More screenshots
Works with the AI Agents you already use
Claude Code
Cursor
Codex CLI
DeepSeek
Muse+22 moreClaude CodeCursorCodex CLIDeepSeekMuse
Dots
Manus
Grok
Grok Bot+18 agentsProduction Access Evidence Packet
Organize production-access records into a traceable evidence packet with Claude.
$1
Production Access Evidence Packet
Example session with this skill installed
Organize the evidence from ticket #402. The customer approved read-only access for 2 hours. Log shows a 4-hour session and one database update using a shared admin account. No MFA log found.
- Read your context and instructions
- Compiled the production access evidence
1. Packet decision
Decision: PARTIAL PRODUCTION-ACCESS EVIDENCE PACKET AVAILABLE.
8. Gaps and conflicts
G1 — Privilege Mismatch: Read-only approved vs database update performed.
G2 — Duration: 2-hour approval vs 4-hour session.
G3 — Attribution: Shared account used; human actor unidentified.
Connects securely to your tools. The creator never sees your data.
About this skill
The problem
Assembling production access evidence for security reviews or audits is a manual, error-prone grind. Scattered logs, Slack approvals, and ticket timestamps often conflict, leaving gaps in the narrative of who did what and when.
What it does
- Reconstructs a traceable timeline of access requests, approvals, activity, and revocation.
- Maps requested permissions against actual provisioned roles and executed commands.
- Identifies gaps such as pre-approval activity, missing MFA, or unrevoked tokens.
- Differentiates between customer approval, internal authority, and break-glass emergency access.
- Generates a structured review packet with source registers and attribution maps.
Why this beats prompting it yourself
General-purpose prompts often conflate role removal with session termination or fail to maintain the distinction between a request and an approval. This skill enforces a neutral, evidence-based workflow that refuses to invent data or draw unauthorized compliance conclusions, ensuring the final packet stands up to professional review.
Use cases
- Generating a handoff packet for incident response or security postmortems.
- Reconciling support team impersonation sessions with customer approvals.
- Investigating privileged access gaps where shared accounts or contractors were used.
- Pre-audit preparation to identify missing evidence before a formal compliance review.
Known limitations
This tool does not connect to live systems or identity providers. It relies entirely on logs and materials you provide via files or the Read tool.
Find more skills like this on the Claude Skills Marketplace, the Codex Skills Marketplace and the Gemini Skills Marketplace, or browse Claude Skills for Agents & Orchestration.
Requires user-supplied logs or files. Cannot connect to live environments or IAM consoles. Does not make legal, compliance, or misconduct determinations.
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 3 months ago
Permissions
Permissions are limited to the active local workspace and are used to inspect user-supplied or local workspace files. The skill package does not require bundled credentials, unrestricted external network access, or automatic production changes.