Agent skill
setup-workspace
Configure workspace context and project settings
Install this agent skill to your Project
npx add-skill https://github.com/majiayu000/claude-skill-registry/tree/main/skills/other/other/setup-workspace-daemn256-workspace-repo-templ
SKILL.md
Setup Workspace
Uses Planner (primary) with Orchestrator support. Guide the creation or update of workspace-specific context. Detects project characteristics and gathers information needed for the agentic kernel to work effectively.
Prerequisites: Access to project root, project files exist (at minimum a README or package manifest)
Modes
Quick Start (Minimum Viable)
For fast setup, only needs:
- Project name and purpose
- Stack confirmation (auto-detected)
- Key documentation pointers
Comprehensive
For full setup, covers all sections in the workspace context schema.
Phase 1: Detection
Scan for Project Markers
- Look for
README.md - Check for package manifests (
package.json,*.csproj,pom.xml) - Look for
docs/ordocs/adr/directories - Scan for configuration files
- Report findings
Output
## Context Anchors
- **Phase:** 1 — Detection
## Detected Markers
| Marker | Found | Details |
| ------------------- | ------ | --------------- |
| README.md | Yes/No | <path> |
| Package manifest | Yes/No | <type and path> |
| docs/ directory | Yes/No | <structure> |
| Configuration files | Yes/No | <list> |
## Next Step
Confirm detection findings are correct.
**Approval Required:** Yes
⛔ CHECKPOINT
STOP. Do not proceed until human explicitly approves:
- Detection findings are correct
- No important markers were missed
Phase 2: Stack Inference
Classify Technology
- Classify backend technology
- Classify frontend technology
- Identify documentation structure
- Report inference
Stack Categories
| Layer | Options |
|---|---|
| Backend | .NET / Node / Java / Python / None |
| Frontend | Angular / React / Vue / None |
| Docs | ADR structure / Custom / None |
Output
## Context Anchors
- **Phase:** 2 — Stack Inference
## Inferred Stack
| Layer | Detection | Confidence |
| -------- | ------------ | ----------------- |
| Backend | <technology> | <High/Medium/Low> |
| Frontend | <technology> | <High/Medium/Low> |
| Docs | <structure> | <High/Medium/Low> |
## Next Step
Confirm stack inference is correct.
**Approval Required:** Yes
⛔ CHECKPOINT
STOP. Do not proceed until human explicitly approves:
- Stack classification is correct
- Technology choices are accurately detected
Phase 3: Project Identity
Gather Project Information
- Ask project name
- Ask one-line purpose
- Ask about domain terminology
- Ask about project-specific conventions
Output
## Context Anchors
- **Phase:** 3 — Project Identity
## Project Identity
- **Name:** <name>
- **Purpose:** <one-line purpose>
- **Domain terms:** <key terms>
- **Conventions:** <project-specific conventions>
## Next Step
Continue to preview.
**Approval Required:** No
Phase 4: Preview and Confirm
Generate and Present
- Generate workspace context from gathered information
- Present preview of the full context file
- Apply after approval
Workspace Context Schema
The workspace context file contains:
- Project identity (name, purpose)
- Domain terminology
- Architecture (pattern, backend, frontend)
- Convention amendments (project-specific overrides)
- Key documentation pointers
Output
## Context Anchors
- **Phase:** 4 — Preview and Confirm
## Generated Workspace Context
<full preview of docs/workspace/context.md content>
## Next Step
Awaiting approval to write workspace context file.
**Approval Required:** Yes
⛔ CHECKPOINT
STOP. Do not write the workspace context file until human explicitly approves:
- Content is accurate
- No sections are missing
- Terminology is correct
Error Handling
| Error | Recovery |
|---|---|
| Empty project (no markers) | Ask user to describe project manually |
| Conflicting markers | Present all detected, ask for clarification |
| Existing context file | Offer to update vs replace |
Recommended Agent Skills
Expand your agent's capabilities with these related and highly-rated skills.
agent-ops-spec
Manage specification documents in .agent/specs/. Use when user provides requirements, acceptance criteria, or feature descriptions that need to be tracked and validated against implementation.
agent-ops-state
Maintain .agent state files. Use at session start, after meaningful steps, and before concluding: read/update constitution/memory/focus/issues/baseline consistently.
agent-ops-spec
Manage specification documents in .agent/specs/. Use when user provides requirements, acceptance criteria, or feature descriptions that need to be tracked and validated against implementation.
agent-ops-testing
Test strategy, execution, and coverage analysis. Use when designing tests, running test suites, or analyzing test results beyond baseline checks.
agent-ops-testing
Test strategy, execution, and coverage analysis. Use when designing tests, running test suites, or analyzing test results beyond baseline checks.
agent-ops-state
Maintain .agent state files. Use at session start, after meaningful steps, and before concluding: read/update constitution/memory/focus/issues/baseline consistently.
Didn't find tool you were looking for?