New: 97,000+ skills indexed from GitHub repos with 100+ stars · every skill safety-checkedBrowse top skillsTop skills
Esc to closeBrowse all skills
Submit a skillBrowse skills
Submit a skillBrowse skills

Official agent skill

Triaging Web Analytics Support

by PostHog in PostHog/posthog-foss

Triage web analytics support tickets end to end: enumerate open tickets from the in-app conversations product and their Zendesk mirrors, classify each into a diagnostic shape (frontend crash, "two…

OfficialMITAuto-check passedSales & Support

Install Triaging Web Analytics Support

skills CLI
$ npx skills add PostHog/posthog-foss --skill triaging-web-analytics-support -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install PostHog/posthog-foss triaging-web-analytics-support --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/PostHog/posthog-foss.git skills-src && mkdir -p .claude/skills && cp -r skills-src/.agents/skills/triaging-web-analytics-support .claude/skills/triaging-web-analytics-support && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Facts

Skill name
triaging-web-analytics-support
GitHub stars
721
Token cost
~1.6k tokens
SKILL.md length
576 words
Files
4 (incl. references)
Skills in repo
213
Repo updated
First seen
Licence
MIT

At a glance

Triage web analytics support tickets end to end: enumerate open tickets from the in-app conversations product and their Zendesk mirrors, classify each into a diagnostic shape (frontend crash, "two…

  • Works in 4 steps: Enumerate the queue → Classify the shape, then run its playbook → Produce artifacts → …
  • Asked to triage the web analytics support channel
  • SKILL.md covers 1. Enumerate the queue, 2. Classify the shape, then…, 3. Produce artifacts and 4. Verification tools
  • Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md

What it does

Triaging Web Analytics Support is an agent skill from PostHog/posthog-foss, published by the product's own GitHub organization. Triage web analytics support tickets end to end: enumerate open tickets from the in-app conversations product and their Zendesk mirrors, classify each into a diagnostic shape (frontend crash, "two numbers don't match", traffic count drop, tracker not loading / undercounting vs a competitor, ad-platform integration error, channel type misclassification), run the matching playbook, and produce reply drafts plus fix PRs where warranted. Use when asked to triage the web analytics support channel, investigate a web…

Its SKILL.md is about 1.6k tokens, which your agent loads only when the skill is triggered. The skill folder holds 4 other files, including reference files (for example `references/diagnostic-playbooks.md`, `references/loading-audit.md` and `references/ticket-queries.md`).

It sits in Sales & Support, covering Customer support. It works with Zendesk and PostHog. The repository describes itself as: PostHog FOSS is a read-only mirror of PostHog, with all proprietary code removed. NOTE: This repo is synced automatically from the main PostHog repo. Please raise any issues and… The licence is MIT.

When your agent uses it

  • Asked to triage the web analytics support channel
  • Investigate a web analytics Zendesk
  • Conversations ticket
  • Explain metric discrepancies a customer reported

Example prompts

  • “two numbers don”
  • “/triaging-web-analytics-support”

Workflow steps

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

  1. Enumerate the queue
  2. Classify the shape, then run its playbook
  3. Produce artifacts
  4. Verification tools

What it can do on your machine

Read from SKILL.md and the folder at commit 2c48221. 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

    No scripts in the folder and no shell commands in SKILL.md.

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

  • Network

    No URLs in SKILL.md.

    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

Triaging Web Analytics Support loads about 1.6k tokens when it runs, and up to ~4.6k if it reads all its reference files. Until then it costs about 200 tokens; SKILL.md has 576 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~200
When it runs · the whole SKILL.md, loaded when a task matches
~1.6k
With references · SKILL.md plus every file in references/, read only if the agent opens them
~4.6k

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

Auto-check passed

The automated check found no risky patterns in SKILL.md.

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 PostHog/posthog-foss at commit 2c48221, republished under its MIT licence (© PostHog). 576 words, ~1,579 tokens.

