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/_fix_contract.md
View on GitHub# Shared Fix Output Contract (assisted fixes)
Assisted-fix prompts receive a single finding (file, line, evidence) plus the
current content of the target file. They MUST return a single JSON object that
the remediation engine applies as an edit on the fix branch — never to the
user's default branch.
```json
{
"condition_id": "SEC-011",
"file": "relative/path.py",
"can_fix": true,
"explanation": "what the change does and why it closes the gap",
"edits": [
{
"old_string": "exact substring to replace (must be unique in the file)",
"new_string": "replacement"
}
],
"new_files": [
{ "path": "relative/new_file.py", "content": "full file content" }
],
"manual_followup": "anything the human must still do (e.g. set an env var, rotate the key)"
}
```
Rules:
- Preserve the file's existing style, imports, and indentation.
- `old_string` must match the source EXACTLY and be unique; prefer the smallest
unambiguous span.
- Make the minimal change that closes the gap — do not refactor unrelated code.
- If you cannot produce a safe automatic fix, return `can_fix: false` with an
`explanation`; the engine will downgrade it to advisory guidance.
- Never introduce a real secret value. When removing a hardcoded secret, replace
it with an env-var/config reference and note the rotation step in
`manual_followup`.
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 |