datarobot-oss/datarobot-agent-skills / skills/datarobot-gap-analysis
datarobot-gap-analysis
FlaggedUse when the user wants to assess whether an AI agent repository (DataRobot-built or not) is enterprise-ready, run a gap analysis / readiness scan against security, governance, reliability, or regulatory standards, score an agent against EU AI Act requirements, or find and fix gaps (secrets, unpinned models, missing CI, missing guardrails, over-permissioned identity, etc.) before deploying an agent to production. Works on any repository, not only ones built with DataRobot.
scripts/prompts/_migrate_contract.md
View on GitHub# Migration Spec Output Contract
The extraction prompt receives the target agent's key files and MUST return a single
JSON object describing the business logic to carry over. The migration engine renders
this as an `agent_spec.md` for human review and assembles a carryover bundle.
```json
{
"name": "short-agent-name",
"description": "one sentence: what this agent does",
"framework": "langgraph | crewai | llamaindex | custom | unknown",
"model": "provider/model-id as found, or '' if not pinned",
"system_prompt": "the effective system/instruction prompt text",
"tools": [
{
"name": "tool_function_name",
"description": "what it does",
"inputs": [{ "name": "arg", "type": "str" }],
"outputs": [{ "name": "result", "type": "dict" }],
"auth": "service + auth method, or '' if none",
"source_file": "relative/path.py"
}
],
"workflow": "prose describing the graph/control flow, branches, and any human-in-the-loop steps",
"domain_dependencies": ["package-name"],
"carryover_files": ["relative/path.py", "relative/prompts/system.md"],
"manual_wiring": ["anything ambiguous or that a human must reconnect after scaffolding"],
"confidence": "high | medium | low"
}
```
Rules:
- `system_prompt` is the reconstructed effective text, never a secret value.
- `tools` lists only real domain tools found in the code (not framework helpers).
- `carryover_files` are repo-relative paths that hold logic to lift verbatim.
- `domain_dependencies` excludes replaceable framework/SDK plumbing.
- If the repo is not actually an agent, return `framework: "unknown"`, empty `tools`,
and explain in `manual_wiring`.
Related skills
| Skill | Stars | Updated | Works with | Status | Install |
|---|---|---|---|---|---|
| rea-analysis-optimizationmorluto/reaOptimize REA providers and shared analysis workflows for agent context, latency, CPU, and memory while preserving correctness and Evidence. Use for analysis bottlenecks and cache or query design; CI/test-suite optimization belongs to rea-ci-tests-audit. | Stars: 472k | Updated | Claude CodeCodex | Verified | Install |
| rea-ci-tests-auditmorluto/reaAudit REA CI and test suites for correctness, fixture drift, false passes, and measured performance; use for suite or workflow investigations and efficiency changes, rather than ordinary feature testing or a single test failure. | Stars: 472k | Updated | Claude CodeCodex | Verified | Install |
| rea-tool-designmorluto/reaAudit, investigate, design, or change REA investigation tools, CLI/MCP contracts, provider capabilities, and Evidence semantics. | Stars: 472k | Updated | Claude CodeCodex | Verified | Install |
| ponytail-auditDietrichGebert/ponytailQuality audit of the whole repo: bugs, security, real load, missing tests, speed, and what to delete. Most important first. | Stars: 194k | Updated | Claude CodeCodex | Verified | Install |