template-builder
Interactive guided wizard for creating GitHub issue templates, PR templates, and discussion templates. Answer simple questions and get production-ready YAML templates -- no manual YAML writing required.
What this skill does
Derived from `.claude/agents/template-builder.md`. Treat platform-specific tool names or delegation instructions as Codex equivalents.
## Authoritative Sources
- **GitHub Issue Templates** — https://docs.github.com/en/communities/using-templates-to-encourage-useful-issues-and-pull-requests/configuring-issue-templates-for-your-repository
- **GitHub Pull Request Templates** — https://docs.github.com/en/communities/using-templates-to-encourage-useful-issues-and-pull-requests/creating-a-pull-request-template-for-your-repository
- **GitHub Discussion Templates** — https://docs.github.com/en/discussions/managing-discussions-for-your-community/creating-discussion-category-forms
# Template Builder Agent
[Shared instructions](shared-instructions.md)
**Skills:** [`github-workflow-standards`](../skills/github-workflow-standards/SKILL.md), [`github-scanning`](../skills/github-scanning/SKILL.md)
A magical interactive agent that guides you through building GitHub issue templates step-by-step using VS Code's Ask Questions feature. Instead of writing YAML, answer simple questions and the agent generates the template for you.
# Template Builder Agent
[Shared instructions](../../.github/agents/shared-instructions.md)
**Skills:** [`github-workflow-standards`](../../.github/skills/github-workflow-standards/SKILL.md), [`github-scanning`](../../.github/skills/github-scanning/SKILL.md)
A magical interactive agent that guides you through building GitHub issue templates step-by-step using VS Code's Ask Questions feature. Instead of writing YAML, answer simple questions and the agent generates the template for you.
## How to Use
### In VS Code
1. Open Copilot Chat (`Ctrl+Shift+I` Windows, `Cmd+Shift+I` macOS)
2. Type: `@template-builder` or `/build-template`
3. The agent will ask you a series of questions to understand your template
4. Answer each question in the Ask Questions prompts
5. The agent generates your complete YAML template
6. Copy the output to `.github/ISSUE_TEMPLATE/your-template-name.yml`
### In GitHub Web
1. Open Copilot Chat (Copilot button in top right)
2. Mention: `@template-builder`
3. Type your template goals (e.g., "I want to build an accessibility bug report template")
4. The agent provides step-by-step YAML scaffolding you can copy and refine
## Example Workflow
**You:** `@template-builder create accessibility bug template`
**Agent asks (via Ask Questions):**
1. Template name? -> You answer: "Accessibility Bug Report"
2. What's this template for? -> "Report screen reader and keyboard issues"
3. First field? -> "Screen Reader (dropdown)"
4. Dropdown options? -> "NVDA, JAWS, VoiceOver, Other"
5. Is it required? -> "Yes"
6. Next field? -> "Browser (dropdown)"
... (continues for each field)
**Agent outputs:** Complete YAML template ready to paste
---
## Template Builder Guide: Step-by-Step
### Phase 1: Gather Template Metadata
The agent starts by asking core questions about your template:
**Questions:**
- What is the template name? (e.g., "Bug Report", "Feature Request", "Accessibility Issue")
- One-line description of this template's purpose
- Default title prefix for issues (e.g., "[BUG]", "[A11Y]", "[FEAT]")
- What labels should this template auto-apply? (comma-separated)
**Agent generates:**
```yaml
name: Your Template Name
description: Your description
title: "[TAG] "
labels: ["label1", "label2"]
```
---
### Phase 2: Build Form Fields Interactively
The agent walks through adding fields one-by-one:
**Questions for each field:**
1. Field type? -> Show options:
- `markdown` (instructional text)
- `input` (single-line text)
- `textarea` (multi-line text)
- `dropdown` (select from options)
- `checkboxes` (multiple selections)
2. Field label? (required)
3. Help text / description? (optional)
4. Is this field required? (yes/no)
5. For `textarea`: Should code highlighting be enabled? (markdown, python, javascript, etc.)
6. For `dropdown`: What are the options? (comma-separated or one per line)
7. For `dropdown`: Can user select multiple? (yes/no)
8. Another field? (yes/no)
**Agent generates field YAML:**
```yaml
- type: dropdown
id: screen-reader
attributes:
label: Screen Reader
description: Which screen reader are you using?
options:
- NVDA
- JAWS
- VoiceOver
validations:
required: true
```
---
### Phase 3: Generate Complete Template
Once all fields are entered, the agent:
1. **Asks for final review:**
- "Does this capture all the information you need?"
- "Any fields to reorder or remove?"
2. **Generates the complete YAML:**
- Full frontmatter with all metadata
- All fields in order
- Proper validation setup
- Formatted and ready to copy
3. **Provides usage instructions:**
- Where to save the file (.github/ISSUE_TEMPLATE/your-name.yml)
- How to test it
- How to edit it later
- How to add it to the template chooser via config.yml
---
## Pre-Built Workflow: Guided Accessibility Template
The agent includes a guided workflow for the most common case: building an accessibility bug report template.
### Invoke with:
- `@template-builder` + "create accessibility template"
- `/build-a11y-template`
### Workflow:
The agent skips to Phase 2 but pre-populates it with accessibility-specific fields:
1. Component affected? (dropdown with agent names)
2. Screen reader (with NVDA, JAWS, VoiceOver, TalkBack, etc. pre-options)
3. Browser version
4. Operating system
5. Expected behavior vs actual behavior
6. Steps to reproduce
7. WCAG success criterion (dropdown with criteria)
8. Before submitting checklist (checkboxes for verification)
Output: Production-ready accessibility bug template you can immediately use.
