claude-turing 4.8.0 → 4.8.1

package/skills/turing/regress/SKILL.md

@@ -9,9 +9,9 @@ CI for your model. After any change to code, dependencies, or data, verify metri
 
 ## Steps
 
-1. **Activate environment:**
+1. **Sync environment:**
    ```bash
-   source .venv/bin/activate
+   uv sync
    ```
 
 2. **Parse arguments from `$ARGUMENTS`:**
@@ -23,7 +23,7 @@ CI for your model. After any change to code, dependencies, or data, verify metri
 
 3. **Run regression gate:**
    ```bash
-   python scripts/regression_gate.py $ARGUMENTS
+   uv run python scripts/regression_gate.py $ARGUMENTS
    ```
 
 4. **Report results:**

package/skills/turing/replay/SKILL.md

@@ -8,8 +8,8 @@ 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`
+1. **Sync environment:** `uv sync`
+2. **Run:** `uv 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/`

package/skills/turing/report/SKILL.md

@@ -2,7 +2,7 @@
 name: report
 description: Generate a markdown research report from experiment history — structured for sharing, archiving, or including in documentation. More detailed than a brief, less visual than a poster.
 argument-hint: "[--since YYYY-MM-DD] [--output path]"
-allowed-tools: Read, Bash(python scripts/*:*, source .venv/bin/activate:*, mkdir:*), Grep, Glob
+allowed-tools: Read, Bash(uv run python scripts/*:*, uv sync:*, mkdir:*), Grep, Glob
 ---
 
 Generate a structured markdown research report summarizing the experiment campaign.
@@ -14,12 +14,12 @@ Generate a structured markdown research report summarizing the experiment campai
 Use the logbook generator in markdown mode as the data backbone:
 
 ```bash
-source .venv/bin/activate && python scripts/generate_logbook.py --format markdown
+uv run python scripts/generate_logbook.py --format markdown
 ```
 
 Also gather supplementary data:
 ```bash
-source .venv/bin/activate && python scripts/generate_brief.py
+uv run python scripts/generate_brief.py
 cat experiment_state.yaml 2>/dev/null || true
 cat RESEARCH_PLAN.md 2>/dev/null || true
 ```

package/skills/turing/reproduce/SKILL.md

@@ -9,9 +9,9 @@ Verify that a logged experiment can be reproduced with consistent results.
 
 ## Steps
 
-1. **Activate environment:**
+1. **Sync environment:**
    ```bash
-   source .venv/bin/activate
+   uv sync
    ```
 
 2. **Parse arguments from `$ARGUMENTS`:**
@@ -22,7 +22,7 @@ Verify that a logged experiment can be reproduced with consistent results.
 
 3. **Run reproducibility verification:**
    ```bash
-   python scripts/reproduce_experiment.py $ARGUMENTS
+   uv run python scripts/reproduce_experiment.py $ARGUMENTS
    ```
 
 4. **Report results:**

package/skills/turing/retry/SKILL.md

@@ -9,9 +9,9 @@ Auto-diagnose and recover from experiment failures.
 
 ## Steps
 
-1. **Activate environment:**
+1. **Sync environment:**
    ```bash
-   source .venv/bin/activate
+   uv sync
    ```
 
 2. **Parse arguments from `$ARGUMENTS`:**
@@ -21,7 +21,7 @@ Auto-diagnose and recover from experiment failures.
 
 3. **Run smart retry:**
    ```bash
-   python scripts/smart_retry.py $ARGUMENTS
+   uv run python scripts/smart_retry.py $ARGUMENTS
    ```
 
 4. **Report results:**

package/skills/turing/review/SKILL.md

@@ -8,8 +8,8 @@ allowed-tools: Read, Bash(*), Grep, Glob
 Simulate a conference reviewer before you submit. Each weakness links to the command that fixes it.
 
