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-extract-spec.md
View on GitHub# Business-Logic Extraction — Migration Spec
You are migrating an existing AI agent onto the DataRobot **af-component** stack
(af-component-base + llm + datarobot-mcp + agent@langgraph). You are given the key
files of someone else's agent repository: entrypoints, the agent/graph definition,
tool definitions, prompts, and config.
Your job is to **extract the business logic** — the parts that are expensive to
recreate and that encode what this agent actually does — into a structured spec. You
are NOT fixing or rewriting anything. You are describing what to carry over so the
logic can be lifted into a fresh, conformant af-components base.
## What counts as business logic (extract this)
- The **system / instruction prompt(s)** that define the agent's role and behavior.
- The **domain tools**: each tool's name, what it does, its inputs/outputs, and any
external service + auth it needs.
- The **workflow / graph shape**: nodes, control flow, branching, human-in-the-loop
steps, state passed between steps.
- **Domain dependencies**: third-party libraries the logic genuinely needs (NOT the
framework plumbing — langchain/langgraph/crewai/litellm/openai SDKs are replaceable).
- The specific source files that hold this logic and should be carried over verbatim.
## What to ignore (the framework will replace it)
- LLM client wiring, retry/transport code, the agent runtime/executor, MCP plumbing,
auth boilerplate, logging/tracing setup. These are regenerated by af-components.
## Rules
- Describe faithfully; do not invent tools or steps that aren't in the code.
- If the system prompt is assembled from fragments, reconstruct the effective text.
- Never copy a real secret value into the spec — reference the env var/config key.
- When something is unclear, lower `confidence` and note it in `manual_wiring`.
Return a SINGLE JSON object following the output contract below — nothing else.
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 |