Agentforce Data Cloud 360° session view
Trace, inspect and summarize one Agentforce session — hierarchical trace from Data Cloud audit rows, with session discovery
- What
- Trace, inspect and summarize one Agentforce session — hierarchical trace from Data Cloud audit rows, with session discovery
- Cost
- Free
- Needs
- the sf CLI (authenticated against the target org — sf org login web --alias <alias>), Data Cloud enabled on the target org (STDM + GenAI DMOs materialized), Python 3.10+
- Install
- Copy the installer prompt below into your Muse — your agent does the rest.
Curated by Skill Harbor — Salesforce's official Agentforce session analyzer: a three-stage pipeline (fetch → assemble → render) that reconstructs one Agentforce session — by Agent Session UUID or 0Mw MessagingSession id — from Data Cloud STDM + GenAI DMO audit rows into a hierarchical trace (session → interactions → steps → messages → generations → gateway requests) plus a human-readable summary with session identity, transcript, per-turn rows, feedback and escalation flags, audit-chain integrity checks and empty-DMO diagnostics — with session discovery when the user has no id (filter by time, agent, channel, outcome, conversation text), all artifacts landing under `~/.vibe/data/`. By @forcedotcom, listed here with credit to its creator. Honest caveats: DC-only — it answers what happened, not what could have happened (no runtime planner telemetry: eligible topics, action-selection reasons); needs the `sf` CLI authenticated against a Data Cloud-enabled org and Python 3.10+; fresh sessions may lag Data Cloud materialization; Apache-2.0 licensed. Skill Harbor never reviews the code, review it yourself before use. Discovered via skills.sh.
Version:
Install
Prerequisites: the sf CLI (authenticated against the target org — sf org login web --alias <alias>), Data Cloud enabled on the target org (STDM + GenAI DMOs materialized), Python 3.10+ Install "Agentforce Data Cloud 360° session view" for me. It teaches Salesforce's three-stage pipeline (fetch → assemble → render) for reconstructing one Agentforce session from Data Cloud audit rows: session id forms, session discovery, the fetch_dc/assemble_dc/render_dc scripts, output artifacts, the DC-only blind spot, and caveats — by @forcedotcom, Apache-2.0 licensed. Repository: https://github.com/forcedotcom/sf-skills/blob/main/skills/agentforce-d360-analyze/SKILL.md 1. Fetch the SKILL.md file (and any helper files) from the repository path into a temporary folder and summarize what it does in one or two sentences. 2. Safety check: review the SKILL.md and scripts for anything suspicious (unexpected network calls, shell commands, credential harvesting). This repo should contain zero secrets in code, credentials only via the secure vault, allowed hosts declared in the SKILL.md. Verify that holds here; STOP on any red flag and tell me. 3. Install it as a skill: copy SKILL.md and its helper files into the agent's skills directory, in a folder named "agentforce-d360-analyze". 4. Verify with no network calls: frontmatter valid, files in place. 5. Report what was installed, where, and what I still need to do myself (e.g. authenticate the sf CLI against my Data Cloud-enabled org; confirm Python 3.10+ is available). GitHub is optional: if I have a GitHub account or the gh CLI, you may use it; otherwise public access is fine. Never require it unless it's in the prerequisites above. Rules: don't touch anything outside the temp folder and the install target. If anything looks off, stop and ask me.
Questions
How do I install a build?
Every product page includes a copy-paste install prompt. Paste it into your Muse and it sets the build up for you — no manual configuration.
Where does my money go?
Straight to the seller. Skill Harbor never processes payments: checkout happens on the seller’s own page, usually Stripe.
What does the ✓ next to a creator’s name mean?
It means we confirmed the identity of the person behind the listing. It says nothing about the code itself — always check a build before installing it.