 ## Steps
-1. `source .venv/bin/activate`
-2. `python scripts/simulate_review.py $ARGUMENTS`
+1. `uv sync`
+2. `uv run python scripts/simulate_review.py $ARGUMENTS`
 3. **Saved:** `experiments/reviews/`
 
 ## Examples

package/skills/turing/rules/loop-protocol.md

@@ -16,9 +16,9 @@ The autoresearch harness enforces a strict separation between the **hypothesis s
 
 ## Execution Rules
 
-- **ALWAYS redirect training output:** `python train.py > run.log 2>&1`
+- **ALWAYS redirect training output:** `uv run python train.py > run.log 2>&1`
 - **ALWAYS parse metrics with grep** between `---` delimiters: `grep -A 10 "^---" run.log | head -10`
-- **ALWAYS activate the venv first:** `source .venv/bin/activate`
+- **ALWAYS run Python through uv:** `uv run python ...`
 - **NEVER install new packages** without human approval
 
 ## Git Discipline
@@ -40,16 +40,16 @@ The autoresearch harness enforces a strict separation between the **hypothesis s
 
 ## Sweep Workflow
 
-1. Generate queue: `python scripts/sweep.py`
-2. Check status: `python scripts/sweep.py --status`
-3. Get next: `python scripts/sweep.py --next`
+1. Generate queue: `uv run python scripts/sweep.py`
+2. Check status: `uv run python scripts/sweep.py --status`
+3. Get next: `uv run python scripts/sweep.py --next`
 4. Apply overrides, create branch, run training
-5. Mark: `python scripts/sweep.py --mark <name> complete|failed`
+5. Mark: `uv run python scripts/sweep.py --mark <name> complete|failed`
 6. Repeat until queue is empty
 
 ## Logging Rules
 
-- **Log every experiment** to `experiments/log.jsonl` via `python scripts/log_experiment.py` — kept and discarded alike.
+- **Log every experiment** to `experiments/log.jsonl` via `uv run python scripts/log_experiment.py` — kept and discarded alike.
 - **Include all metrics, config, and description** of the hypothesis and its outcome.
 
 ## Convergence Rules
@@ -64,11 +64,11 @@ The researcher agent's Bash access is restricted to a whitelist of necessary com
 
 | Allowed Pattern | Purpose |
 |-----------------|---------|
-| `python train.py:*` | Execute training |
-| `python scripts/*:*` | Run utility scripts (logging, metrics, sweep) |
+| `uv run python train.py:*` | Execute training |
+| `uv run python scripts/*:*` | Run utility scripts (logging, metrics, sweep) |
 | `git:*` | Branch, commit, merge, reset operations |
-| `source .venv/bin/activate:*` | Virtual environment activation |
-| `pip:*` | Package installation (requires human approval) |
+| `uv sync:*` | Virtual environment activation |
+| `uv add:*` | Package installation (requires human approval) |
 
 **Blocked by omission:** `cat`, `head`, `tail`, `less` (prevents reading hidden files via shell), `curl`, `wget` (prevents data exfiltration), arbitrary command execution.
 

package/skills/turing/sanity/SKILL.md

@@ -9,9 +9,9 @@ Run a battery of fast checks before committing to a full training run. Catches w
 
 ## Steps
 
-1. **Activate environment:**
+1. **Sync environment:**
    ```bash
-   source .venv/bin/activate
+   uv sync
    ```
 
 2. **Parse arguments from `$ARGUMENTS`:**
@@ -21,7 +21,7 @@ Run a battery of fast checks before committing to a full training run. Catches w
 
 3. **Run sanity checks:**
    ```bash
-   python scripts/sanity_checks.py $ARGUMENTS
+   uv run python scripts/sanity_checks.py $ARGUMENTS
    ```
 
 4. **Checks performed:**

package/skills/turing/scale/SKILL.md

@@ -9,9 +9,9 @@ Predict full-scale performance from a handful of small experiments. Answers "is
 
 ## Steps
 
-1. **Activate environment:**
+1. **Sync environment:**
    ```bash
-   source .venv/bin/activate
+   uv sync
    ```
 
 2. **Parse arguments from `$ARGUMENTS`:**
@@ -24,11 +24,11 @@ Predict full-scale performance from a handful of small experiments. Answers "is
 3. **Plan or analyze:**
    - **Plan mode (default):** generates scale point configs to run
      ```bash
-     python scripts/scaling_estimator.py --axis data --points 4
+     uv run python scripts/scaling_estimator.py --axis data --points 4
      ```
    - **Analyze mode:** fits power law to completed results
      ```bash
-     python scripts/scaling_estimator.py --analyze experiments/scaling/results.yaml
+     uv run python scripts/scaling_estimator.py --analyze experiments/scaling/results.yaml
      ```
 
