explain
Document the reasoning behind implementation decisions as markdown files. Creates decision records that future developers can reference.
What this skill does
# Explain (Decision Documentation)
Create decision records that document the reasoning behind implementation choices.
## Philosophy
Good code is self-documenting for *what* it does. But *why* it does it that way? That's lost to time unless we capture it.
> "Six months from now, when someone asks 'Why did we do it this way?', will there be an answer?"
The value of this skill isn't compliance—it's **preserving context** that makes the codebase maintainable.
## Config Integration
Follow the migration preflight in `references/config-migration.md`, then check for `.assistant-config.md` in the project root.
**Decisions location** (in order of precedence):
1. `Decisions location` setting in config
2. Existing `decisions/` directory
3. Existing `docs/decisions/` or `docs/adr/` directory
4. Default: create `decisions/`
If no config exists, ask the user where to store decisions or use the default.
## When to Use
Run `/explain` after:
- Completing a significant implementation
- Making an architectural decision
- Choosing between multiple valid approaches
- Implementing something counterintuitive
- When future developers might ask "why was it done this way?"
## Input
The user will provide:
- File path(s) to explain, OR
- Feature/change description, OR
- Specific question ("Why did we use X instead of Y?")
If nothing provided, explain recent uncommitted changes.
## Process
### 1. Understand the Decisions
For the code being explained, identify:
- Key architectural choices
- Algorithm or pattern selections
- Library/dependency choices
- Trade-offs that were made
- Constraints that influenced the approach
### 2. Research Context
Gather context before writing:
- What patterns exist elsewhere in the codebase?
- Were there constraints from existing code?
- What does the task file or PR description say?
- What alternatives could have been used?
### 3. Generate File Name
Use the pattern: `NNNN-short-description.md`
- Check existing files in decisions directory
- Use next available number (0001, 0002, etc.)
- Keep description short (2-4 words, kebab-case)
Examples:
- `0001-use-zustand-for-state.md`
- `0002-jwt-over-sessions.md`
- `0003-monorepo-structure.md`
### 4. Write Decision Record
Create the file in the decisions directory.
## Output Format
```markdown
# [Number]. [Decision Title]
**Date**: [YYYY-MM-DD]
**Status**: Accepted
**Context**: [What prompted this decision]
## Decision
[1-2 sentence summary of what was decided]
## Why This Approach
- [Primary reason]
- [Secondary reason]
- [Constraint that influenced this]
## Alternatives Considered
### [Alternative A]
**Pros**: [benefits]
**Cons**: [drawbacks]
**Why not**: [specific reason rejected]
### [Alternative B]
**Pros**: [benefits]
**Cons**: [drawbacks]
**Why not**: [specific reason rejected]
## Trade-offs Accepted
- [What we gave up and why it's acceptable]
## Consequences
- [What this decision means for future development]
- [Things to watch out for]
## Related
- [Links to related code, PRs, or other decisions]
```
## After Writing
Output confirmation:
```markdown
## Decision Record Created
**File**: `decisions/0003-use-zustand-for-state.md`
### Summary
Documented decision to use Zustand over Redux for state management.
### Key Points
- Simpler API reduces boilerplate
- Trade-off: Less ecosystem tooling
- Revisit if: Complex state debugging needed
```
## Why This Matters
Decision records serve multiple purposes:
- **Onboarding**: New developers understand architectural choices
- **Maintenance**: Future changes can respect original constraints
- **Accountability**: Decisions are traceable and reviewable
- **Learning**: The team builds shared understanding over time
Without this context, teams make the same decisions repeatedly, or worse—undo good decisions because they don't understand why they were made.
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.