@ara-commons/ara-skills 0.3.0 → 0.4.0

package/skills/rigor-reviewer/SKILL.md

@@ -148,6 +148,7 @@ For each claim's Falsification criteria field:
 
 - **Over-claiming**: Does any Statement use universal scope markers ("all models", "any dataset", "state-of-the-art across all") while cited experiments cover only specific, narrow conditions? The gap must be substantial.
 - **Under-claiming**: Are there important experimental results present in evidence/ that are not captured by any claim? (Evidence without a corresponding claim.)
+- **Attribution vs mechanism**: Does any Statement merely name *which* components of this one system rank highest/lowest (load-bearing, dominant, decorative, inert) without stating what that ranking *reveals*? Apply the name-deletion test — strike the system's component names; if no transferable relationship survives, the Statement is attribution, not insight. Flag as `major` (the claim is a league table of this system, not a reusable finding); suggest the generalization the ranking licenses.
 - **Assumption explicitness**: Are key assumptions stated in problem.md (Assumptions section) or constraints.md? Are there unstated assumptions implied by the experimental design?
 - **Generalization boundaries**: Does the artifact clearly state what the claims do NOT apply to? Check constraints.md and limitations in the exploration tree.
 - **Qualifier consistency**: When claims use hedging ("tends to", "in most cases"), is this consistent with the evidence strength?

package/skills/rigor-reviewer/references/review-dimensions.md

@@ -65,6 +65,7 @@ resolution, field presence, YAML parsing) is handled entirely by Level 1.
 |-------|---------------|-----------------|
 | Over-claiming | Statement uses universal scope while evidence covers narrow conditions | critical if extreme, major if moderate |
 | Under-claiming | Evidence files or experiment results not captured by any claim | minor |
+| Attribution vs mechanism | Statement names which components rank where (name-deletion test leaves nothing transferable) instead of what the ranking reveals | major |
 | Assumption explicitness | Key assumptions stated in problem.md or constraints.md | major if unstated assumptions affect validity |
 | Generalization boundaries | Artifact states what claims do NOT apply to | minor |
 | Qualifier consistency | Hedging language matches evidence strength | minor |

package/src/index.js

@@ -17,7 +17,7 @@ ${chalk.bold('Usage:')}
 
 ${chalk.bold('Install options:')}
   --all                         Install every skill (default if no --skill given)
-  --skill <id>                  Install one skill (repeatable). Ids: compiler, research-manager, rigor-reviewer
+  --skill <id>                  Install one skill (repeatable). Ids: compiler, research-manager, rigor-reviewer, research-visualizer
   --agent <id>                  Target one agent (repeatable). Default: auto-detect, else claude-code
   --local                       Install into ./<agent>/skills instead of $HOME
   --force                       Overwrite existing installations