 4. **Scaling axes:**

package/skills/turing/search/SKILL.md

@@ -8,8 +8,8 @@ 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`
+1. **Sync environment:** `uv sync`
+2. **Run:** `uv 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
 

package/skills/turing/seed/SKILL.md

@@ -9,9 +9,9 @@ Run a multi-seed study to verify that experiment results are robust across rando
 
 ## Steps
 
-1. **Activate environment:**
+1. **Sync environment:**
    ```bash
-   source .venv/bin/activate
+   uv sync
    ```
 
 2. **Parse arguments from `$ARGUMENTS`:**
@@ -22,7 +22,7 @@ Run a multi-seed study to verify that experiment results are robust across rando
 
 3. **Run seed study:**
    ```bash
-   python scripts/seed_runner.py $ARGUMENTS
+   uv run python scripts/seed_runner.py $ARGUMENTS
    ```
 
 4. **Report results:**

package/skills/turing/sensitivity/SKILL.md

@@ -9,9 +9,9 @@ Which hyperparameters actually matter? Stop wasting time on the ones that don't.
 
 ## Steps
 
-1. **Activate environment:**
+1. **Sync environment:**
    ```bash
-   source .venv/bin/activate
+   uv sync
    ```
 
 2. **Parse arguments from `$ARGUMENTS`:**
@@ -21,7 +21,7 @@ Which hyperparameters actually matter? Stop wasting time on the ones that don't.
 
 3. **Run sensitivity analysis:**
    ```bash
-   python scripts/sensitivity_analysis.py $ARGUMENTS
+   uv run python scripts/sensitivity_analysis.py $ARGUMENTS
    ```
 
 4. **Report includes:**

package/skills/turing/share/SKILL.md

@@ -8,8 +8,8 @@ allowed-tools: Read, Bash(*), Grep, Glob
 Package experiments for collaborator handoff or paper supplementary material.
 
 ## Steps
-1. `source .venv/bin/activate`
-2. `python scripts/package_experiments.py $ARGUMENTS`
+1. `uv sync`
+2. `uv run python scripts/package_experiments.py $ARGUMENTS`
 3. **Saved:** `exports/packages/<name>/`
 
 ## Examples

package/skills/turing/simulate/SKILL.md

@@ -8,8 +8,8 @@ allowed-tools: Read, Bash(*), Grep, Glob
 Predict outcomes before spending compute. Ranks proposed configs and recommends which to run vs skip.
 
 ## Steps
-1. `source .venv/bin/activate`
-2. `python scripts/experiment_simulator.py $ARGUMENTS`
+1. `uv sync`
+2. `uv run python scripts/experiment_simulator.py $ARGUMENTS`
 3. **Saved:** `experiments/simulations/`
 
 ## How it works

package/skills/turing/status/SKILL.md

@@ -10,7 +10,7 @@ Show the current state of the ML training pipeline. This is an observation-only
 
 1. **Run metrics display:**
    ```bash
-   source .venv/bin/activate && python scripts/show_metrics.py --last 10
+   uv run python scripts/show_metrics.py --last 10
    ```
 
 2. **Summarize for the user:**

package/skills/turing/stitch/SKILL.md

@@ -9,9 +9,9 @@ Decompose your ML pipeline into stages that can be independently varied, cached,
 
 ## Steps
 
-1. **Activate environment:**
+1. **Sync environment:**
    ```bash
-   source .venv/bin/activate
+   uv sync
    ```
 
 2. **Parse arguments from `$ARGUMENTS`:**
@@ -23,7 +23,7 @@ Decompose your ML pipeline into stages that can be independently varied, cached,
 
 3. **Run pipeline manager:**
    ```bash
-   python scripts/pipeline_manager.py $ARGUMENTS
+   uv run python scripts/pipeline_manager.py $ARGUMENTS
    ```
 
 4. **Report results:**

package/skills/turing/suggest/SKILL.md

@@ -2,7 +2,7 @@
 name: suggest
 description: Literature-grounded model selection. Reads the ML task context, searches recent literature, and suggests model architectures worth trying — with citations. Suggestions are auto-queued as hypotheses.
 argument-hint: "[task description override]"
-allowed-tools: Read, Write, Bash(python scripts/*:*, source .venv/bin/activate:*), Grep, Glob, WebSearch, WebFetch
+allowed-tools: Read, Write, Bash(uv run python scripts/*:*, uv sync:*), Grep, Glob, WebSearch, WebFetch
 ---
 