Download SKILL.mdSave it as .claude/skills/triaging-web-analytics-support/SKILL.md (or your agent's skills folder). This skill also uses 3 other files; get the full folder from GitHub.
name
triaging-web-analytics-support
description
Triage web analytics support tickets end to end: enumerate open tickets from the in-app conversations product and their Zendesk mirrors, classify each into a diagnostic shape (frontend crash, "two numbers don't match", traffic count drop, tracker not loading / undercounting vs a competitor, ad-platform integration error, channel type misclassification), run the matching playbook, and produce reply drafts plus fix PRs where warranted. Use when asked to triage the web analytics support channel, investigate a web analytics Zendesk or conversations ticket, or explain metric discrepancies a customer reported. Internal-only: queries cross-customer support and usage data; never copy customer names or their traffic numbers into public artifacts (PRs, issues, commits).

Triaging web analytics support tickets

The job: turn a pile of open support tickets into (a) reply drafts grounded in code or data, and (b) draft PRs for real bugs. Most reported "bugs" are explainable semantics; most real bugs show up in error tracking or raw data before they show up in the code. Diagnose before writing code, and always determine which layer a symptom lives in before proposing a fix.

1. Enumerate the queue

Tickets live in the conversations product and are queryable via the PostHog MCP execute-sql tool against system.support_tickets (project 2, US). Zendesk mirrors carry full comment history in the data warehouse. See references/ticket-queries.md for ready-to-run SQL: open-ticket scans, keyword filters, full Zendesk comment extraction (the child_events JSON pattern), and resolving a requester email to an org/team across US and EU regions.

Slack channel #support-web-analytics mirrors new Zendesk tickets; the in-app ticket link in each message carries the conversations UUID.

2. Classify the shape, then run its playbook

Detailed walk-throughs with worked examples are in references/diagnostic-playbooks.md. The shapes:

ShapeTrigger phrasesFirst move
Frontend crash"everything crashes", exception ID, stack traceError tracking lookup; sourcemapped frames name the file. Check both US and EU projects
Two numbers don't match"two different bounce rates", "insight X disagrees with tile Y"Semantics first, not code: event-level vs session-entry scoping, "landing vs containing", any-event vs entry-event filters explain most of these
Count drop over time"pageviews declined", "tracking loss"Layer split: raw stored counts vs query-side exclusion. $pageview vs $pageleave ratio, UA segmentation, SDK version pin. Bot-shaped traffic disappearing is common and is not a PostHog bug
Tracker not loading / undercounts competitor"numbers lower than <other tool>", GTM, consent, ad blockersRuntime loading audit with Playwright against their live site: load method, first-request timing, blocklist simulation. See references/loading-audit.md
Ad-platform integration error"can't re-add source", OAuth errors, "no conversions"Source re-creation paths, OAuth failure modes (for example Microsoft AADSTS650052), attribution join keys (exact campaign name + normalized source, both UTMs required for the fallback)
Channel type misclassification"shows as Direct", "wrong channel"posthog/models/channel_type/channel_definitions.json + the decision tree in posthog/hogql/database/schema/channel_type.py; unknown source + stripped referrer falls through to Direct

Two cross-cutting rules:

  • Determine the layer before the fix. Capture → ingestion → stored events → query-time classification → UI. A drop in raw count() can't be caused by query-time bot exclusion; a classification change can't alter stored counts. State which layer the evidence points at.
  • Check for prior art before building. Search open issues/PRs and the channel history; several recurring asks (self-referral exclusion, AI channel type, OAuth error surfacing) have open issues with context that changes the right response.
Show full SKILL.md (146 more words)Show less

3. Produce artifacts

  • Reply drafts: ground every claim in a file:line, a query result, or a doc link. Offer the customer the aligned filter/property instead of only explaining why they're "wrong" (for example: session $entry_utm_campaign instead of event utm_campaign).
  • Fix PRs: one worktree + branch per fix, conventional commit, draft PR using the repo template. Public-repo safety: describe bugs generically; never include customer names, Zendesk numbers, or customer traffic volumes. Slack/ticket links behind auth are acceptable as origin context.
  • Session note: keep a running triage note (.notes/) with one section per ticket and an explicit "action left" marker per ticket, so a human can pick up the queue.

