New: 98,000+ 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

Agent skill

Posthog Product Health Audit

by boardsesh in boardsesh/boardsesh

Mine Boardsesh's PostHog telemetry (error tracking, session recordings, product analytics) with a multi-agent workflow, then file verified, deduplicated, severity-labelled GitHub issues.

Apache-2.0Auto-check passedData & Analytics

Install Posthog Product Health Audit

skills CLI
$ npx skills add boardsesh/boardsesh --skill posthog-product-health-audit -a claude-code

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

GitHub CLI
$ gh skill install boardsesh/boardsesh posthog-product-health-audit --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/boardsesh/boardsesh.git skills-src && mkdir -p .claude/skills && cp -r skills-src/.claude/skills/posthog-product-health-audit .claude/skills/posthog-product-health-audit && 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
posthog-product-health-audit
GitHub stars
164
Token cost
~2.1k tokens
SKILL.md length
905 words
Files
2
Skills in repo
5
Repo updated
First seen
Licence
Apache-2.0

At a glance

Mine Boardsesh's PostHog telemetry (error tracking, session recordings, product analytics) with a multi-agent workflow, then file verified, deduplicated, severity-labelled GitHub issues.

  • Works in 5 steps: search or info to find the tool. → info before every call . → For query-* tools, schema before… → …
  • Asked to analyse PostHog errors/recordings/analytics
  • SKILL.md covers When to use, Run it, The four phases and Severity rubric → labels, plus 4 more sections
  • Runs JavaScript scripts from its folder; calls gh; reaches us.posthog.com

What it does

Posthog Product Health Audit is an agent skill from boardsesh/boardsesh. Mine Boardsesh's PostHog telemetry (error tracking, session recordings, product analytics) with a multi-agent workflow, then file verified, deduplicated, severity-labelled GitHub issues. Use when asked to analyse PostHog errors/recordings/analytics, do a production-health or bug sweep, or turn telemetry into tracked issues. Project id 412845; repo boardsesh/boardsesh.

Its SKILL.md is about 2.1k tokens, which your agent loads only when the skill is triggered. The skill folder holds 1 other file (for example `audit-workflow.js`).

It sits in Data & Analytics, covering Product analytics. It works with PostHog, GitHub and Model Context Protocol. The licence is Apache-2.0.

When your agent uses it

  • Asked to analyse PostHog errors/recordings/analytics
  • Do a production-health
  • Turn telemetry into tracked issues

Example prompts

  • “/posthog-product-health-audit”

Requirements

  • Node.js

Workflow steps

5 steps, taken from the first numbered list in SKILL.md.

  1. search or info to find the tool.
  2. info before every call .
  3. For query-* tools, schema before populating array fields (e.g. schema query-funnel series).
  4. Confirm every event/property name with read-data-schema (kind: events / event_properties / event_property_values) — names like $pageview…
  5. calls that touch collected data need a context arg: 15–25 words, third person.

What it can do on your machine

Read from SKILL.md and the folder at commit 52ea68f. 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

    Ships script files (JavaScript), which the agent can run.

    Shell commands in SKILL.md call:

    • gh

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

  • Network

    Hosts in commands or code, which the agent is likely to contact:

    • us.posthog.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

Posthog Product Health Audit loads about 2.1k tokens when it runs. Until then it costs about 100 tokens; SKILL.md has 905 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~100
When it runs · the whole SKILL.md, loaded when a task matches
~2.1k

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 boardsesh/boardsesh at commit 52ea68f, republished under its Apache-2.0 licence (© boardsesh). 905 words, ~2,069 tokens.

Download SKILL.mdSave it as .claude/skills/posthog-product-health-audit/SKILL.md (or your agent's skills folder). This skill also uses 1 other file; get the full folder from GitHub.
name
posthog-product-health-audit
description
Mine Boardsesh's PostHog telemetry (error tracking, session recordings, product analytics) with a multi-agent workflow, then file verified, deduplicated, severity-labelled GitHub issues. Use when asked to analyse PostHog errors/recordings/analytics, do a production-health or bug sweep, or turn telemetry into tracked issues. Project id 412845; repo boardsesh/boardsesh.

PostHog product-health audit

Turns production telemetry into a short list of real, deduplicated bugs and files them as GitHub issues with the right severity. Built around the PostHog MCP (mcp__posthog__exec) and a four-phase Workflow. The canonical implementation lives next to this file: audit-workflow.js.

When to use

  • "Analyse our PostHog errors / recordings / analytics."
  • "Do a production-health sweep / find bugs from telemetry."
  • "Triage what users are hitting and open issues."

