adk-docs
guidelines for creating, reviewing, updating, and searching ADK documentation - use when users ask about writing, maintaining, or auditing ADK bot docs
What this skill does
# ADK Documentation Management
Use this skill when helping users create, review, update, or maintain documentation for their ADK projects. Users write guides and docs for their own bots and features — code examples should come from their project and the official ADK repo.
## When to Use This Skill
Activate this skill when users:
- Want to create documentation for their bot ("Document my order workflow", "Write a guide for my custom actions")
- Need to review existing project docs for accuracy ("Check if my docs are still correct")
- Want to update docs after changing their bot ("I refactored the checkout flow, update the docs")
- Need to check if docs are in sync with their code ("Are my docs current?")
- Want to search their project documentation ("Find docs about my payment handler")
- Ask about documentation standards or templates
- Mention `/adk-document`
## Available Documentation
| File | Description |
|------|-------------|
| [references/doc-standards.md](./references/doc-standards.md) | Document types, templates, quality checklists, and health metrics |
## Available Commands
| Command (and suggested subcommand) | Description |
|---------|-------------|
| `/adk-document create [topic]` | Create documentation for a feature in the user's bot |
| `/adk-document review [doc-path]` | Review project docs for accuracy and completeness |
| `/adk-document update [doc-path] [what-changed]` | Update project docs after code changes |
| `/adk-document sync [optional-doc-path]` | Check if project docs are in sync with the bot's code |
| `/adk-document search [search-term]` | Search project documentation for specific topics |
## Shared Principles
### 1. AI-Optimized Structure
- Clear section headers (`##`, `###`, `####`) so ripgrep can find sections
- Table of contents at top with anchor links
- Right-sized for document type (see doc-standards reference)
- Keyword-rich section names — no vague "Advanced Topics" or "Other"
### 2. Code-First Approach
- Every concept needs a working code example from actual project code
- Include file paths with line numbers for verification
- Primary sources for examples (in priority order):
1. The user's own ADK project (look for `agent.config.ts` in the workspace) — BEST
2. The official ADK repo examples (clone or find locally)
3. ADK runtime usage (`@botpress/runtime` packages)
- Never invent or speculate examples — all code must be verifiable
### 3. Critical Distinctions
- ADK primitives (from `@botpress/runtime`) vs Botpress SDK primitives
- `this.send()` in conversations vs `client.createMessage()` in workflows
- Messages (persistent, stored) vs Events (ephemeral, not stored)
- Agnostic APIs vs channel-specific features
### 4. No Speculation
- Do NOT add Common Mistakes or Best Practices sections unless the user explicitly provides them
- Use `❌ WRONG` / `✅ CORRECT` only when documenting actual reported errors
- Workflows and examples must be verified from actual code, not imagined
### 5. Writing Style
- **Direct and actionable** — "Use `this.send()`" not "You might want to consider..."
- **Technically accurate** — test examples against actual ADK code
- **Assumes intelligence** — provide context and guidance, not hand-holding
- **No marketing fluff** — straight to the technical substance
## How to Answer
When a user asks about documentation without invoking a specific command:
1. **Load the `adk` skill (& more, if needed)** for ADK context and knowledge
2. **Identify what they need** — creating, reviewing, updating, syncing, or searching
3. **Point them to the right command** or help directly using the principles above
4. **Reference doc-standards** for template and quality guidance
## Documentation Location
Documentation is written in the user's own project. Ask the user where they want docs saved if not obvious (common locations: `./docs/`, `./guides/`, or project root).
## Discovering Code Sources
Discover the user's project and the official ADK repo for examples:
```javascript
// Find ADK projects in the workspace
Glob({ pattern: "**/agent.config.ts" })
// Find ADK runtime usage in the user's project
Grep({ pattern: "from ['\"]@botpress/runtime", output_mode: "files_with_matches" })
// Look for existing project documentation
Glob({ pattern: "./{docs,guides}/**/*.md" })
// Find official ADK examples if available locally
Glob({ pattern: "**/adk/examples/**/*.ts" })
```
## Cross-References
- **`adk` skill** — Core ADK knowledge (actions, workflows, conversations, etc.)
- **`adk-evals` skill** — Testing and eval documentation
- **`adk-frontend` skill** — Frontend integration documentation
- **`adk-integrations` skill** — Integration lifecycle documentation
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.