4. Verification tools

  • Runtime loading audits and traffic simulation: references/loading-audit.md.
  • Production query-side checks (per-team event series, UA splits, ingestion warnings): the querying-production-databases-via-metabase skill covers prod-us and prod-eu access.
  • Error tracking: MCP query-error-tracking-issues-list / query-error-tracking-issue-events with verbosity: stack gives sourcemapped frames.

© PostHog, MIT. 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 .agents/skills/triaging-web-analytics-support of PostHog/posthog-foss.

  • SKILL.md
  • references/diagnostic-playbooks.md
  • references/loading-audit.md
  • references/ticket-queries.md

Open the folder on GitHubat commit 2c48221

Compare with similar skills

Triaging Web Analytics Support next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

Triaging Web Analytics Support compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Triaging Web Analytics Support this skillPostHog/posthog-foss721—~1.6kAutomated safety check: PassMIT
Supporthaacked/dotfiles134—~2.9kAutomated safety check: PassNone
Support Ticket Triagecomposio-community/awesome-codex-skills17k—~364Automated safety check: PassNone
Zendesk Experttheneoai/awesome-skills183—~4.8kAutomated safety check: PassMIT
Siftranknoperator/siftrank223—~2.9kAutomated safety check: PassMIT
Customer Support Agentmastra-ai/mastra29k—~2.2kAutomated safety check: PassCustom licence

Similar skills

  • Support

    haacked/dotfiles

    Support hero workflow — start a ticket investigation with auto-organized notes, find existing notes, or generate the weekly highlights log.

    134 GitHub stars~2.9k tokensUpdated yesterday
    Sales & SupportAuto-check passed

  • Support Ticket Triage

    composio-community/awesome-codex-skills

    Triage customer support tickets/emails/chats into categories, priority, and next action; draft responses and create reproducible steps; use for Zendesk/Intercom/Help Scout exports or pasted threads.

    17k GitHub stars~364 tokensUpdated 2 mo ago
    Sales & SupportAuto-check passed

  • Zendesk Expert

    theneoai/awesome-skills

    Zendesk客服系统：工单、工作流、自动化。Use when managing customer support. An agent skill from theneoai/awesome-skills.

    183 GitHub stars~4.8k tokensUpdated 4 mo ago
    Sales & SupportAuto-check passed

  • Siftrank

    noperator/siftrank

    Find needles in haystacks with SiftRank. An agent skill from noperator/siftrank.

    223 GitHub stars~2.9k tokensUpdated 17 days ago
    Sales & SupportAuto-check passed

  • Customer Support Agent

    mastra-ai/mastra

    Authoring playbook for building agents that triage and reply to customer messages — support tickets, email inquiries, chat questions, refund requests, or product issues.

    29k GitHub stars~2.2k tokensUpdated today
    Sales & SupportAuto-check passed

  • Add Agent Adapter

    safedep/gryph

    A skill your agent uses when adding support for a new AI coding agent to Gryph, or when changing how an existing agent adapter is wired.

    171 GitHub stars~679 tokensUpdated 2 days ago
    Sales & SupportAuto-check passed

More from PostHog/posthog-foss

All 213 skills in this repo

  • Authoring Log Alerts

    PostHog/posthog-foss

    Official

    Author useful, low-noise log alerts on services in a PostHog project.

    721 GitHub stars~3k tokensUpdated today
    Auto-check passed

  • Autoresolving PR Conflicts

    PostHog/posthog-foss

    Official

    Operating procedure for the conflict-autoresolver agent: sweep open PostHog/posthog PRs that conflict with master, resolve the trivial conflicts (generated artifacts deterministically, source…

    721 GitHub stars~4.2k tokensUpdated today
    Auto-check passed

  • Diagnosing Stacktrace Symbolication

    PostHog/posthog-foss

    Official

    Help users debug PostHog Error Tracking stack-trace symbolication for any supported platform — JavaScript/TypeScript web, React Native (Hermes), Android (Proguard / R8), or iOS / macOS (dSYM).