Read-only against PostHog. The only writes are the GitHub issues you create in Phase 4, plus a one-time from-posthog label.

Run it

Workflow({ scriptPath: ".claude/skills/posthog-product-health-audit/audit-workflow.js" })

Optional args: { project, repo, lookbackDays } — defaults (412845 / boardsesh/boardsesh / 30) live in audit-workflow.js; that file is the source of truth if these drift. The workflow returns structured findings and drafts issue specs — it does not file. You review issueSpecs, then file (Phase 4). This keeps a human checkpoint before anything lands on a public repo.

The workflow runs in the background; you get notified on completion. Watch live with /workflows.

The four phases

1 — Collect (4 parallel agents, PostHog MCP, read-only). Each follows the schema-first discipline below.

  • Errors — query-error-tracking-issues-list (active, -30d, by occurrences, test accounts filtered), then query-error-tracking-issue + query-error-tracking-issue-events to pull stack frame, screen/URL, app version, $lib (platform), and $session_ids for the top ~8 root causes. Run a second pass with library: "posthog-js" — the top list skews mobile (posthog-react-native), so confirm web $exception coverage rather than assume it.
  • Analytics — web-analytics-weekly-digest for the macro picture, then failure rates (not raw counts) from execute-sql over paired events (Bluetooth Connection Failed/…Success, Climb Sent to Board Failure/…Success, Tick Save Failed/Tick Logged, …) and query-funnel for Login Attempted→Succeeded, Onboarding Tour Started→Completed, Session Started→Climb Sent to Board Success. A growing site inflates absolute counts and bounce-rate by composition — flag rates and drop-off, never raw jumps.
  • Recordings — query-session-recordings-list for console_error_count > 0 and short high-click sessions, then session-recording-summarize on ~5 high-signal replays to get the user-facing symptom. Deep-link as https://us.posthog.com/project/<id>/replay/<recording_id>.
  • Web hygiene — $csp_violation, poor $web_vitals (LCP/CLS) by page, $dead_click hotspots.

2 — Verify (pipeline per candidate). classify (label + severity + suspected file via repo grep + whether a fix already exists) → refute (adversarial skeptic that tries to kill it; defaults to a lower keep level when uncertain). Each candidate ends as issue, hygiene, or drop.

3 — Dedup gate (mandatory). A dedicated dedup agent runs for each surviving candidate as the final stage of the verify pipeline() (so dedup for one finding overlaps verification of the next — no barrier). It searches open and closed issues (gh issue list --search, gh search issues) for the same root cause. duplicate:true candidates are recorded with a link and not filed; near-matches go in relatedIssues. When unsure, it errs toward duplicate:false (a reviewed near-dup beats a missed bug).

4 — Synthesize → File. One issue per root cause, climber-voice title, body = symptom + PostHog evidence link + occurrences/users/sessions + suspected file + severity rationale + related issues. Then create them with gh (see below).

Severity rubric → labels

SeverityMeaningLabel
P0crash / data-loss / security / total blocker for many userspriority:P0
P1core-flow bug or gap (login broken, send-to-board fails, board list blocked)priority:P1
P2noticeable, has a workaround (e.g. a validation error, a recurring 5xx pattern)priority:P2
P3cosmetic / long-tail / hygienepriority:P3

Every filed issue also gets bug, the provenance label from-posthog, and a platform label (ios / android / mobile / web). Only use labels that already exist — check gh label list.

Show full SKILL.md (360 more words)Show less

Noise policy

Real-but-not-user-facing telemetry (user cancels thrown as errors, dev/screenshot-only ReferenceErrors, log spam) is not filed one-per-item. The synthesis step rolls it into a single P3 "error-tracking hygiene" issue as a checklist (what to stop logging / guard, and where). When a run turns up no such noise, issueSpecs.hygiene is null — skip it, don't file a placeholder. Transient infra blips (a lone 502/504, a DNS miss) and expected behaviour (e.g. "auth required" when logged out — confirm in code first) are dropped, with the reason recorded.

Filing (Phase 4)

bash
# one-time provenance label, mirrors the existing from-sentry convention
gh label create from-posthog --color BFD4F2 --description "Filed from PostHog product telemetry" 2>/dev/null || true

# per issue, from issueSpecs.issues[]
gh issue create --repo boardsesh/boardsesh \
  --title "<title>" --body "<body>" \
  --label "priority:P1,bug,from-posthog,android"

# the single bundled hygiene issue from issueSpecs.hygiene

Afterwards print a summary: filed (#, title, severity), skipped-as-duplicate (→ existing #), skipped-as-noise/transient. Confirm with gh issue list --label from-posthog.

