document
Generate structured code documentation for files, services, or modules.
Skill by twlines
Chalk Labs
Need help deploying document?
Chalk Labs sets up agents like this inside real teams: connected to your tools, tested on your data, with a human in the loop where it matters.
Install
Works with Claude Code, Claude apps, Codex, Cursor, Gemini CLI, GitHub Copilot, VS Code, OpenCode, Goose, Windsurf. Read the repository before you give any tool access to your data.
npx agentmarket install skill/twlines-document
Asks which of your tools to add it to (Claude Code, Codex, Cursor, VS Code, Windsurf, Gemini CLI, Claude Desktop) and shows the change first. See https://agentmart.dev/cli.
Get the weekly diff
The weekly diff: one email a week with new agent tools, notable updates and grade changes, plus security alerts for tools you follow. Double opt-in, one-click unsubscribe.
About
Use cases: documents, backend
Reviews
Write a reviewNo reviews yet. Installed it? Reviews come from verified installers only. How reviews work
Permissions
What this skill can do and what it asks for, from its SKILL.md. Checked Oct 25, 2026.
- Tools
- No tools found
- Secrets
- None asked for
- Install scripts
- None found
Network hosts it talks to 1
codeload.github.com· found in install command
Files it touches
~/.claude/skills/document
What's inside
- Skill name
document- Description
- Generate structured code documentation for files, services, or modules. Use when the user asks to document code, understand a module, generate API docs, or wants a reference for a service. Invoke with /document <path-or-module-name>.
- License
- MIT
- Instructions
- 99 lines in SKILL.md · view on GitHub
Files (1)
- SKILL.md
SKILL.md (first lines)
# Code Documentation Generator
Generate structured, accurate documentation for Maslow codebase modules. Documentation is derived from reading the actual code — never fabricated.
## Workflow
1. **Identify the target** — file path, service name, or module directory
2. **Read all relevant source files** — the target and its direct dependencies
3. **Analyze** — extract the API surface, data flow, dependencies, and patterns
4. **Generate documentation** — write structured markdown following the template below
5. **Output** — print the documentation to the conversation (do NOT write files unless explicitly asked)
## Output Template
Generate documentation following this structure:
```markdown
# <Module Name>
> One-sentence purpose.
## Overview
2-3 sentences explaining what this module does, why it exists, and where it sits in the architecture.
## API Surface
### Public Interface
For each exported function/method/class:
- **`methodName(params): ReturnType`** — what it does (one line)
### Configuration
Environment variables, config keys, or constructor options this module depends on.
## Data Flow
How data moves through this module — what comes in, what goes out, what side effects occur.
Use a simple arrow diagram if helpful:
```
Input → Transform → Output
↓
Side Effect
```
## Dependencies
| Dependency | Why |
|-----------|-----|
| ServiceName | Brief reason |
## Database Schema (if applicable)
Tables, columns, indexes this module owns or queries.
## Error Handling
How errors are surfaced — Effect error channel types, fallback behavior, retry logic.
## Gotchas
Bullet list of non-obvious behaviors, footguns, or constraints a developer should know.
## Example Usage
```typescript
// Minimal working example showing how to use this module
```
```
## Rules
- **Read before documenting** — never guess at APIs or behavior. Read the source.
- **Be precise** — use actual type names, actual method signatures. No placeholders.
- **Skip empty sections** — if a module has no database schema, omit that section entirely.
- **Effect-TS aware** — document `Effect.Effect<A, E>` signatures with both success and error channels. Note `Layer` dependencies.
- **Concise** — this is reference material, not a tutorial. One line per method unless complexity demands more.
- **Link to source** — reference file paths with line numbers for key definitions (e.g., `src/services/Kanban.ts:42`).
## Scope Handling
| Input | Action |
|-------|--------|
| File path (e.g., `src/services/Kanban.ts`) | Document that single file |
| Service name (e.g., `Kanban`) | Find and document the service file |
| Directory (e.g., `packages/shared`) | Document the module: index exports, key files, package purpose |
| `all` or `full` | Generate a high-level architecture doc covering all services and their relationships |
## Architecture Context
This codebase follows the Effect-TS service layer pattern:
- Services are defined as `Context.Tag` with a service interface
- Implementations are `Layer.effect` or `Layer.scoped` (for resources with finalizers)
- Layer composition order matters — see CLAUDE.md for the dependency graph
- Boundary rules: `apps/*` → `packages/*` only, `src/` → `packages/*` onlyFrom twlines/maslow, MIT.
