claude-turing 4.6.0 → 4.8.0

package/commands/transfer.md

@@ -1,7 +1,6 @@
 ---
 name: transfer
 description: Cross-project knowledge transfer — find similar prior projects and surface what worked. Builds institutional ML memory.
-disable-model-invocation: true
 argument-hint: "[--from project-path] [--auto]"
 allowed-tools: Read, Bash(*), Grep, Glob
 ---

package/commands/trend.md

@@ -1,7 +1,6 @@
 ---
 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
 ---

package/commands/try.md

@@ -1,7 +1,6 @@
 ---
 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.
-disable-model-invocation: true
 argument-hint: "<hypothesis description>"
 allowed-tools: Read, Write, Edit, Bash(python scripts/*:*, source .venv/bin/activate:*), Grep, Glob
 ---

package/commands/turing.md

@@ -7,10 +7,10 @@ You are the Turing ML research router. Detect the user's intent and identify the
 
 ## Execution Contract
 
-Turing sub-commands are explicit slash-command skills. Current sub-commands are `slash_only` and use `disable-model-invocation: true`, so router handling must not claim model dispatch into those skills.
+Turing sub-commands are slash-command skills that allow model invocation, so router handling may select the focused skill when the user's intent matches a sub-command.
 
-- If the user explicitly invokes `/turing:<cmd>`, Claude Code runtime handles that slash command.
-- If the user invokes `/turing` as a router and the detected command is `slash_only`, give the exact slash command to run.
+- If the user explicitly invokes `/turing:<cmd>`, handle that focused sub-command directly.
+- If the user invokes `/turing` as a router and the detected command is `slash_only`, route to the focused sub-command skill when appropriate.
 - If a command has a documented safe equivalent script, the assistant may execute those documented steps inline when safe and appropriate.
 
 ## Routing Table

package/commands/update.md

@@ -1,7 +1,6 @@
 ---
 name: update
 description: Incremental model update — add new data without full retraining, with forgetting detection.
-disable-model-invocation: true
 argument-hint: "<exp-id> --new-data <path> [--replay-ratio 0.1] [--tolerance 0.005]"
 allowed-tools: Read, Bash(*), Grep, Glob
 ---

package/commands/validate.md

@@ -1,7 +1,6 @@
 ---
 name: validate
 description: Run stability validation on the current experiment configuration. Executes N runs to measure metric variance and auto-configures multi-run evaluation if variance is too high.
-disable-model-invocation: true
 argument-hint: "[--auto]"
 allowed-tools: Read, Bash(*), Grep, Glob
 ---

package/commands/warm.md

@@ -1,7 +1,6 @@
 ---
 name: warm
 description: Warm-start from a prior model — load checkpoint, optionally freeze layers, adjust learning rate, and continue training.
-disable-model-invocation: true
 argument-hint: "<exp-id> [--freeze-layers encoder] [--unfreeze-after 5]"
 allowed-tools: Read, Bash(*), Grep, Glob
 ---

package/commands/watch.md

@@ -1,7 +1,6 @@
 ---
 name: watch
 description: Live training monitor with early-warning alerts for loss spikes, NaN, overfitting, and metric plateaus.
-disable-model-invocation: true
 argument-hint: "[--alerts] [--interval 10] [--analyze run.log]"
 allowed-tools: Read, Bash(*), Grep, Glob
 ---

package/commands/whatif.md

@@ -1,7 +1,6 @@
 ---
 name: whatif
 description: What-if analysis — answer hypotheticals from existing experiment data without running new experiments.
-disable-model-invocation: true
 argument-hint: "\"<question>\" [--json]"
 allowed-tools: Read, Bash(*), Grep, Glob
 ---

package/commands/xray.md

@@ -1,7 +1,6 @@
 ---
 name: xray
 description: Internal model diagnostics — gradient flow, dead neurons, activation stats, weight distributions, tree depth analysis.
-disable-model-invocation: true
 argument-hint: "[exp-id] [--layer encoder.layer.2] [--compare exp-a exp-b]"
 allowed-tools: Read, Bash(*), Grep, Glob
 ---