superlab 0.1.9 → 0.1.10

package/package-assets/shared/skills/lab/stages/review.md

@@ -14,6 +14,7 @@
 - `.lab/context/mission.md`
 - `.lab/context/decisions.md`
 - `.lab/context/evidence-index.md`
+- `.lab/context/data-decisions.md`
 - `.lab/context/terminology-lock.md`
 
 ## Context Write Set
@@ -24,6 +25,8 @@
 ## Reviewer Priorities
 
 - unfair or weak baselines
+- missing canonical baselines, strong historical baselines, recent strong public methods, or closest prior work without a justified omission
+- unrepresentative benchmark mix or missing classic-public versus recent-strong-public coverage
 - leakage risk
 - metric mismatch
 - unsupported causal or statistical claims

package/package-assets/shared/skills/lab/stages/run.md

@@ -11,6 +11,8 @@
 
 - `.lab/context/mission.md`
 - `.lab/context/state.md`
+- `.lab/context/data-decisions.md`
+- `.lab/config/workflow.json`
 
 ## Context Write Set
 
@@ -22,6 +24,9 @@
 - Prefer the smallest experiment that exercises the full pipeline.
 - Fail fast on data, environment, or metric wiring problems.
 - Record the exact launch command and output location.
+- Write durable run outputs, logs, and checkpoints under `results_root`.
+- Write figures or plots under `figures_root`.
+- Keep change-local files under `.lab/changes/<change-id>/` limited to manifests, tiny fixtures, and one-off harnesses, not canonical results.
 
 ## Minimum Procedure
 

package/package-assets/shared/skills/lab/stages/spec.md

@@ -17,6 +17,7 @@
 - `.lab/context/mission.md`
 - `.lab/context/decisions.md`
 - `.lab/context/state.md`
+- `.lab/context/data-decisions.md`
 
 ## Context Write Set
 
@@ -33,6 +34,7 @@
 ## Conversion Rules
 
 - Convert the chosen idea into explicit requirements.
+- Carry the approved dataset package, source choices, and benchmark mix into the change.
 - Preserve evaluation boundaries from the idea stage.
 - Translate risks into concrete tasks when possible.
 - Make task granularity small enough that `/lab:run` and `/lab:iterate` can execute predictably.
@@ -48,6 +50,11 @@
 ## Minimum Task Coverage
 
 - change setup
+- dataset acquisition
+- source verification
+- split verification
+- preprocessing
+- benchmark protocol
 - artifact creation
 - validation run
 - evaluation normalization

package/package-assets/shared/skills/lab/stages/write.md

@@ -12,12 +12,14 @@
 ## Config Read Set
 
 - `.lab/config/workflow.json`
+- `paper_template_root` from `.lab/config/workflow.json`
 
 ## Context Read Set
 
 - `.lab/context/mission.md`
 - `.lab/context/decisions.md`
 - `.lab/context/evidence-index.md`
+- `.lab/context/data-decisions.md`
 - `.lab/context/terminology-lock.md`
 
 ## Context Write Set
@@ -45,6 +47,9 @@ Run these on every round:
 
 - Change one section or one clearly bounded subsection per round.
 - LaTeX is the required manuscript output format.
+- If `paper_template_root` is configured, inspect that template directory before drafting and align the manuscript structure to it.
+- Treat attached template directories as user-owned and potentially modified. Do not rewrite template files unless the user explicitly asks.
+- If no paper template is configured, use the default LaTeX scaffold under the deliverable paper directory.
 - Load only the current section guide. Do not load every section guide at once.
 - Build a compact mini-outline before prose.
 - For each subsection, explicitly include motivation, design, and technical advantage when applicable.

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "superlab",
-  "version": "0.1.9",
+  "version": "0.1.10",
   "description": "Strict /lab research workflow installer for Codex and Claude",
   "keywords": [
     "codex",