Fix bugs in skills: wrong tool name, broken regex, missing steps

- review-implementation: "Task tool" → "Agent tool" (tool doesn't exist)
- review-implementation: Remove narrow HEAD~1 detection, use main..HEAD only
- review-implementation: Add run_in_background guidance for parallel dispatch
- structural-reviewer-prompt: Fix grep-style \| to ripgrep | alternation
- fix-pr: Add $REPO resolution, replace {owner}/{repo} placeholders
- fix-pr: Clarify --jq warning scope (gh api only, not gh pr view)
- add-rule: Add export_schemas to Step 6, fix section title
- add-model: Add Step 2.5 for declare_variants! macro registration
- add-model: Add declare_variants! to Common Mistakes table

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>

Author: GiggleLiu

.claude/skills/add-model/SKILL.md

@@ -85,6 +85,22 @@ Key decisions:
 - **`dims()`:** returns the configuration space dimensions (e.g., `vec![2; n]` for binary variables)
 - **`evaluate()`:** must check feasibility first, then compute objective
 
+## Step 2.5: Register variant complexity
+
+Add `declare_variants!` at the bottom of the model file (after the trait impls, before the test link). Each line declares a concrete type instantiation with its best-known worst-case complexity:
+
+```rust
+crate::declare_variants! {
+    ProblemName<SimpleGraph, i32>  => "1.1996^num_vertices",
+    ProblemName<SimpleGraph, One>  => "1.1996^num_vertices",
+}
+```
+
+- The complexity string references the getter method names from Step 1.5 (e.g., `num_vertices`)
+- One entry per supported `(graph, weight)` combination
+- The string is parsed as an `Expr` AST — supports `+`, `*`, `^`, `exp()`, `log()`, `sqrt()`
+- See `src/models/graph/maximum_independent_set.rs` for the reference pattern
+
 ## Step 3: Register the model
 
 Update these files to register the new problem type:
@@ -146,5 +162,6 @@ Then run the [review-implementation](../review-implementation/SKILL.md) skill to
 | Missing `#[path]` test link | Add `#[cfg(test)] #[path = "..."] mod tests;` at file bottom |
 | Wrong `dims()` | Must match the actual configuration space (e.g., `vec![2; n]` for binary) |
 | Not registering in `mod.rs` | Must update both `<category>/mod.rs` and `models/mod.rs` |
+| Forgetting `declare_variants!` | Required for variant complexity metadata used by the paper's auto-generated table |
 | Forgetting CLI dispatch | Must add match arms in `dispatch.rs` (`load_problem` + `serialize_any_problem`) |
 | Forgetting CLI alias | Must add lowercase entry in `problem_name.rs` `resolve_alias()` |

.claude/skills/add-rule/SKILL.md

@@ -131,11 +131,12 @@ example_fn!(test_<source>_to_<target>, reduction_<source>_to_<target>);
 
 Invoke the `/write-rule-in-paper` skill to write the reduction-rule entry in `docs/paper/reductions.typ`. That skill covers the full authoring process: complexity citation, self-contained proof, detailed worked example, and verification checklist.
 
-## Step 6: Regenerate graph and verify
+## Step 6: Regenerate exports and verify
 
 ```bash
-cargo run --example export_graph  # Update reduction_graph.json
-make test clippy                  # Must pass
+cargo run --example export_graph    # Update reduction_graph.json
+cargo run --example export_schemas  # Update problem schemas
+make test clippy                    # Must pass
 ```
 
 Then run the [review-implementation](../review-implementation/SKILL.md) skill to verify all structural and semantic checks pass.

.claude/skills/fix-pr/SKILL.md

@@ -11,14 +11,17 @@ Resolve PR review comments, fix CI failures, and address codecov coverage gaps f
 
 **IMPORTANT:** Do NOT use `gh api --jq` for extracting data — it uses a built-in jq that
 chokes on response bodies containing backslashes (common in Copilot code suggestions).
-Always pipe to `python3 -c` instead.
+Always pipe to `python3 -c` instead. (`gh pr view --jq` is fine — only `gh api --jq` is affected.)
 
 ```bash
+# Get repo identifiers
+REPO=$(gh repo view --json nameWithOwner --jq .nameWithOwner)  # e.g., "owner/repo"
+
 # Get PR number
 PR=$(gh pr view --json number --jq .number)
 
 # Get PR head SHA (on remote)
-HEAD_SHA=$(gh api repos/{owner}/{repo}/pulls/$PR | python3 -c "import sys,json; print(json.load(sys.stdin)['head']['sha'])")
+HEAD_SHA=$(gh api repos/$REPO/pulls/$PR | python3 -c "import sys,json; print(json.load(sys.stdin)['head']['sha'])")
 ```
 
