- Home
- Skills
- Product Management
- evolution audit
Works with the AI Agents you already use
evolution audit
Turn code discovery into a phased enterprise roadmap for SaaS, on-premise, and AI-native distribution.
$29
evolution audit
Example session with this skill installed
Run an evolution audit on this repo. Use the discovery-audit.md in docs/remediation/ and assume our target is a secure on-premise deployment for financial clients.
- Read your context and instructions
- Compiled the evolution audit
I have completed the evolution audit by analyzing the discovery baseline against your on-premise target. The audit identified critical gaps in identity management (DM-A) and external telemetry that will break in air-gapped environments.
Evolution Audit Report: Phase 1 & 2
| ID | Initiative | Goal | Gap Closed | Done Criteria |
|---|---|---|---|---|
| M1 | Local Auth Provider | Replace external OAuth with local OIDC | DM-A (Auth) | System boots without WAN |
| M2 | Data Egress Proxy | Centralize all outbound requests | DM-C (Network) | Single config for all exit IPs |
| MCP-01 | Logs Tool | Read-only MCP server for system logs | AI Readiness | Tool returns last 100 lines |
| M3 | Asset Localisation | Bundle all CDNs into the binary | DM-B (Assets) | 0 external script tags |
Target Architecture: Secure On-Premise
The current architecture relies on three external CDNs and a hardcoded Stripe dependency. To reach the target, the distribution lens (Section F) requires moving to a local license key validation system. The identified moat is the proprietary data transformation logic in /src/core/engine, which is currently evidenced as a "Technical Moat: Proven".
Direct Answers
- What to build next: Local authentication wrapper.
- What to sell: Standard On-Premise (Tier 1).
- What NOT to build: The proposed public API (postponed due to auth refactor).
Next steps
- Run
action-planto break Phase 1 into specific implementation tasks. - Review
docs/remediation/work/evolution/gate.mdto see the full security validation results. - Use
design-memoryto commit these architectural decisions to the project history.
Connects securely to your tools. The creator never sees your data.
About this skill
Technical debt and feature rot often hide the path to enterprise readiness. This skill audits your codebase and product architecture to map exactly how to reach SaaS, on-premise, and air-gapped milestones. It identifies competitive moats and generates a phased roadmap based on hard code evidence, moving you from a discovery baseline to a concrete execution plan.
What it does
- Distribution assessment. Evaluates readiness for SaaS, on-premise, and air-gapped deployments, identifying blockers in external dependencies or identity providers.
- MCP strategy. Plans Model Context Protocol (MCP) servers and AI features, categorizing tools by read/write/execute permissions and security requirements.
- Competitive moat grading. Analyzes the codebase and user facts to grade technical moats based on evidence rather than speculation.
- Phased roadmapping. Constructs a multi-phase development plan where initiatives are tied to specific code gaps and discovery findings.
- Enterprise readiness checks. Validates white-labeling potential and public API surface areas against deterministic architectural constraints.
How it works
- Load baseline. Reads the existing discovery audit and user-provided facts (competitors, team size, pricing) to ground the analysis.
- Parallel auditing. Triggers audits across distribution, channels, and market lenses to identify specific gaps.
- Synthesize report. Consolidates findings into a structured report covering target architecture and the eight core product questions.
- Automated validation. Runs the
audit.pychecker to ensure no dependency loops exist and all air-gapped constraints are met.
Frameworks & tools
Built for Python 3 environments. It utilizes internal scripts (audit.py, decisions.py) to process code maps and decision digests.
Why this beats prompting it yourself
Manual prompting often misses deep architectural dependencies like identity provider failures in air-gapped modes or probabilistic risks in AI features. This skill enforces a strict quality gate that prevents "hallucinated" moats and ensures every roadmap item is tied to a specific baseline discovery.
Use cases
- Enterprise transition. Determining the specific refactors needed to support an on-premise enterprise client.
- AI integration. Designing an MCP server that exposes local tools to agents with proper security approvals.
- Strategic planning. Building a technical roadmap for a board meeting grounded in actual code debt and capabilities.
Known limitations
Requires a pre-existing discovery-audit report to function effectively. It will not propose full rewrites unless incremental change is proven impossible by the code analysis.
Find more skills like this on the Claude Skills Marketplace, the Codex Skills Marketplace and the Gemini Skills Marketplace, or browse Claude Skills for Product Management.
Requires Python 3 for validation scripts. Must have a discovery-audit baseline report to avoid speculative results. Does not perform external state changes or code writes.
How to use
- 1
Connect your agent to the Agensi MCP
Copy the prompt and paste it into Claude, ChatGPT, Cursor or any agent that supports MCP. It sets up the connection for you. Manual setup
- 2
Sign in to Agensi
Your agent shows a sign-in link. Sign in and click Allow.
- 3
Ask for what you need
Your agent loads this skill and uses it on your task. It always asks before buying a skill.
Reviews
No reviews yet
Be one of the first to try it. Every listed skill goes through the trust checks below.
Security scanned
Checked by our 8-point scan before listing
Fresh listing
Recently published to Agensi
Money-back guarantee
Doesn't do what its page promises? You get your money back.
Trust & safety
Security scan
Security scan passed 12 days ago
- Software
Python