agentforce-d360-analyze

Name: agentforce-d360-analyze
Author: forcedotcom

744stars272forks

How to install agentforce-d360-analyze?

forcedotcom/sf-skills/agentforce-d360-analyze

$npx -y skills add forcedotcom/sf-skills --skill agentforce-d360-analyze

Installs into the current project.

Summary

Data Cloud 360° view of a single Agentforce session. TRIGGER when user asks to trace, inspect, summarize, or describe a specific Agentforce session by session id (Agent Session UUID 019d… or MessagingSession id 0Mw…). Also triggers on session discovery — find/list/search sess

Files · 1

View on GitHub

SKILL.md

1	# agentforce-d360-analyze — Data Cloud 360° session view
2
3	Hierarchical session reconstruction from Data Cloud STDM + GenAI DMOs for one Agentforce session. Three stages — fetch → assemble → render. Typical wall-clock: ~10–30s for a ~15-turn session.
4
5	The pipeline is DC-only: it reads runtime audit rows that Data Cloud has materialized. It is not a runtime-availability tool — see "DC-only blind spot" below for what this skill cannot answer.
6
7	## If the user hasn't given enough to proceed
8
9	When invoked with no session id AND no discovery criteria, print this block verbatim — do not paraphrase, do not pre-run any script. Trigger condition: the input is empty OR contains no session-id shape (neither a UUID nor a `0Mw…` messaging id) AND no discovery expression (no time phrase / `--agent` / `--channel` / `--outcome` / `--grep` / verbs like "find" / "list").
10
11	> Which session should I pull from Data Cloud, and in which org?
12	>
13	> I need:
14	> - Session id — either an Agent Session UUID (`019db7f6-…`) or a MessagingSession id (`0Mw…`, 15/18 chars).
15	> - No session id? — Tell me what you remember and I'll find it: how recent (e.g. "last 2 hours", "today", a date), which agent, which channel (Messaging / Builder / Voice), how it ended (escalated, user ended, transferred, timed out), or a phrase from the conversation. I'll show matching sessions as a numbered list — you pick one, I pull it.
16	> - Org alias — for `sf` CLI auth (the alias you configured with `sf org login`).
17	>
18	> Artifacts land in `~/.vibe/data/agentforce-d360-analyze/<org_id15>/<agent>__<ver>/<session_id>/` (override per-script with `--data-dir <path>`).
19
20	## Session id forms — UUID or MessagingSession id
21
22	Both forms are accepted on `--session`:
23
24	\| Form \| Example \| Resolution \|
25	\|---\|---\|---\|
26	\| Agent Session UUID \| `019dface-0000-7000-8000-000000000002` \| Pass-through \|
27	\| MessagingSession id (`0Mw` prefix) \| `0MwTESTMSG12345AAA` \| Resolved via `resolve_session.py` — live DC lookup on first fetch, disk-first thereafter \|
28
29	Multi-match is real. One MessagingSession id can map to multiple Agent Session UUIDs. On multi-match the resolver prints every candidate and exits non-zero; the user re-invokes with a specific UUID.
30
31	Artifacts always land under `~/.vibe/data/agentforce-d360-analyze/<org_id15>/<agent>__<ver>/<session_id>/` (default; overridable per-script with `--data-dir <path>`) — the messaging id is a lookup key only, never a directory name. The dominant agent (first in `sorted(agents_observed)`) names the `<agent>__<ver>/` segment.
32
33	## Resolving the script prefix
34
35	The default install puts the skill under the runtime's plugin root. If the
36	skill was cloned somewhere else (e.g. directly from the `forcedotcom/sf-skills`
37	repo into a custom path), set `PLUGIN_ROOT` to point at the runtime's skills
38	directory.
39
40	```bash
41	prefix="${SKILL_ROOT:-${PLUGIN_ROOT:-$HOME/.vibe/skills}/agentforce-d360-analyze}/scripts"
42	```
43
44	Every subsequent invocation in this doc uses `"$prefix/..."`.
45
46	## Session discovery (no id yet)
47
48	When the user doesn't have a session id, run `discover_sessions.py` against the STDM session DMO. Prints a numbered picker; user picks one; proceed with the chosen UUID.
49
50	```bash
51	python3 "$prefix/discover_sessions.py" --org <alias> [filters...]
52	```
53
54	Filters (all optional except `--org`): `--since <expr>` (default last 24h; accepts "last 2 hours", "today", ISO dates), `--agent <api-name>`, `--channel <Messaging\|Builder\|Voice>`, `--outcome <USER_ENDED\|ESCALATED\|TRANSFERRED\|TIMEOUT\|NOT_SET>`, `--grep <substring>` (conversation text), `--tz <IANA>`, `--limit <N>` (default 20).
55
56	Output: markdown table with `#`, `UUID`, `Start (UTC)`, `Agent`, `Channel`, `Duration`, `Outcome`. User replies with a number; proceed with that UUID.
57
58	## Pipeline — three stages
59
60	```
61	fetch_dc.py → 24 dc.<name>.json + dc._session_manifest.json (DC Query REST waterfall, 5 waves)
62	assemble_dc.py → dc._session_tree.json (pure in-memory hierarchical join)
63	render_dc.py → dc._session_summary.md (human summary, multi-section)
64	```
65
66	Each stage is independently runnable. `fetch_dc.py --session <sid> --org <alias>` chains all three by default.
67
68	### Invocation
69
70	```bash
71	python3 "$prefix/fetch_dc.py" --session <session-id-or-messaging-id> --org <alias>
72	```
73
74	Flags:

People who liked this also viewed

6 picks

Type

agentforce-d360-analyze

744stars272forks

View on GitHub

How to install agentforce-d360-analyze?

forcedotcom/sf-skills/agentforce-d360-analyze

$npx -y skills add forcedotcom/sf-skills --skill agentforce-d360-analyze

Installs into the current project.

