diff --git a/.github/ISSUE_TEMPLATE/bug_report.md b/.github/ISSUE_TEMPLATE/bug_report.md
index bdce7faabb49c4c058c632f1fe1e7b00163bd509..a7cbfda00ec2345b6e2813e8fe22d7db0ea0388b 100644
--- a/.github/ISSUE_TEMPLATE/bug_report.md
+++ b/.github/ISSUE_TEMPLATE/bug_report.md
@@ -20,5 +20,8 @@ Steps to reproduce the behavior:
 **Expected behavior**
 A clear and concise description of what you expected to happen.
 
+**Actual behavior**
+A clear and concise description of the actual results.
+
 **Additional context**
 Add any other context about the problem here.
diff --git a/.github/PULL_REQUEST_TEMPLATE/add_datasets.md b/.github/PULL_REQUEST_TEMPLATE/add_datasets.md
new file mode 100644
index 0000000000000000000000000000000000000000..dfb3ea10fe1c3604af9d8e9c2e83fb95c01bf146
--- /dev/null
+++ b/.github/PULL_REQUEST_TEMPLATE/add_datasets.md
@@ -0,0 +1,16 @@
+- **Name:** *name of the dataset*
+- **Description:** *short description of the dataset (or link to social media or blog post)*
+- **Paper:** *link to the dataset paper if available*
+- **Data:** *link to the Github repository or current dataset location*
+- **License:** *what is the license of the dataset*
+- **Motivation:** *what are some good reasons to have this dataset*
+
+
+### Checkbox
+
+- [ ] Create `data/unified_datasets/$dataset_name` folder, where `$dataset_name` is the name of the dataset.
+- [ ] Create the dataset scripts under `data/unified_datasets/$dataset_name` following `data/unified_datasets/README.md`.
+- [ ] Run `python check.py $dataset` in the `data/unified_datasets` directory to check the validation of processed dataset and get data statistics and shuffled dialog ids.
+- [ ] Add the dataset card `data/unified_datasets/$dataset_name/README.md` following `data/unified_datasets/README_TEMPLATE.md`.
+- [ ] Upload the data, scripts, and dataset card to https://huggingface.co/ConvLab
+- [ ] Update `NOTICE` with license information.
diff --git a/.github/PULL_REQUEST_TEMPLATE/add_model.md b/.github/PULL_REQUEST_TEMPLATE/add_model.md
new file mode 100644
index 0000000000000000000000000000000000000000..387b02441605ff07c4e9c27e4b7e2f1989d1361e
--- /dev/null
+++ b/.github/PULL_REQUEST_TEMPLATE/add_model.md
@@ -0,0 +1,15 @@
+- **Name:** *name of the model*
+- **Description:** *short description of the model (or link to social media or blog post)*
+- **Paper:** *link to the model paper if available*
+- **Repo:** *link to the Github repository of official implementation*
+- **License:** *what is the license of the code*
+- **Motivation:** *what are some good reasons to have this model*
+
+
+### Checkbox
+
+- [ ] The model supports unified data format and provides training scripts.
+- [ ] The model has implemented module interface and can be used to build an agent (Add examples in `agent_examples`).
+- [ ] Add the model card `README` under its directory.
+- [ ] Upload the checkpoints, and model card to https://huggingface.co/ConvLab
+- [ ] Update `NOTICE` with license information.
diff --git a/PULL_REQUEST_TEMPLATE.md b/.github/PULL_REQUEST_TEMPLATE/custom.md
similarity index 100%
rename from PULL_REQUEST_TEMPLATE.md
rename to .github/PULL_REQUEST_TEMPLATE/custom.md
diff --git a/.github/PULL_REQUEST_TEMPLATE/fix_bug.md b/.github/PULL_REQUEST_TEMPLATE/fix_bug.md
new file mode 100755
index 0000000000000000000000000000000000000000..719d39e99e66d74511ddddeb83204d7f8d9fee8b
--- /dev/null
+++ b/.github/PULL_REQUEST_TEMPLATE/fix_bug.md
@@ -0,0 +1,23 @@
+**Describe the bug**
+A clear and concise description of what the bug is.
+
+**To Reproduce**
+Steps to reproduce the behavior:
+1. Go to '...'
+2. Click on '....'
+3. Scroll down to '....'
+4. See error
+
+**Expected behavior**
+A clear and concise description of what you expected to happen.
+
+**Actual behavior**
+A clear and concise description of the actual results.
+
+**Additional context**
+Add any other context about the problem here.
+
+**How to fix**
+Changes made to fix the bug.
+
+**Reference Issues:** #XX (XX is the issue number you work on)