Frontend Session Rca

What it does

When your agent uses it

• The user asks to explain
• Review a session
• Asks if a session is healthy
• Pastes Frontend Observability session context (app id

Example prompts

• “session narrator”
• “frontend-session-rca”
• “Use the frontend-session-rca skill to diagnose a Grafana Frontend Observability (RUM) session: whether it is healthy, what went wrong, ranked…”
• “/frontend-session-rca”

Workflow steps

4 steps, taken from the step headings in SKILL.md.

1. 1Collect identity
2. 2Ensure gcx
3. 3Fetch the session
4. 4Read the dump, then answer

What it can do on your machine

Read from SKILL.md and the folder at commit 1ccacf2. It shows what the files ask for, not the result of running them.

• Tool permissions

  Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

  From allowed-tools in the SKILL.md frontmatter.

• Runs code

  Shell commands in SKILL.md call:

  • brew

  From the folder's file list and the shell code blocks in SKILL.md.

• Network

  Links to these hosts (documentation or services it may open):

  • github.com

  From URLs in SKILL.md, links to its own repository left out.

• Credentials

  Names no API keys, tokens, secrets or passwords.

  From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Frontend Session Rca loads about 2.3k tokens when it runs, and up to ~5k if it reads all its reference files. Until then it costs about 230 tokens; SKILL.md has 966 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it

~230

When it runs · the whole SKILL.md, loaded when a task matches

~2.3k

With references · SKILL.md plus every file in references/, read only if the agent opens them

~5k

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.

SKILL.md

The full file from grafana/skills at commit 1ccacf2, republished under its Apache-2.0 licence (© grafana). 966 words, ~2,346 tokens.

name

frontend-session-rca

description

Diagnoses a Grafana Frontend Observability (RUM) session: whether it is healthy, what went wrong, ranked problems with timestamps and evidence, likely cause, how to fix it. Optional follow-up: zoom in on the top error, impact across sessions, Session Replay, or a Tempo trace if the user asks. Fetches telemetry with `gcx frontend sessions get --save` and reads only that dump file. Use when the user asks to explain, diagnose, analyse, RCA, or review a session; asks if a session is healthy; pastes Frontend Observability session context (app id, session id, datasource UID); or mentions Faro, user journey, Core Web Vitals, exceptions, ANR, or a web or mobile RUM session — even if they do not say "session narrator" or "frontend-session-rca". Do not use this skill to instrument an app (Faro Web, React Native, Flutter, native OpenTelemetry) — use `app-observability` for Faro Web setup instead.

license

Apache-2.0

command -v gcx && gcx frontend sessions get -h

gcx login --server <grafana_url>

gcx config view -o json

gcx frontend sessions get <session_id> \
  --app <app_id> \
  -d <datasource_uid> \
  --since <since> \
  --save /tmp/session-<session_id>.txt

## Session overview
- App, session id, web or mobile, duration (`session_start` → last event as `session_end` only if `session_start` is in this dump; if that event is missing, say so — do not use the first row as start. `session_end` is not a Faro event)
- Environment: browser/OS or device/SDK, geo, app version, user id/username if present (avoid email/PII unless the user explicitly asks)
- Outcome: **healthy** | **degraded** | **error** | **unknown**

## What the user did
3–6 sentences of the journey in time order, oldest first (navigation, views, actions). No raw dump.

## Session health
One paragraph: healthy or not, and why (exceptions, failed HTTP, poor web vitals or mobile startup/jank, ANR, rage clicks).

## Problems found
Ranked list. Each item:
- Severity: critical / warning / info
- Timestamp (from the dump)
- What happened (exception type/message, HTTP status+URL, web vital or mobile cold/warm start / jank, …)
- Lead-up: the 1–3 events immediately before it
- `traceID` if that row has one (the id only — not a Tempo URL)
- Session Replay at this timestamp — only web + `session_replay_start`; convert both times to ms, then `?t=` ([grafana-links.md](references/grafana-links.md)). Omit on mobile, if there is no recording, or if `t < 0`.

## Likely cause
One or two sentences citing dump evidence. If several independent issues, say so — do not force a single root cause.

## How to fix it
Concrete next engineering steps (code, config, backend, or telemetry gaps). See [signal-catalog.md](references/signal-catalog.md).

## Follow-up
- <1–3 short questions named from this dump>

© grafana, Apache-2.0. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

SKILL.md and 3 other files (references) in skills/grafana-cloud/frontend-session-rca of grafana/skills.

• SKILL.md
• references/dump-format.md
• references/grafana-links.md
• references/signal-catalog.md

Open the folder on GitHubat commit 1ccacf2