plan-v2-extract-domain
Collaboratively identify and formalize an existing codebase concept as a named domain.
Skill by AI-Substrate
Chalk Labs
Need help deploying plan-v2-extract-domain?
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/ai-substrate-plan-v2-extract-domain
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
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/plan-v2-extract-domain
What's inside
- Skill name
plan-v2-extract-domain- Description
- Collaboratively identify and formalize an existing codebase concept as a named domain. No files are moved — this is about communication and traceability, not refactoring.
- License
- MIT
- Instructions
- 407 lines in SKILL.md · view on GitHub
Files (1)
- SKILL.md
SKILL.md (first lines)
Please deep think / ultrathink as this is a complex task. # extract-domain Collaboratively identify and formalize an existing codebase concept as a **named domain** without moving files. This is a workshop with the user, not an automated refactor. The goal is **communication** — future plans can reference "the auth domain" and everyone knows what that means. ```md User input: $ARGUMENTS # Expected: # <concept> — the concept to extract (e.g., "authentication", "billing") # Optional flags: # --domain <slug> — override the auto-generated slug # --list — list existing domains and exit ``` ## What This Command Does 1. **Explores** the codebase to discover all code related to the concept 2. **Catalogues** discovered files and their roles — presented to user for review 3. **Workshops** with user to define what belongs vs. doesn't (boundary) 4. **Identifies** public interfaces other code already consumes (contracts) 5. **Maps** internal components (services, adapters, repos — composition) 6. **Writes** `docs/domains/<slug>/domain.md` pointing to files where they currently live 7. **Updates** `docs/domains/registry.md` (creates it if first domain) ## What This Command Does NOT Do - ❌ Move files to a new directory structure - ❌ Refactor imports - ❌ Create new source directories - ❌ Change any code --- ## Step 0: List Mode If `--list` flag provided: - Read `docs/domains/registry.md` (if exists) - Display all registered domains with slug, type, status - If `docs/domains/domain-map.md` exists, show it too — the map gives the visual overview of how domains relate - If no registry exists, report "No domains registered yet" - Exit ## Step 1: Check for Existing Domain - Read `docs/domains/registry.md` if it exists - Read `docs/domains/domain-map.md` if it exists — understand the current domain topology, existing contract relationships, and where a new domain might fit - Check if a domain with matching slug already exists - If exists: report it and ask user whether to update or abort - Generate slug from concept: lowercase, replace spaces with hyphens, strip non-alphanumeric ## Step 2: Explore Launch 2 research subagents in parallel to discover code related to the concept: **Subagent 1: Code Discovery** "Find all code related to the concept '<concept>' in this codebase. Search for: - Services, handlers, controllers related to <concept> - Adapters wrapping external SDKs/APIs for <concept> - Repositories/data access for <concept> - Models, types, interfaces for <concept> - Configuration files for <concept> - Middleware, hooks, plugins for <concept> - Tests related to <concept> Output: List of files with suspected roles (service, adapter, repository, model, config, test, middleware, other)" **Subagent 2: Dependency & Contract Discovery** "Find how other parts of the codebase consume '<concept>' functionality. Search for: - Imports/requires from <concept>-related files - Public interfaces/classes that other modules depend on - Event channels, message queues related to <concept> - Shared types/contracts consumed externally Output: List of public interfaces with their consumers" ## Step 3: Present & Workshop Present discovered files to the user in a table: ``` I found these files related to "<concept>": | # | File | Suspected Role | Include? | |---|------|---------------|----------| | 1 | src/services/auth-service.ts | Service | ✅ | | 2 | src/middleware/jwt.ts | Middleware | ? | | 3 | src/models/user.ts | Model (shared?) | ? | | ... | ... | ... | ... | ``` Ask the user to confirm/adjust using the ask_user tool: 1. **For uncertain files**: "Should `<file>` be part of the `<concept>` domain, or does it belong elsewhere?" 2. **Boundary definition**: "What does this domain OWN vs. what does it NOT own?" 3. **Shared files**: "Some files serve multiple concepts. Should I note them as shared?" 4. **Contracts**: "These interfaces are consumed by other code — are they the right public surface?" **Key principle**: The agent proposes, the user decides. Domain boundary identification is a collaborative conversation. ## Step 3.5: Identify Concepts Group discovered contracts (from Subagent 2) into **named concepts** — consumer-facing capabilities that the domain offers. Each concept groups related contracts into one capability a consumer might search for. For each concept, identify: - **Concept name**: A verb phrase describing what consumers can do (e.g., "Subscribe to file changes", "Authenticate a user") - **Entry point**: The primary contract/function a consumer imports first - **What it does**: One sentence describing the capability **Grouping rules**: - Related contracts that serve one consumer use case = one concept - A single contract can be its own concept if it's independently useful - All concepts that a consumer might search for get a row — not limited to a "top 3"
From AI-Substrate/harness-engineering, MIT.