PostHog MCP discipline (do not skip)

mcp__posthog__exec is CLI-style. The order is mandatory, like reading a file before editing it:

  1. search <regex> or info <tool> to find the tool.
  2. info <tool> before every call <tool>.
  3. For query-* tools, schema <tool> <field> before populating array fields (e.g. schema query-funnel series).
  4. Confirm every event/property name with read-data-schema (kind: events / event_properties / event_property_values) — names like $pageview still need confirming per project; the Boardsesh taxonomy drifts.
  5. calls that touch collected data need a context arg: 15–25 words, third person.

Key tools: query-error-tracking-issues-list, query-error-tracking-issue, query-error-tracking-issue-events, query-session-recordings-list, session-recording-summarize, web-analytics-weekly-digest, query-trends, query-funnel, execute-sql, read-data-schema.

Re-running

Safe to re-run on a schedule. The dedup gate keeps it from re-filing anything already tracked, so each run only surfaces genuinely new problems. Bump lookbackDays for a wider sweep; the first collector pass auto-discovers fresh top errors, so no seed list is needed.

Watch-outs on re-run (the pipeline logic isn't unit-tested — verify by eye):

  • The dedup gate is keyword-driven gh search. On a large tracker, skim issueSpecs against gh issue list --label from-posthog before filing to confirm nothing already-tracked slipped through — especially issues phrased differently from the error string.
  • A finding marked keep: "drop" skips dedup entirely (intended — dropped items are never filed). A finding marked hygiene that the dedup gate flags as a duplicate is excluded from the bundle and routed to duplicates.
  • When every candidate is dropped/deduped, issueSpecs is { issues: [], hygiene: null } and no synth agent runs — a clean run with nothing to file is a valid outcome, not an error.

© boardsesh, 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 1 other file in .claude/skills/posthog-product-health-audit of boardsesh/boardsesh.

  • SKILL.md
  • audit-workflow.js

Open the folder on GitHubat commit 52ea68f

Compare with similar skills

Posthog Product Health Audit 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.

Posthog Product Health Audit compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Posthog Product Health Audit this skillboardsesh/boardsesh164—~2.1kAutomated safety check: PassApache-2.0
Prod TelemetryUsefulSoftwareCo/executor4.1k—~1.9kAutomated safety check: PassMIT
Building A DashboardPostHog/posthog40k—~2.3kAutomated safety check: PassCustom licence
Debugging MCP AnalyticsPostHog/posthog40k—~7.6kAutomated safety check: PassCustom licence
Querying Canvas DataPostHog/posthog40k—~5kAutomated safety check: PassCustom licence
Adding MCP Store ServersPostHog/posthog40k—~1.6kAutomated safety check: PassCustom licence

Similar skills

  • Prod Telemetry

    UsefulSoftwareCo/executor

    Query Executor's production telemetry — Axiom traces (executor-cloud dataset), prod Postgres via PlanetScale, PostHog product analytics — through the Executor MCP.

    4.1k GitHub stars~1.9k tokensUpdated today
    Data & AnalyticsAuto-check passed

  • Building A Dashboard

    PostHog/posthog

    Official

    Build a new dashboard, or update an existing one, from a set of insights — the same job the in-app assistant does with its upsert-dashboard tool, but over MCP.

    40k GitHub stars~2.3k tokensUpdated yesterday
    Data & AnalyticsAuto-check passed

  • Debugging MCP Analytics

    PostHog/posthog

    Official

    Debug, support, and build PostHog MCP Analytics — product analytics for MCP servers (the @posthog/mcp and posthog.mcp SDKs plus the mcpanalytics product).

    40k GitHub stars~7.6k tokensUpdated yesterday
    Agent WorkflowsAuto-check passed

  • Querying Canvas Data

    PostHog/posthog

    Official

    Get PostHog data into a canvas correctly: the host-injected ph SDK (loadInsight, query, capture, state, connectors, openExternal, navigate), the data hierarchy (saved insights first, typed query…

    40k GitHub stars~5k tokensUpdated yesterday
    Agent WorkflowsAuto-check passed

  • Adding MCP Store Servers

    PostHog/posthog

    Official

    Add a third-party MCP server (Linear, Notion, GitHub, ...) to the PostHog MCP store catalog.

