feat: add visor-agent-dev skill for AI coding assistants#562
Conversation
Cross-tool skill (Claude Code, Codex, OpenCode) that guides developers through the full visor assistant development workflow: writing YAML tests, config validation, mock/real provider testing, interactive --message testing, task trace debugging, and response evaluation. Includes safety guardrails to prevent destructive actions, unauthorized real provider usage, and secret leakage. Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
PR OverviewThis PR adds a comprehensive AI coding assistant skill ( Files Changed
Total: 500 additions, 0 deletions across 3 files What This PR Accomplishes
Key Technical ChangesSkill StructureThe SKILL.md file follows the Claude Code skill format:
Symlink StrategySafety Guardrails Implemented
Architecture & Impact Assessmentgraph TD
A[AI Coding Assistant] --> B{Platform Detection}
B -->|Claude Code| C[.claude/skills/visor-agent-dev/SKILL.md]
B -->|Codex| D[.agents/skills/visor-agent-dev → C]
B -->|OpenCode| E[.opencode/skills/visor-agent-dev → C]
C --> F[Development Workflow]
F --> G[Step 1: Understand Goal]
F --> H[Step 2: Write YAML Tests]
F --> I[Step 3: Validate Config]
F --> J[Step 4: Run with Mocks]
F --> K[Step 5: Real Providers]
F --> L[Step 6: Interactive Testing]
F --> M[Step 7: Debug Traces]
F --> N[Step 8: Evaluate Quality]
H --> O[*.tests.yaml files]
I --> P[visor validate --config]
J --> Q[visor test --only case#stage]
K --> R[visor test --no-mocks]
L --> S[visor --message --tui]
M --> T[visor tasks trace --full]
N --> U[visor tasks evaluate]
style C fill:#e1f5ff
style D fill:#ffe1e1
style E fill:#e1ffe1
Affected System Components
Development Flow Diagramflowchart LR
A[Write Tests] --> B[Validate Config]
B --> C[Run with Mocks]
C --> D{Pass?}
D -->|No| A
D -->|Yes| E[User Approval?]
E -->|No| C
E -->|Yes| F[Real Providers]
F --> G[Interactive Testing]
G --> H[Debug Traces]
H --> I{Working?}
I -->|No| A
I -->|Yes| J[Complete]
Scope Discovery & Context ExpansionDirect Impact
Related Files (Referenced in Skill)
Reference ImplementationThe skill references the Oel production assistant at
Configuration Patterns CoveredSkills- id: my-new-skill
description: "needs to [what triggers this skill]"
requires: [code-explorer]
knowledge: |
## Instructions
tools:
my-tool:
command: npx
args: [my-mcp-server]
allowed_commands: ['grep:*', 'find:*']
disallowed_commands: ['rm:*', 'sudo:*']Workflowsversion: "1.0"
id: my-workflow
inputs: [query]
steps:
fetch-data:
type: mcp
method: search
process:
type: ai
depends_on: [fetch-data]
outputs:
- name: result
value_js: "return outputs?.['process']?.text ?? null;"Test Assertions
Review Notes
Test Plan (from PR author)
Metadata
Powered by Visor from Probelabs Last updated: 2026-03-24T08:19:07.716Z | Triggered by: pr_opened | Commit: e44fada 💡 TIP: You can chat with Visor using |
✅ Security Check PassedNo security issues found – changes LGTM. Architecture Issues (10)
Performance Issues (1)
Powered by Visor from Probelabs Last updated: 2026-03-24T07:59:17.089Z | Triggered by: pr_opened | Commit: e44fada 💡 TIP: You can chat with Visor using |
Summary
SKILL.md) that guides AI coding agents through the full visor assistant development workflow.claude/skills/locationnpx -y @probelabs/visor@latestso no global install is neededWhat the skill covers
--only), stage filtering (#stage), parallel suites, discovery, debug flags--messageflow with task tracking, TUI modetasks list→tasks show→tasks trace --fullFiles
.claude/skills/visor-agent-dev/SKILL.md— canonical skill definition.agents/skills/visor-agent-dev— symlink for Codex discovery.opencode/skills/visor-agent-dev— symlink for OpenCode discoveryTest plan
SKILL.mdrenders correctly in Claude Code via/visor-agent-devls -la .agents/skills//.opencode/skills/)$mention or/skillslist🤖 Generated with Claude Code