the Turing ML research router. Detect the user's intent and route to the
 | "calibrate", "calibration", "ECE", "reliability diagram", "overconfident", "probability calibration" | `/turing:calibrate` | Analyze |
 | "feature", "features", "feature selection", "feature importance", "which features matter", "redundant features" | `/turing:feature` | Analyze |
 | "curriculum", "training order", "easy to hard", "data ordering", "curriculum learning" | `/turing:curriculum` | Optimize |
+| "prune", "pruning", "sparsity", "remove weights", "smaller model", "weight pruning" | `/turing:prune` | Optimize |
+| "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 |
+| "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 |
+| "annotate", "note", "tag experiment", "add note", "experiment note" | `/turing:annotate` | Record |
+| "search", "find experiment", "query experiments", "which experiments" | `/turing:search` | Query |
+| "template", "recipe", "save config", "reusable config", "starting point" | `/turing:template` | Manage |
+| "replay", "re-run", "revisit", "retry old", "would it work now" | `/turing:replay` | Validate |
 
 ## Sub-commands
 
@@ -112,6 +123,17 @@ You are the Turing ML research router. Detect the user's intent and route to the
 | `/turing:calibrate [exp-id]` | Probability calibration: ECE/MCE, reliability diagrams, Platt/isotonic/temperature scaling | (inline) |
 | `/turing:feature [--method]` | Automated feature selection: multi-method consensus ranking, redundancy, interaction generation | (inline) |
 | `/turing:curriculum [exp-id]` | Training curriculum optimization: difficulty scoring, strategy comparison, impossible sample detection | (inline) |
+| `/turing:prune <exp-id>` | Weight pruning: magnitude/structured/lottery, sparsity sweep, knee point detection | (inline) |
+| `/turing:quantize <exp-id>` | Post-training quantization: FP16/INT8, accuracy-latency comparison, QAT suggestion | (inline) |
+| `/turing:merge <exp-ids...>` | Model merging: uniform/greedy soup, TIES, DARE — free accuracy, zero latency cost | (inline) |
+| `/turing:surgery <exp-id>` | Architecture modification: add/remove layer, widen/narrow, swap activation, skip connections | (inline) |
+| `/turing:trend` | Long-term trend analysis: improvement velocity, family ROI, diminishing returns detection | (inline) |
+| `/turing:flashback` | Session context restoration: "where was I?" after days away from the project | (inline) |
+| `/turing:archive` | Experiment lifecycle cleanup: compress old artifacts, prune checkpoints, summary index | (inline) |
+| `/turing:annotate <exp-id>` | Retrospective annotations: add human notes, tags, search by content | (inline) |
+| `/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) |
 
 ## Proactive Detection
 

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "claude-turing",
-  "version": "3.3.0",
+  "version": "3.5.0",
   "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

@@ -32,6 +32,8 @@ const SUB_COMMANDS = [
   "sanity", "baseline", "leak",
   "xray", "sensitivity", "calibrate",
   "feature", "curriculum",
+  "prune", "quantize", "merge", "surgery",
+  "trend", "flashback", "archive", "annotate", "search", "template", "replay",
 ];
 
 export async function install(opts = {}) {

package/src/verify.js

@@ -63,6 +63,17 @@ const EXPECTED_COMMANDS = [
   "calibrate/SKILL.md",
   "feature/SKILL.md",
   "curriculum/SKILL.md",
+  "prune/SKILL.md",
+  "quantize/SKILL.md",
+  "merge/SKILL.md",
+  "surgery/SKILL.md",
+  "trend/SKILL.md",
+  "flashback/SKILL.md",
+  "archive/SKILL.md",
+  "annotate/SKILL.md",
+  "search/SKILL.md",
+  "template/SKILL.md",
+  "replay/SKILL.md",
 ];
 
 const EXPECTED_AGENTS = ["ml-researcher.md", "ml-evaluator.md"];