kata-customize
Manage template overrides for customizing Kata output formats. List available templates, copy defaults for local editing, edit overrides, validate template schemas. Triggers include "customize template", "override template", "edit template", "template overrides", "list templates", "show templates", "template customization", "manage templates", "what templates can I customize", "template schema", "custonmize Kata", "custom config".
What this skill does
<objective>
Manage template overrides for customizing Kata output formats.
Templates control the structure of planning artifacts (plans, summaries, UAT sessions, verification reports, changelogs). Override a template to change how Kata generates these files for your project.
Operations: list, copy, edit, validate.
</objective>
<context>
$ARGUMENTS
</context>
<process>
## 1. Validate Environment
```bash
ls .planning/ 2>/dev/null
```
**If not found:** Error — run `/kata-new-project` first.
## 2. Determine Operation
Parse `$ARGUMENTS` for the operation:
- If contains "list" or "show" or no arguments → **list** operation
- If contains "copy" → **copy** operation (extract template name from remaining args)
- If contains "edit" or "modify" or "change" → **edit** operation (extract template name)
- If contains "validate" or "check" or "drift" → **validate** operation
If unclear, present AskUserQuestion:
```
What would you like to do?
1. **List templates** — See all customizable templates and their override status
2. **Copy a template** — Copy a default template for local customization
3. **Edit a template** — Modify an existing template override
4. **Validate overrides** — Check all overrides for missing required fields
```
## 3. List Operation
Run the discovery script:
```bash
bash "${CLAUDE_PLUGIN_ROOT}/skills/kata-customize/scripts/list-templates.sh"
```
Parse the JSON output. Display:
```
━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━
Kata > CUSTOMIZABLE TEMPLATES
━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━
| Template | Used By | Controls | Status |
| --- | --- | --- | --- |
| summary-template.md | kata-execute-phase | Phase completion docs | {override / default} |
| plan-template.md | kata-plan-phase | Phase plan structure | {override / default} |
| UAT-template.md | kata-verify-work | UAT session format | {override / default} |
| verification-report.md | kata-verify-work | Verification report format | {override / default} |
| changelog-entry.md | kata-complete-milestone | Changelog entry format | {override / default} |
Override location: `.planning/templates/`
To customize a template:
`/kata-customize copy summary-template.md`
```
After displaying the list, stop. Do not proceed to another operation.
## 4. Copy Operation
Requires a template name argument. If not provided, run list operation first, then ask user to select.
**Step 4a: Resolve the default template path**
```bash
DEFAULT_PATH=$(node "${CLAUDE_PLUGIN_ROOT}/skills/kata-customize/scripts/kata-lib.cjs" resolve-template "$TEMPLATE_NAME" 2>&1)
```
If the resolve script exits non-zero, the template name is invalid. Display the error and stop.
**Step 4b: Check for existing override**
```bash
[ -f ".planning/templates/$TEMPLATE_NAME" ] && echo "EXISTS" || echo "NEW"
```
If EXISTS, ask user via AskUserQuestion:
```
An override for `{TEMPLATE_NAME}` already exists at `.planning/templates/{TEMPLATE_NAME}`.
1. **Overwrite** — Replace with default (your customizations will be lost)
2. **Cancel** — Keep current override
```
If user selects Cancel, stop.
**Step 4c: Copy the default**
```bash
mkdir -p .planning/templates
cp "$DEFAULT_PATH" ".planning/templates/$TEMPLATE_NAME"
```
**Step 4d: Confirm**
```
━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━
Kata > TEMPLATE COPIED
━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━
Copied default to: `.planning/templates/{TEMPLATE_NAME}`
Edit the file to customize, then validate:
`/kata-customize validate`
```
## 5. Edit Operation
Requires a template name argument. If not provided, run list operation to show overrides, then ask which to edit.
**Step 5a: Check override exists**
```bash
[ -f ".planning/templates/$TEMPLATE_NAME" ] && echo "EXISTS" || echo "MISSING"
```
If MISSING, ask user via AskUserQuestion:
```
No override exists for `{TEMPLATE_NAME}`.
1. **Copy and edit** — Copy the default first, then edit
2. **Cancel** — Do nothing
```
If user selects "Copy and edit", run step 4c first.
**Step 5b: Read current content**
Read `.planning/templates/{TEMPLATE_NAME}` and display the current content to the user.
**Step 5c: Accept modifications**
Ask the user what they want to change. Two paths:
- If user describes specific changes ("change heading X to Y", "add field Z"), apply the edits to the file using Edit tool and write the updated content.
- If user says they will edit externally ("let me edit it", "I'll do it in my editor"), acknowledge and offer to validate when they return.
**Step 5d: Validate after edit**
After writing changes (or when user returns from external editing), run single-template validation:
```bash
node "${CLAUDE_PLUGIN_ROOT}/skills/kata-customize/scripts/kata-lib.cjs" check-template-drift
```
If drift warnings mention the edited template, display them. If clean, display:
```
━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━
Kata > TEMPLATE VALID
━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━
`{TEMPLATE_NAME}` has all required fields. Override is active.
```
## 6. Validate Operation
Run validation on all overrides:
```bash
DRIFT_OUTPUT=$(node "${CLAUDE_PLUGIN_ROOT}/skills/kata-customize/scripts/kata-lib.cjs" check-template-drift 2>/dev/null)
```
If `DRIFT_OUTPUT` is empty and `.planning/templates/` exists with .md files:
```
━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━
Kata > ALL TEMPLATES VALID
━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━
All template overrides pass schema validation.
```
If `DRIFT_OUTPUT` is empty and no overrides exist:
```
━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━
Kata > NO OVERRIDES
━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━
No template overrides found at `.planning/templates/`.
To create an override:
`/kata-customize copy summary-template.md`
```
If `DRIFT_OUTPUT` has content (warnings):
```
━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━
Kata > TEMPLATE DRIFT DETECTED
━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━
{DRIFT_OUTPUT}
To fix, edit the override or reset to default:
`/kata-customize edit {template-name}`
`/kata-customize copy {template-name}` (resets to default)
```
</process>
<success_criteria>
- [ ] Templates listed with descriptions and override status
- [ ] Default copied to .planning/templates/ with overwrite protection
- [ ] Edit operation reads current content and applies user changes
- [ ] Validation runs after edit and reports missing fields
- [ ] All operations use existing infrastructure (kata-lib.cjs resolve-template, kata-lib.cjs check-template-drift)
- [ ] Skill responds to natural language triggers
</success_criteria>
Related 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.