    721 GitHub stars~2.2k tokensUpdated today
    Auto-check passed

  • Exploring Apm Traces

    PostHog/posthog-foss

    Official

    Investigates distributed application performance using PostHog APM (OpenTelemetry span) data via MCP.

    721 GitHub stars~3.5k tokensUpdated today
    Auto-check passed

  • Exploring LLM Traces

    PostHog/posthog-foss

    Official

    Debug and inspect LLM/AI agent traces using PostHog's MCP tools.

    721 GitHub stars~4.4k tokensUpdated today
    Auto-check passed

  • Investigate Metric

    PostHog/posthog-foss

    Official

    Diagnose why a product metric changed (dropped, spiked, or plateaued) by orchestrating breakdowns, actors, paths, lifecycle, retention, and annotations queries.

    721 GitHub stars~1.9k tokensUpdated today
    Auto-check passed

Works with

Categories

Questions about Triaging Web Analytics Support

What does Triaging Web Analytics Support do?

Triage web analytics support tickets end to end: enumerate open tickets from the in-app conversations product and their Zendesk mirrors, classify each into a diagnostic shape (frontend crash, "two…. Triaging Web Analytics Support is an agent skill from PostHog/posthog-foss, published by the product's own GitHub organization. Triage web analytics support tickets end to end: enumerate open tickets from the in-app conversations product and their Zendesk mirrors, classify each into a diagnostic shape (frontend crash, "two numbers don't match", traffic count drop, tracker not loading / undercounting vs a competitor, ad-platform integration error, channel type misclassification), run the matching playbook, and produce reply drafts plus fix PRs where warranted.

When should I use Triaging Web Analytics Support?

Triaging Web Analytics Support fits situations like: asked to triage the web analytics support channel; investigate a web analytics Zendesk; conversations ticket; explain metric discrepancies a customer reported.

How do I install Triaging Web Analytics Support in Claude Code?

Run `npx skills add PostHog/posthog-foss --skill triaging-web-analytics-support -a claude-code`. Or copy the skill folder (.agents/skills/triaging-web-analytics-support in PostHog/posthog-foss) into .claude/skills/triaging-web-analytics-support in your project. Claude Code loads it when a task matches its description.

How do I install Triaging Web Analytics Support in Codex?

Run `npx skills add PostHog/posthog-foss --skill triaging-web-analytics-support -a codex`. Or copy the skill folder (.agents/skills/triaging-web-analytics-support in PostHog/posthog-foss) into .agents/skills/triaging-web-analytics-support in your project. Codex loads it when a task matches its description.

Can I use Triaging Web Analytics Support in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add PostHog/posthog-foss --skill triaging-web-analytics-support -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/triaging-web-analytics-support, .gemini/skills/triaging-web-analytics-support, .github/skills/triaging-web-analytics-support and .opencode/skills/triaging-web-analytics-support in your project.

What does Triaging Web Analytics Support need to run?

SKILL.md names no scripts, command-line tools or credentials: Triaging Web Analytics Support is instructions for the agent only.

Does Triaging Web Analytics Support access the network?

SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.

Is Triaging Web Analytics Support safe to install?

Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.

What licence does Triaging Web Analytics Support use?

Triaging Web Analytics Support is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Triaging Web Analytics Support use?

About 1.6k tokens (SKILL.md is roughly 6.3k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full. Its references folder adds about 3.1k tokens, read only when the agent opens those files.

What are the alternatives to Triaging Web Analytics Support?

Skills that share tags, products or a category with Triaging Web Analytics Support: Support (haacked/dotfiles, 134 stars), Support Ticket Triage (composio-community/awesome-codex-skills, 17k stars), Zendesk Expert (theneoai/awesome-skills, 183 stars) and Siftrank (noperator/siftrank, 223 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Triaging Web Analytics Support?

PostHog (a GitHub organization, an official publisher) maintains it in PostHog/posthog-foss, which has 721 GitHub stars. The repository holds 213 skills in this directory. The repository was last updated on October 7, 2026.

Source: PostHog/posthog-foss on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.