    40k GitHub stars~1.6k tokensUpdated yesterday
    Agent WorkflowsAuto-check passed

  • Kql Query Authoring

    SCStelz/security-investigator

    A skill your agent uses when asked to write, create, or help with KQL (Kusto Query Language) queries for Microsoft Sentinel, Defender XDR, or Azure Data Explorer.

    249 GitHub stars~5.7k tokensUpdated 2 days ago
    Data & AnalyticsAuto-check passed

More from boardsesh/boardsesh

  • Bug Bash Campaign

    boardsesh/boardsesh

    Run a multi-agent bug bash — pick a batch of open bugs by priority label, claim them, investigate then implement via subagents, pair adversarial reviews, and shepherd every PR to ready-for-review…

    164 GitHub stars~2.4k tokensUpdated today
    Auto-check passed

  • Discord Feedback Triage

    boardsesh/boardsesh

    Classify collected Boardsesh Discord messages into GitHub issue decisions — bug, feature, question, noise, or duplicate — deduplicating against the existing tracker.

    164 GitHub stars~1.6k tokensUpdated today
    Auto-check passed

  • Sentry Issue Campaign

    boardsesh/boardsesh

    Drive Sentry-derived GitHub issues to merged PRs at scale — pick by priority label, self-assign, plan then implement via subagents, pair adversarial reviews, and shepherd every PR to ready-for-review.

    164 GitHub stars~2k tokensUpdated today
    Auto-check passed

  • Android Screenshots

    boardsesh/boardsesh

    Capture screenshots of the Boardsesh React Native app (packages/mobile/) running on an Android emulator, driven against Metro with a cached dev-client APK.

    164 GitHub stars~1.1k tokensUpdated today
    Auto-check passed

Works with

Categories

Questions about Posthog Product Health Audit

What does Posthog Product Health Audit do?

Mine Boardsesh's PostHog telemetry (error tracking, session recordings, product analytics) with a multi-agent workflow, then file verified, deduplicated, severity-labelled GitHub issues. Posthog Product Health Audit is an agent skill from boardsesh/boardsesh. Mine Boardsesh's PostHog telemetry (error tracking, session recordings, product analytics) with a multi-agent workflow, then file verified, deduplicated, severity-labelled GitHub issues.

When should I use Posthog Product Health Audit?

Posthog Product Health Audit fits situations like: asked to analyse PostHog errors/recordings/analytics; do a production-health; turn telemetry into tracked issues.

How do I install Posthog Product Health Audit in Claude Code?

Run `npx skills add boardsesh/boardsesh --skill posthog-product-health-audit -a claude-code`. Or copy the skill folder (.claude/skills/posthog-product-health-audit in boardsesh/boardsesh) into .claude/skills/posthog-product-health-audit in your project. Claude Code loads it when a task matches its description.

How do I install Posthog Product Health Audit in Codex?

Run `npx skills add boardsesh/boardsesh --skill posthog-product-health-audit -a codex`. Or copy the skill folder (.claude/skills/posthog-product-health-audit in boardsesh/boardsesh) into .agents/skills/posthog-product-health-audit in your project. Codex loads it when a task matches its description.

Can I use Posthog Product Health Audit 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 boardsesh/boardsesh --skill posthog-product-health-audit -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/posthog-product-health-audit, .gemini/skills/posthog-product-health-audit, .github/skills/posthog-product-health-audit and .opencode/skills/posthog-product-health-audit in your project.

What does Posthog Product Health Audit need to run?

Going by SKILL.md and its folder, Posthog Product Health Audit needs JavaScript for the scripts in its folder and the command-line tools its instructions call (gh). Our summary lists: Node.js.

Does Posthog Product Health Audit access the network?

SKILL.md names 1 domain. In commands or code: us.posthog.com; the agent is likely to contact it when it follows the instructions. This is read from the text; nothing was executed.

Is Posthog Product Health Audit 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 Posthog Product Health Audit use?

Posthog Product Health Audit is published under the Apache-2.0 licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Posthog Product Health Audit use?

About 2.1k tokens (SKILL.md is roughly 8.3k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.

What are the alternatives to Posthog Product Health Audit?

Skills that share tags, products or a category with Posthog Product Health Audit: Prod Telemetry (UsefulSoftwareCo/executor, 4.1k stars), Building A Dashboard (PostHog/posthog, 40k stars), Debugging MCP Analytics (PostHog/posthog, 40k stars) and Querying Canvas Data (PostHog/posthog, 40k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Posthog Product Health Audit?

boardsesh (a GitHub organization) maintains it in boardsesh/boardsesh, which has 164 GitHub stars. The repository holds 5 skills in this directory. The repository was last updated on October 11, 2026.

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