 Suggest model architectures for the current ML task. Supports two strategies:
@@ -25,7 +25,7 @@ cat config.yaml
 ```
 
 ```bash
-source .venv/bin/activate && python scripts/show_metrics.py --last 10 2>/dev/null || echo "No experiments yet"
+uv run python scripts/show_metrics.py --last 10 2>/dev/null || echo "No experiments yet"
 ```
 
 If `$ARGUMENTS` is provided, use that as the task description. Otherwise, infer from `config.yaml` (model type, primary metric, data source, target column).
@@ -66,7 +66,7 @@ From the literature, synthesize **3-5 concrete model architecture suggestions**.
 For each suggestion, add to the hypothesis queue:
 
 ```bash
-source .venv/bin/activate && python scripts/manage_hypotheses.py add "<model>: <rationale> (source: <citation>)" --priority medium --source literature
+uv run python scripts/manage_hypotheses.py add "<model>: <rationale> (source: <citation>)" --priority medium --source literature
 ```
 
 ### 5. Show Results
@@ -105,7 +105,7 @@ Same detection logic as the literature strategy — find `config.yaml` + `train.
 ### 2. Run Tree Search
 
 ```bash
-source .venv/bin/activate && python scripts/treequest_suggest.py \
+uv run python scripts/treequest_suggest.py \
     --log experiments/log.jsonl \
     --config config.yaml \
     --top 5 \
@@ -120,7 +120,7 @@ If TreeQuest is not installed, the script automatically falls back to greedy bes
 For each result from the tree search, queue as a hypothesis:
 
 ```bash
-source .venv/bin/activate && python scripts/manage_hypotheses.py add "<description>" --priority medium --source treequest
+uv run python scripts/manage_hypotheses.py add "<description>" --priority medium --source treequest
 ```
 
 ### 4. Show Results

package/skills/turing/surgery/SKILL.md

@@ -9,8 +9,8 @@ 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`
+1. **Sync environment:** `uv sync`
+2. **Run:** `uv 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

package/skills/turing/sweep/SKILL.md

@@ -2,38 +2,38 @@
 name: sweep
 description: Generate and run a systematic hyperparameter sweep. Computes the cartesian product of configured parameter ranges and processes the queue sequentially with full experiment logging.
 argument-hint: "[sweep_config.yaml]"
-allowed-tools: Read, Write, Edit, Bash(python train.py:*, python scripts/*:*, git:*, source .venv/bin/activate:*, pip:*), Grep, Glob
+allowed-tools: Read, Write, Edit, Bash(uv run python train.py:*, uv run python scripts/*:*, git:*, uv sync:*, uv add:*), Grep, Glob
 ---
 
 Run a systematic hyperparameter sweep using the sweep configuration.
 
 ## Steps
 
-1. **Activate environment:**
+1. **Sync environment:**
    ```bash
-   source .venv/bin/activate
+   uv sync
    ```
 
 2. **Resolve config:** Use `$ARGUMENTS` as sweep config path, or default to `sweep_config.yaml`.
 
 3. **Generate queue** (if not already generated):
    ```bash
-   python scripts/sweep.py [sweep_config.yaml]
+   uv run python scripts/sweep.py [sweep_config.yaml]
    ```
 
 4. **Check queue status:**
    ```bash
-   python scripts/sweep.py --status
+   uv run python scripts/sweep.py --status
    ```
 
 5. **Process queue sequentially:**
-   - Get next: `python scripts/sweep.py --next`
+   - Get next: `uv run python scripts/sweep.py --next`
    - Apply config overrides to `config.yaml`
    - Create experiment branch: `git checkout -b exp/NNN-description`
-   - Run training: `python train.py > run.log 2>&1`
+   - Run training: `uv run python train.py > run.log 2>&1`
    - Parse metrics: `grep -A 10 "^---" run.log | head -10`
    - Log the experiment
-   - Mark complete: `python scripts/sweep.py --mark <name> complete`
+   - Mark complete: `uv run python scripts/sweep.py --mark <name> complete`
    - If improved, merge to main. If not, return to main.
    - Repeat until queue is empty
 