More from twlines/maslow
- 0.409score
effect-service
twlines
Scaffold a new Effect-TS service following Maslow's Context.Tag + Layer pattern.
SkillDFreshness: DClaude Code +9 - 0.409score
maslow-audit
twlines
Run architecture, security, and code quality audits on the Maslow codebase.
SkillDFreshness: DClaude Code +9 - 0.409score
wire-feature
twlines
Scaffold and wire a full-stack feature across server, shared types, and client.
SkillDFreshness: DClaude Code +9 - 0.404score
refactor-patterns
twlines
Safe refactoring patterns for moves, renames, and extractions
SkillDFreshness: DClaude Code +9 - 0.404score
conversation-context
twlines
How to use prior decisions and daily logs before starting work
SkillDFreshness: DClaude Code +9 - 0.401score
effect-conventions
twlines
Effect-TS patterns and anti-patterns for Maslow codebase
SkillDFreshness: DClaude Code +9 - 0.401score
pr-preparation
twlines
Commit and PR preparation standards for agent output
SkillDFreshness: DClaude Code +9 - 0.401score
schema-to-service
twlines
End-to-end pipeline for adding a new entity to Maslow
SkillDFreshness: DClaude Code +9 - 0.401score
effect-testing
twlines
Effect-TS testing patterns with Vitest
SkillDFreshness: DClaude Code +9 - 0.401score
error-diagnosis
twlines
Common failure patterns and fixes in the Maslow codebase
SkillDFreshness: DClaude Code +9 - 0.401score
git-worktree
twlines
Git worktree isolation rules for agent execution
SkillDFreshness: DClaude Code +9 - 0.401score
import-conventions
twlines
Import path and module boundary rules
SkillDFreshness: DClaude Code +9
Signals
- Stars
- 0
- Forks
- 0
- Open issues
- 0
- Last commit (this folder)
- Feb 13, 2026 (8 months ago)
From GitHub (fetched Oct 24, 2026).
Details
- License
- MIT
- Repository
- github.com/twlines/maslow
- First seen
- Oct 24, 2026
- Last checked
- Oct 24, 2026
- Source
- GitHubgithub-graphql
More from twlines
- 0.409score
maslow-audit
twlines
Run architecture, security, and code quality audits on the Maslow codebase.
SkillDFreshness: DClaude Code +9 - 0.409score
wire-feature
twlines
Scaffold and wire a full-stack feature across server, shared types, and client.
SkillDFreshness: DClaude Code +9 - 0.409score
effect-service
twlines
Scaffold a new Effect-TS service following Maslow's Context.Tag + Layer pattern.
SkillDFreshness: DClaude Code +9 - 0.404score
refactor-patterns
twlines
Safe refactoring patterns for moves, renames, and extractions
SkillDFreshness: DClaude Code +9 - 0.404score
conversation-context
twlines
How to use prior decisions and daily logs before starting work
SkillDFreshness: DClaude Code +9 - 0.401score
sql-migration
twlines
SQLite schema and migration patterns for Maslow
SkillDFreshness: DClaude Code +9
Done for you
Rather not set it up yourself?
Chalk Labs scopes, builds and runs agents for your team: the task audit, the eval harness, the integrations and the weekly ops report. Fixed scope, priced before we start.
See how we build AI agents →Read the case studies
Chalk Labs is a two-founder AI and growth studio. We build AI agents, CRMs and MVPs for Web3 and AI companies, and have shipped 50+ product and token launches.
- launches shipped
- 50+
- launches shipped
- media placements
- 500+
- media placements
- founders on every account
- 2
- founders on every account
Press we've placed: Forbes · CoinDesk · Decrypt · Cointelegraph · The Block
Rahil Jain, Co-founder, Chalk Labs. Ex-Goldman Sachs engineer. You talk to the person who builds it.
Get document running in your business
Tell us what you want to automate. A founder replies within one working day with a plan, not a pitch deck.
Cite this page
document skill. Agent Mart. https://agentmart.dev/skills/twlines-document (last updated 2026-10-24)