More from AI-Substrate/harness-engineering
- 0.529score
validate-v2
AI-Substrate
Adaptive, high-signal post-action validation for whatever was just produced — unified plan, tasks, code change, workshop, legacy spec, or any artifact.
SkillBFreshness: BClaude Code +9 - 0.525score
eng-harness-flow
AI-Substrate
Front door for the engineering-harness loop.
SkillBFreshness: BClaude Code +9 - 0.525score
builder
AI-Substrate
The single front door to the SDD pipeline (docs/plans/): research → product plan → implementation guide → tasks → implement → review → post-flight → ship.
SkillBFreshness: BClaude Code +9 - 0.524score
grill-agent-done
AI-Substrate
Interrogate and defend the definition of done and the evidence that will prove it — one claim at a time, until each claim is lined up against the right grade…
SkillBFreshness: BClaude Code +9 - 0.524score
eng-harness-in-a-box
AI-Substrate
The engineering-harness loop with zero dependencies — an engineering harness in a box.
SkillBFreshness: BClaude Code +9 - 0.524score
telemetry-insights-narrate
AI-Substrate
Route the LLM edge of the cohort-telemetry insights layer: turn a generated insights.json into short prose for the report's reserved narrator slot (narrator)…
SkillBFreshness: BClaude Code +9 - 0.524score
flow-eval-run
AI-Substrate
Start a peer-driven flow-conformance eval run with zero archaeology: pick or scaffold a scenario, spawn a BLIND subject peer to do the task, then score the…
SkillBFreshness: BClaude Code +9 - 0.521score
plan-0-v2-constitution
AI-Substrate
Establish or refresh the project constitution and align the supporting norms documents before any planning phases begin.
SkillBFreshness: BClaude Code +9 - 0.519score
the-flow
AI-Substrate
Backwards-compatible redirect for the SDD pipeline.
SkillBFreshness: BClaude Code +9 - 0.515score
eng-harness-0-harnessability-assessment
AI-Substrate
Assess a Git repository's harnessability — how easily a human or agent can enter, operate, modify, observe, prove, and improve it through an engineering…
SkillBFreshness: BClaude Code +9
Signals
- Stars
- 0
- Forks
- 0
- Open issues
- 42
- Last commit (this folder)
- Jul 6, 2026 (3 months ago)
- Last release
- Aug 30, 2026 (2 months ago)
From GitHub (fetched Oct 24, 2026).
Details
- License
- MIT
- First seen
- Oct 24, 2026
- Last checked
- Oct 24, 2026
- Source
- GitHubgithub-graphql
More from AI-Substrate
- 0.529score
validate-v2
AI-Substrate
Adaptive, high-signal post-action validation for whatever was just produced — unified plan, tasks, code change, workshop, legacy spec, or any artifact.
SkillBFreshness: BClaude Code +9 - 0.525score
eng-harness-flow
AI-Substrate
Front door for the engineering-harness loop.
SkillBFreshness: BClaude Code +9 - 0.525score
builder
AI-Substrate
The single front door to the SDD pipeline (docs/plans/): research → product plan → implementation guide → tasks → implement → review → post-flight → ship.
SkillBFreshness: BClaude Code +9 - 0.524score
grill-agent-done
AI-Substrate
Interrogate and defend the definition of done and the evidence that will prove it — one claim at a time, until each claim is lined up against the right grade…
SkillBFreshness: BClaude Code +9 - 0.524score
eng-harness-in-a-box
AI-Substrate
The engineering-harness loop with zero dependencies — an engineering harness in a box.
SkillBFreshness: BClaude Code +9 - 0.524score
telemetry-insights-narrate
AI-Substrate
Route the LLM edge of the cohort-telemetry insights layer: turn a generated insights.json into short prose for the report's reserved narrator slot (narrator)…
SkillBFreshness: BClaude 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 plan-v2-extract-domain 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
plan-v2-extract-domain skill. Agent Mart. https://agentmart.dev/skills/ai-substrate-plan-v2-extract-domain (last updated 2026-10-24)