Summary

Files · 1

View on GitHub

SKILL.md

1	# agentforce-d360-analyze — Data Cloud 360° session view
2
3	Hierarchical session reconstruction from Data Cloud STDM + GenAI DMOs for one Agentforce session. Three stages — fetch → assemble → render. Typical wall-clock: ~10–30s for a ~15-turn session.
4
5	The pipeline is DC-only: it reads runtime audit rows that Data Cloud has materialized. It is not a runtime-availability tool — see "DC-only blind spot" below for what this skill cannot answer.
6
7	## If the user hasn't given enough to proceed
8
9	When invoked with no session id AND no discovery criteria, print this block verbatim — do not paraphrase, do not pre-run any script. Trigger condition: the input is empty OR contains no session-id shape (neither a UUID nor a `0Mw…` messaging id) AND no discovery expression (no time phrase / `--agent` / `--channel` / `--outcome` / `--grep` / verbs like "find" / "list").
10
11	> Which session should I pull from Data Cloud, and in which org?
12	>
13	> I need:
14	> - Session id — either an Agent Session UUID (`019db7f6-…`) or a MessagingSession id (`0Mw…`, 15/18 chars).
15	> - No session id? — Tell me what you remember and I'll find it: how recent (e.g. "last 2 hours", "today", a date), which agent, which channel (Messaging / Builder / Voice), how it ended (escalated, user ended, transferred, timed out), or a phrase from the conversation. I'll show matching sessions as a numbered list — you pick one, I pull it.
16	> - Org alias — for `sf` CLI auth (the alias you configured with `sf org login`).
17	>
18	> Artifacts land in `~/.vibe/data/agentforce-d360-analyze/<org_id15>/<agent>__<ver>/<session_id>/` (override per-script with `--data-dir <path>`).
19
20	## Session id forms — UUID or MessagingSession id
21
22	Both forms are accepted on `--session`:
23
24	\| Form \| Example \| Resolution \|
25	\|---\|---\|---\|
26	\| Agent Session UUID \| `019dface-0000-7000-8000-000000000002` \| Pass-through \|
27	\| MessagingSession id (`0Mw` prefix) \| `0MwTESTMSG12345AAA` \| Resolved via `resolve_session.py` — live DC lookup on first fetch, disk-first thereafter \|
28
29	Multi-match is real. One MessagingSession id can map to multiple Agent Session UUIDs. On multi-match the resolver prints every candidate and exits non-zero; the user re-invokes with a specific UUID.
30
31	Artifacts always land under `~/.vibe/data/agentforce-d360-analyze/<org_id15>/<agent>__<ver>/<session_id>/` (default; overridable per-script with `--data-dir <path>`) — the messaging id is a lookup key only, never a directory name. The dominant agent (first in `sorted(agents_observed)`) names the `<agent>__<ver>/` segment.
32
33	## Resolving the script prefix
34
35	The default install puts the skill under the runtime's plugin root. If the
36	skill was cloned somewhere else (e.g. directly from the `forcedotcom/sf-skills`
37	repo into a custom path), set `PLUGIN_ROOT` to point at the runtime's skills
38	directory.
39
40	```bash
41	prefix="${SKILL_ROOT:-${PLUGIN_ROOT:-$HOME/.vibe/skills}/agentforce-d360-analyze}/scripts"
42	```
43
44	Every subsequent invocation in this doc uses `"$prefix/..."`.
45
46	## Session discovery (no id yet)
47
48	When the user doesn't have a session id, run `discover_sessions.py` against the STDM session DMO. Prints a numbered picker; user picks one; proceed with the chosen UUID.
49
50	```bash
51	python3 "$prefix/discover_sessions.py" --org <alias> [filters...]
52	```
53
54	Filters (all optional except `--org`): `--since <expr>` (default last 24h; accepts "last 2 hours", "today", ISO dates), `--agent <api-name>`, `--channel <Messaging\|Builder\|Voice>`, `--outcome <USER_ENDED\|ESCALATED\|TRANSFERRED\|TIMEOUT\|NOT_SET>`, `--grep <substring>` (conversation text), `--tz <IANA>`, `--limit <N>` (default 20).
55
56	Output: markdown table with `#`, `UUID`, `Start (UTC)`, `Agent`, `Channel`, `Duration`, `Outcome`. User replies with a number; proceed with that UUID.
57
58	## Pipeline — three stages
59
60	```
61	fetch_dc.py → 24 dc.<name>.json + dc._session_manifest.json (DC Query REST waterfall, 5 waves)
62	assemble_dc.py → dc._session_tree.json (pure in-memory hierarchical join)
63	render_dc.py → dc._session_summary.md (human summary, multi-section)
64	```
65
66	Each stage is independently runnable. `fetch_dc.py --session <sid> --org <alias>` chains all three by default.
67
68	### Invocation
69
70	```bash
71	python3 "$prefix/fetch_dc.py" --session <session-id-or-messaging-id> --org <alias>
72	```
73
74	Flags:

People who liked this also viewed

6 picks

Type