package/skills/turing/template/SKILL.md

@@ -8,8 +8,8 @@ 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`
+1. **Sync environment:** `uv sync`
+2. **Run:** `uv 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)
 

package/skills/turing/train/SKILL.md

@@ -2,7 +2,7 @@
 name: train
 description: Run the autonomous ML experiment loop. Iteratively hypothesizes, trains, evaluates, and decides — keeping only improvements. Implements the autoresearch pattern with formal convergence detection and git-disciplined rollback.
 argument-hint: "[max_iterations]"
-allowed-tools: Read, Write, Edit, Bash(python train.py:*, python scripts/*:*, git:*, source .venv/bin/activate:*, pip:*), Grep, Glob
+allowed-tools: Read, Write, Edit, Bash(uv run python train.py:*, uv run python scripts/*:*, git:*, uv sync:*, uv add:*), Grep, Glob
 ---
 
 You are an autonomous ML researcher. Your goal: iteratively improve a model by following the experiment loop protocol — the scientific method applied to machine learning.
@@ -26,9 +26,9 @@ Read `program.md` in the ML project directory for the complete protocol. Follow
 
 1. **Restore memory:** Read `.claude/agent-memory/ml-researcher-{project_name}/MEMORY.md` for prior observations and best results.
 2. **Read protocol:** Read `program.md` completely — it defines the experiment loop, constraints, and output format.
-3. **Bootstrap data:** Check for training data at `config.yaml` → `data.source`. If no splits exist, run `python prepare.py`.
-4. **Bootstrap venv:** `test -d .venv || (python3 -m venv .venv && source .venv/bin/activate && pip install -r requirements.txt)`
-5. **Assess state:** `source .venv/bin/activate && python scripts/show_metrics.py --last 5`
+3. **Bootstrap data:** Check for training data at `config.yaml` → `data.source`. If no splits exist, run `uv run python prepare.py`.
+4. **Bootstrap uv environment:** `uv sync`
+5. **Assess state:** `uv run python scripts/show_metrics.py --last 5`
 6. **Begin the loop** from program.md.
 
 ## The Loop
@@ -47,7 +47,7 @@ Use `@ml-evaluator` for analysis tasks. It is read-only (no Write/Edit) and cann
 
 ## Context Management
 
-- Redirect all training output: `python train.py > run.log 2>&1`
+- Redirect all training output: `uv run python train.py > run.log 2>&1`
 - Parse metrics with grep, never read full output
 - Persist observations to MEMORY.md after each experiment
 

package/skills/turing/transfer/SKILL.md

@@ -9,9 +9,9 @@ Find similar prior projects and surface what worked. "Last time you had tabular
 
 ## Steps
 
-1. **Activate environment:**
+1. **Sync environment:**
    ```bash
-   source .venv/bin/activate
+   uv sync
    ```
 
 2. **Parse arguments from `$ARGUMENTS`:**
@@ -22,7 +22,7 @@ Find similar prior projects and surface what worked. "Last time you had tabular
 
 3. **Run knowledge transfer:**
    ```bash
-   python scripts/knowledge_transfer.py $ARGUMENTS
+   uv run python scripts/knowledge_transfer.py $ARGUMENTS
    ```
 
 4. **Report includes:**

package/skills/turing/trend/SKILL.md

@@ -8,8 +8,8 @@ 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`
+1. **Sync environment:** `uv sync`
+2. **Run:** `uv 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`
 

package/skills/turing/try/SKILL.md

@@ -2,7 +2,7 @@
 name: try
 description: Inject a hypothesis into the agent's experiment queue. This is how research taste reaches the agent — the human selects which coins to flip, the agent flips them.
 argument-hint: "<hypothesis description>"
-allowed-tools: Read, Write, Edit, Bash(python scripts/*:*, source .venv/bin/activate:*), Grep, Glob
+allowed-tools: Read, Write, Edit, Bash(uv run python scripts/*:*, uv sync:*), Grep, Glob
 ---
 
 Inject a human hypothesis into the experiment queue for the next `/turing:train` iteration.
@@ -15,18 +15,18 @@ This is the taste-leverage mechanism: you provide judgment about what's worth tr
 
 2. **Check for archetype syntax.** If the argument starts with `archetype:`, expand it:
    ```bash
-   source .venv/bin/activate && python scripts/manage_hypotheses.py add --archetype <name> --priority high --source human
+   uv run python scripts/manage_hypotheses.py add --archetype <name> --priority high --source human
    ```
 