---
## Advanced: Customize the Template Builder
The Template Builder agent itself can be extended. Students in the workshop can:
1. **Add new field types** -> Extend the agent to support custom validations
2. **Create workflow templates** -> Pre-built templates for specific issue types (Security, Documentation, etc.)
3. **Add conditional fields** -> Show/hide fields based on previous answers
4. **Export to markdown** -> Generate Markdown templates in addition to YAML
5. **Template sharing** -> Generate a code block to share with other projects
---
## Integration with Nexus
The Template Builder works alongside the five core agents:
| Agent | Creates | Template Builder Uses |
|-------|---------|----------------------|
| @daily-briefing | Issue summaries | Templates to collect consistent data |
| @issue-tracker | Issue recommendations | Templates to standardize issue quality |
| @pr-review | PR checklists | Templates to structure PR descriptions |
| @analytics | Performance insights | Templates to capture metrics consistently |
| @template-builder | Issue templates themselves | (This agent) |
**Together:** The five agents automate workflow; the Template Builder automates the infrastructure that makes workflows possible.
---
## Day 2 Amplifier: From Manual to Magical
| Day 1 | Day 2 in Browser | Day 2 in VS Code | Nexus |
|-------|------------------|------------------|------------|
| Learn to identify accessibility issues in code review | Learn to design templates that prevent those issues | Use Template Builder to generate templates interactively | Agent automates the entire cycle |
| (Chapter 14) | (Chapter 15) | (Chapter 16) | (Capstone) |
---
## Hands-On Exercise: Build Your Own Template Builder
During the workshop (Chapter 16), you will extend this agent:
### Exercise 1: Generate Your Project's Template
1. Open VS Code
2. Activate Copilot Chat
3. Type: `@template-builder` + describe your project's needs
4. Follow the Ask Questions flow
5. Save the generated YAML to your fork
### Exercise 2: Add a Workflow Variant
The base agent handles general templates. Add a `security-template` or `documentation-template` variant:
1. Open the Template Builder agent definition
2. Add a new slash command: `/build-securRelated in Writing & Docs
jax-development
IncludedUse this skill when the user is writing, debugging, profiling, refactoring, reviewing, benchmarking, parallelising, exporting, or explaining JAX code, or when they mention JAX, jax.numpy, jit, grad, value_and_grad, vmap, scan, lax, random keys, pytrees, jax.Array, sharding, Mesh, PartitionSpec, NamedSharding, pmap, shard_map, Pallas, XLA, StableHLO, checkify, profiler, or the JAX repo. It helps turn NumPy or PyTorch-style code into pure functional JAX, fix tracer/control-flow/shape/PRNG bugs, remove recompiles and host-device syncs, choose transforms and sharding strategies, inspect jaxpr/lowering/IR, and benchmark compiled code correctly.
nature-article-writer
IncludedDrafts, rewrites, diagnostically critiques, and style-calibrates primary research manuscripts for Nature and Nature Portfolio journals. Use when the user wants a Nature-style title, summary paragraph or abstract, introduction, results, discussion, methods, figure legends, presubmission enquiry, cover letter, reviewer response, or when a scientific draft sounds generic, jargon-heavy, structurally weak, or AI-ish and needs precise, broad-reader-friendly prose without inventing data, analyses, or references. Best for primary research articles and letters rather than reviews or press releases unless explicitly adapting one.
deckrd
IncludedDocument-driven framework that derives requirements, specifications, implementation plans, and executable tasks from goals through structured AI dialogue. Use when user says "write requirements", "create spec", "plan implementation", "derive tasks", "structure this feature", "break down into tasks", or "document this module". Also use for reverse engineering existing code into docs (/deckrd rev). Do NOT use for direct code writing — use /deckrd-coder after tasks are generated. Do NOT use when the user only wants to run or fix existing code without planning.
clinical-decision-support
IncludedGenerate professional clinical decision support (CDS) documents for pharmaceutical and clinical research settings, including patient cohort analyses (biomarker-stratified with outcomes) and treatment recommendation reports (evidence-based guidelines with decision algorithms). Supports GRADE evidence grading, statistical analysis (hazard ratios, survival curves, waterfall plots), biomarker integration, and regulatory compliance. Outputs publication-ready LaTeX/PDF format optimized for drug development, clinical research, and evidence synthesis.
handling-sf-data
IncludedSalesforce data operations with 130-point scoring. Use this skill to create, update, delete, bulk import/export, generate test data, and clean up org records using sf CLI and anonymous Apex. TRIGGER when: user creates test data, performs bulk import/export, uses sf data CLI commands, needs data factory patterns for Apex tests, or needs to seed/clean records in a Salesforce org. DO NOT TRIGGER when: SOQL query writing only (use querying-soql), Apex test execution (use running-apex-tests), or metadata deployment (use deploying-metadata).
accelint-ac-to-playwright
IncludedConvert and validate acceptance criteria for Playwright test automation. Use when user asks to (1) review/evaluate/check if AC are ready for automation, (2) assess if AC can be converted as-is, (3) validate AC quality for Playwright, (4) turn AC into tests, (5) generate tests from acceptance criteria, (6) convert .md bullets or .feature Gherkin files to Playwright specs, (7) create test automation from requirements. Handles both bullet-style markdown and Gherkin syntax with JSON test plan generation and validation.