 ### 1a. Fetch Review Comments
@@ -27,23 +30,23 @@ Three sources of feedback to check:
 
 ```bash
 # Copilot and user inline review comments (on code lines)
-gh api repos/{owner}/{repo}/pulls/$PR/comments | python3 -c "
+gh api repos/$REPO/pulls/$PR/comments | python3 -c "
 import sys,json
 for c in json.load(sys.stdin):
     line = c.get('line') or c.get('original_line') or '?'
     print(f'[{c[\"user\"][\"login\"]}] {c[\"path\"]}:{line} — {c[\"body\"]}')
 "
 
 # Review-level comments (top-level review body)
-gh api repos/{owner}/{repo}/pulls/$PR/reviews | python3 -c "
+gh api repos/$REPO/pulls/$PR/reviews | python3 -c "
 import sys,json
 for r in json.load(sys.stdin):
     if r.get('body'):
         print(f'[{r[\"user\"][\"login\"]}] {r[\"state\"]}: {r[\"body\"]}')
 "
 
 # Issue-level comments (general discussion, excluding bots)
-gh api repos/{owner}/{repo}/issues/$PR/comments | python3 -c "
+gh api repos/$REPO/issues/$PR/comments | python3 -c "
 import sys,json
 for c in json.load(sys.stdin):
     login = c['user']['login']
@@ -56,7 +59,7 @@ for c in json.load(sys.stdin):
 
 ```bash
 # All check runs on the PR head
-gh api repos/{owner}/{repo}/commits/$HEAD_SHA/check-runs | python3 -c "
+gh api repos/$REPO/commits/$HEAD_SHA/check-runs | python3 -c "
 import sys,json
 for cr in json.load(sys.stdin)['check_runs']:
     print(f'{cr[\"name\"]}: {cr.get(\"conclusion\") or cr[\"status\"]}')
@@ -67,7 +70,7 @@ for cr in json.load(sys.stdin)['check_runs']:
 
 ```bash
 # Codecov bot comment with coverage diff
-gh api repos/{owner}/{repo}/issues/$PR/comments | python3 -c "
+gh api repos/$REPO/issues/$PR/comments | python3 -c "
 import sys,json
 for c in json.load(sys.stdin):
     if c['user']['login'] == 'codecov[bot]':
@@ -129,7 +132,7 @@ For detailed line-by-line coverage, use the Codecov API:
 
 ```bash
 # Get file-level coverage for the PR
-gh api repos/{owner}/{repo}/issues/$PR/comments | python3 -c "
+gh api repos/$REPO/issues/$PR/comments | python3 -c "
 import sys,json,re
 for c in json.load(sys.stdin):
     if c['user']['login'] == 'codecov[bot]':

.claude/skills/review-implementation/SKILL.md

@@ -21,9 +21,7 @@ Dispatches two parallel review subagents with fresh context (no implementation h
 Determine whether new model/rule files were added:
 
 ```bash
-# Check for NEW files (not just modifications)
-git diff --name-only --diff-filter=A HEAD~1..HEAD
-# Also check against main for branch-level changes
+# Check for NEW files across the entire branch
 git diff --name-only --diff-filter=A main..HEAD
 ```
 
@@ -77,7 +75,7 @@ If an issue is found, pass it as `{ISSUE_CONTEXT}` to both subagents. If not, se
 
 ### Structural Reviewer (if new model/rule detected)
 
-Dispatch using `Task` tool with `subagent_type="superpowers:code-reviewer"`:
+Dispatch using `Agent` tool with `subagent_type="superpowers:code-reviewer"`:
 
 - Read `structural-reviewer-prompt.md` from this skill directory
 - Fill placeholders:
@@ -90,7 +88,7 @@ Dispatch using `Task` tool with `subagent_type="superpowers:code-reviewer"`:
 
 ### Quality Reviewer (always)
 
-Dispatch using `Task` tool with `subagent_type="superpowers:code-reviewer"`:
+Dispatch using `Agent` tool with `subagent_type="superpowers:code-reviewer"`:
 
 - Read `quality-reviewer-prompt.md` from this skill directory
 - Fill placeholders:
@@ -101,7 +99,7 @@ Dispatch using `Task` tool with `subagent_type="superpowers:code-reviewer"`:
   - `{ISSUE_CONTEXT}` -> full issue title + body (or "No linked issue found.")
 - Prompt = filled template
 
-**Both subagents must be dispatched in parallel** (single message, two Task tool calls).
+**Both subagents must be dispatched in parallel** (single message with two Agent tool calls — use `run_in_background: true` on one, foreground on the other, then read the background result with `TaskOutput`).
 
 ## Step 4: Collect and Address Findings
 

.claude/skills/review-implementation/structural-reviewer-prompt.md

@@ -30,7 +30,7 @@ Given: problem name `P` = `{PROBLEM_NAME}`, category `C` = `{CATEGORY}`, file st
 | 2 | `inventory::submit!` present | `Grep("inventory::submit", file)` |
 | 3 | `#[derive(...Serialize, Deserialize)]` on struct | `Grep("Serialize.*Deserialize", file)` |
 | 4 | `Problem` trait impl | `Grep("impl.*Problem for.*{P}", file)` |
-| 5 | `OptimizationProblem` or `SatisfactionProblem` impl | `Grep("(OptimizationProblem\|SatisfactionProblem).*for.*{P}", file)` |
+| 5 | `OptimizationProblem` or `SatisfactionProblem` impl | `Grep("(OptimizationProblem|SatisfactionProblem).*for.*{P}", file)` |
 | 6 | `#[cfg(test)]` + `#[path = "..."]` test link | `Grep("#\\[path =", file)` |
 | 7 | Test file exists | `Glob("src/unit_tests/models/{C}/{F}.rs")` |
 | 8 | Test has creation test | `Grep("fn test_.*creation\|fn test_{F}.*basic", test_file)` |