update template

Author: GiggleLiu

.claude/CLAUDE.md

@@ -111,10 +111,6 @@ Reduction graph nodes use variant IDs: `ProblemName[/GraphType][/Weighted]`
 - Completeness warnings auto-check that all JSON graph nodes/edges are covered in the paper
 - `display-name` dict maps `ProblemName` to display text
 
-## Contributing
-See the sections below for detailed guides on adding reductions, models, tests, and documentation.
-Also see GitHub Issue #3 for coding rules.
-
 ## Adding a Reduction Rule (A -> B)
 
 **Reference implementations — read these first:**
@@ -126,11 +122,13 @@ Also see GitHub Issue #3 for coding rules.
 
 ### 0. Before Writing Code
 
-1. **Brainstorm** — use `superpowers:brainstorming` to discuss with the user:
-   - The math (variable mapping, constraint encoding, penalty terms)
-   - Which example instance to use in `examples/` (must be small, human-explainable, and agreed with the user)
-2. **Generate ground truth** — use Python scripts in `scripts/` (run with `uv`) to create test data in `tests/data/<target>/`.
-3. **Write plan** — save to `docs/plans/` using `superpowers:writing-plans`.
+1. **Ensure you have enough information**
+   - The reduction algorithm, from reliable source, e.g. a paper or a famous website.
+   - Which example instance to use in `examples/`, example is expected for human reading.
+   - The method to generate test data in `tests/data/<target>/` as json files.
+
+   otherwise use `superpowers:brainstorming` to discuss with the user.
+2. **Write plan** — save to `docs/plans/` using `superpowers:writing-plans`.
 
 ### 1. Implement
 

.claude/skills/issue-to-pr.md

@@ -56,10 +56,10 @@ Present issue summary to user.
 ### 3. Verify Issue Completeness
 
 Check that the issue template is fully filled out:
-- For **[Model]** issues: Definition, Variables, Instance Data, Objective, Type Parameters, Example
-- For **[Rule]** issues: Source, Target, Reference, Reduction mapping, Solution Extraction, Size Overhead, Example
+- For **[Model]** issues: A clear mathmatical definition, Type specification, Variables and fields, The complexity clarification, verify an existing solver can solve it, or a solving strategy is provided, A detailed example for human.
+- For **[Rule]** issues: Source, Target, Reference to verify information, Implementable reduction algorithm, Test dataset generation method, Size overhead, A clear example for human.
 
-If any section is missing or unclear, comment on the issue via `gh issue comment <number> --body "..."` asking the contributor to fill in the missing sections. Then stop and wait — do NOT proceed until the issue is complete.
+Verify facts provided by the user, feel free to ask user questions. If any piece is missing or unclear, comment on the issue via `gh issue comment <number> --body "..."` to ask user clarify. Then stop and wait — do NOT proceed until the issue is complete.
 
 ### 4. Research References
 

.github/ISSUE_TEMPLATE/problem.md

@@ -12,7 +12,8 @@ assignees: ''
 **Name:** <!-- e.g. MaximumIndependentSet. Use Maximum/Minimum prefix for optimization problems -->
 **Reference:** <!-- URL or citation for the formal definition -->
 
-<!-- Formal definition: input, feasibility constraints, and objective.
+<!--
+Formal definition: input, feasibility constraints, and objective.
 Define all symbols (e.g. G, V, E, S, K) before using them.
 
 E.g. "Given an undirected graph G=(V,E) where V is the vertex set and E is the edge set,
@@ -21,17 +22,21 @@ find S ⊆ V such that no two vertices in S are adjacent, maximizing |S|."
 
 ## Variables
 
-<!-- How the problem maps to a configuration vector x = (x_0, ..., x_{n-1}).
-Use symbols defined above. -->
+<!--
+How the problem maps to a configuration vector x = (x_0, ..., x_{n-1}).
+Use symbols defined above.
+-->
 
 - **Count:** <!-- e.g. n = |V| (one variable per vertex) -->
 - **Per-variable domain:** <!-- e.g. binary {0,1}, or {0,...,K-1} for K colors -->
 - **Meaning:** <!-- e.g. x_i = 1 if vertex i ∈ S (selected in independent set) -->
 
-## Schema
+## Schema (data type)
 
-<!-- Describe the data fields that define a problem instance.
-Connect fields to the symbols defined above. -->
+<!--
+Describe the data fields that define a problem instance.
+Connect fields to the symbols defined above.
+-->
 
 **Type name:** <!-- e.g. MaximumIndependentSet -->
 **Variants:** <!-- e.g. graph topology (SimpleGraph, GridGraph, UnitDiskGraph), weighted or unweighted -->
@@ -47,9 +52,20 @@ Connect fields to the symbols defined above. -->
 - **Best known exact algorithm:** <!-- e.g. O(1.1996^n) by Xiao & Nagamochi (2017), where n = |V| -->
 - **Best known approximation:** <!-- e.g. no PTAS unless P=NP; or 2-approximation via greedy -->
 
+## How to solve
+<!--
+Solver is required for reduction rule verification purpose.
+- Can it be solved by (existing) bruteforce?
+- Can it be solved by reducing the integer programming? If so, how to reduce?
+- If none apply
+-->
+
 ## Example Instance
 
-<!-- A small but non-trivial instance with known optimal solution, for testing and the paper.
+<!--
+A small but non-trivial instance with known optimal solution, for testing and the paper.
 Should be large enough to exercise the problem's constraints meaningfully (avoid trivial cases like triangle graphs).
-E.g. "Petersen graph: |V|=10, |E|=15, 3-regular. Optimal IS size = 4."
+E.g. "Petersen graph: |V|=10, |E|=15, 3-regular. Optimal IS size = 4, and more details.."
+
+This example will be shown in our paper, where you could find some references.
 -->

.github/ISSUE_TEMPLATE/rule.md

@@ -46,8 +46,10 @@ E.g.
 ## Example Source Instance
 
 <!-- A small but non-trivial source instance for the paper illustration.
-Must be small enough for brute-force solving, but large enough to exercise the reduction meaningfully.
-Only provide the source — the example code auto-generates the target instance, solutions, and JSON.
+Must be small enough for brute-force solving, but large enough to exercise the reduction meaningfully. E.g. "petersen graph: |V|=10, |E|=15, 3-regular" should be perfect.
+Please provide as many details as possible, because
+1. this example will appear in the paper.
+2. AI needs this information to generate example code, run it, and try to compare with what you provided.
 
-E.g. "Petersen graph: |V|=10, |E|=15, 3-regular"
+Please check existing examples in our paper for references.
 -->