    Otherwise, use the raw description:
    ```bash
-   source .venv/bin/activate && python scripts/manage_hypotheses.py add "$ARGUMENTS" --priority high --source human
+   uv run python scripts/manage_hypotheses.py add "$ARGUMENTS" --priority high --source human
    ```
 
 3. **Confirm** with the hypothesis ID and instructions:
    - "Queued as hyp-NNN (high priority, human-injected)"
    - "The agent will prioritize this on the next `/turing:train` iteration"
-   - Show current queue: `python scripts/manage_hypotheses.py list --status queued`
+   - Show current queue: `uv run python scripts/manage_hypotheses.py list --status queued`
 
 ## Examples
 

package/skills/turing/update/SKILL.md

@@ -8,8 +8,8 @@ allowed-tools: Read, Bash(*), Grep, Glob
 Add new data to an existing model without starting from scratch. Detects catastrophic forgetting.
 
 ## Steps
-1. `source .venv/bin/activate`
-2. `python scripts/incremental_update.py $ARGUMENTS`
+1. `uv sync`
+2. `uv run python scripts/incremental_update.py $ARGUMENTS`
 3. **Saved:** `experiments/updates/`
 
 ## Model-specific strategies

package/skills/turing/validate/SKILL.md

@@ -9,19 +9,19 @@ Validate the stability of the current ML pipeline by running it multiple times a
 
 ## Steps
 
-1. **Activate environment:**
+1. **Sync environment:**
    ```bash
-   source .venv/bin/activate
+   uv sync
    ```
 
 2. **Run stability check:**
    ```bash
-   python scripts/validate_stability.py
+   uv run python scripts/validate_stability.py
    ```
 
 3. **If `$ARGUMENTS` contains `--auto`:**
    ```bash
-   python scripts/validate_stability.py --auto
+   uv run python scripts/validate_stability.py --auto
    ```
    This auto-writes `evaluation.n_runs: 3` to `config.yaml` if CV > 5%.
 

package/skills/turing/warm/SKILL.md

@@ -9,9 +9,9 @@ Take a trained checkpoint and use it as initialization for a new experiment. Aut
 
 ## Steps
 
-1. **Activate environment:**
+1. **Sync environment:**
    ```bash
-   source .venv/bin/activate
+   uv sync
    ```
 
 2. **Parse arguments from `$ARGUMENTS`:**
@@ -23,7 +23,7 @@ Take a trained checkpoint and use it as initialization for a new experiment. Aut
 
 3. **Run warm-start planner:**
    ```bash
-   python scripts/warm_start.py $ARGUMENTS
+   uv run python scripts/warm_start.py $ARGUMENTS
    ```
 
 4. **Report results:**

package/skills/turing/watch/SKILL.md

@@ -9,9 +9,9 @@ Stream metrics during training with early-warning alerts. Catches problems mid-r
 
 ## Steps
 
-1. **Activate environment:**
+1. **Sync environment:**
    ```bash
-   source .venv/bin/activate
+   uv sync
    ```
 
 2. **Parse arguments from `$ARGUMENTS`:**
@@ -23,13 +23,13 @@ Stream metrics during training with early-warning alerts. Catches problems mid-r
 
 3. **For post-hoc analysis:**
    ```bash
-   python scripts/training_monitor.py --analyze run.log
+   uv run python scripts/training_monitor.py --analyze run.log
    ```
 
 4. **For live monitoring (inform user):**
    Live monitoring requires a running training process. Suggest the user run in a separate terminal:
    ```bash
-   python scripts/training_monitor.py --log run.log --interval 10
+   uv run python scripts/training_monitor.py --log run.log --interval 10
    ```
 
 5. **Alert types:**

package/skills/turing/whatif/SKILL.md

@@ -8,8 +8,8 @@ allowed-tools: Read, Bash(*), Grep, Glob
 Answer "what if?" questions using existing experiment data. Routes to the right estimator automatically.
 
 ## Steps
-1. `source .venv/bin/activate`
-2. `python scripts/whatif_engine.py $ARGUMENTS`
+1. `uv sync`
+2. `uv run python scripts/whatif_engine.py $ARGUMENTS`
 3. **Saved:** `experiments/whatif/`
 
 ## Supported question types