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

Official agent skill

Diagnosing Experiment Health

by PostHog in PostHog/posthog

Runs diagnostics and a health check on one PostHog experiment: its setup, exposures, results and changes during the run.

OfficialCustom licenceAuto-check passedDatabases

Install Diagnosing Experiment Health

skills CLI
$ npx skills add PostHog/posthog --skill diagnosing-experiment-health -a claude-code

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

GitHub CLI
$ gh skill install PostHog/posthog diagnosing-experiment-health --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.git skills-src && mkdir -p .claude/skills && cp -r skills-src/products/experiments/skills/diagnosing-experiment-health .claude/skills/diagnosing-experiment-health && 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
diagnosing-experiment-health
GitHub stars
40k
Token cost
~5.9k tokens
SKILL.md length
2,718 words
Files
8 (incl. references)
Skills in repo
254
Repo updated
First seen
Licence
Custom licence

At a glance

Runs diagnostics and a health check on one PostHog experiment: its setup, exposures, results and changes during the run.

  • Works in 5 steps: Resolve the experiment → 5 — Pull a diagnostic snapshot (verify… → Match symptom to diagnostic → …
  • : user asks is my experiment healthy / set up right / biased?
  • SKILL.md covers Step 1 — Resolve the experiment, Step 1.5 — Pull a diagnostic…, Step 2 — Match symptom to… and Step 3 — Surface every…, plus 3 more sections
  • Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md

What it does

Diagnosing Experiment Health is an agent skill from PostHog/posthog, published by the product's own GitHub organization. Runs diagnostics and a health check on one PostHog experiment: its setup, exposures, results and changes during the run. Covers 0 exposures, sample ratio mismatch, lost or uneven exposures, users in multiple variants, identity faults, who the experiment counts, significance traps (peeking, A/A, 'target reached', Bayesian vs Frequentist, sequential, CUPED), mid-run edits, pause and freeze, and survey follow-up. TRIGGER when: user asks 'is my experiment healthy / set up right / biased?' or 'why 0 exposures?', asks…

Its SKILL.md is about 5.9k tokens, which your agent loads only when the skill is triggered. The skill folder holds 8 other files, including reference files (for example `references/bias-and-skew.md`, `references/diagnostic-snapshot.md` and `references/empty-experiment.md`).

It sits in Databases. It works with PostHog and SQL. The repository describes itself as: :hedgehog: PostHog is the leading platform for building self-driving products. Our developer tools – AI observability, analytics, session replay, flags, experiments, error…

When your agent uses it

  • : user asks is my experiment healthy / set up right / biased?
  • Why 0 exposures?
  • Asks why it counts different people than their insight
  • Mentions the bias

Example prompts

  • “target reached”
  • “is my experiment healthy / set up right / biased?”
  • “why 0 exposures?”
  • “/diagnosing-experiment-health”

Workflow steps

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

  1. Resolve the experiment
  2. 5 — Pull a diagnostic snapshot (verify before asking)
  3. Match symptom to diagnostic
  4. Surface every diagnostic the evidence supports
  5. Calibrate recommendations to experiment state

What it can do on your machine

Read from SKILL.md and the folder at commit c012c8d. 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

Diagnosing Experiment Health loads about 5.9k tokens when it runs, and up to ~62k if it reads all its reference files. Until then it costs about 263 tokens; SKILL.md has 2,718 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~263
When it runs · the whole SKILL.md, loaded when a task matches
~5.9k
With references · SKILL.md plus every file in references/, read only if the agent opens them
~62k

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

Its licence (Custom licence) doesn't allow us to republish the file, so here is its outline and opening line. It has 2,718 words (~5,875 tokens).

“This skill answers: My PostHog experiment results look wrong, biased, or empty — what's going on? It is the diagnostics and health check for one experiment: its setup, its exposures, its results and what changed during the run.”

— opening of SKILL.md by PostHog, Custom licence
name
diagnosing-experiment-health

Read the full SKILL.md on GitHub

Files

SKILL.md and 7 other files (references) in products/experiments/skills/diagnosing-experiment-health of PostHog/posthog.

  • SKILL.md
  • references/bias-and-skew.md
  • references/diagnostic-snapshot.md
  • references/empty-experiment.md
  • references/interpretation.md
  • references/mid-run-changes.md
  • references/numbers-vs-sql.md
  • references/qualitative-feedback.md

Open the folder on GitHubat commit c012c8d

Used in 1 other repository

We found 1 copy of this SKILL.md (exact, near-identical or edited) in other folders. This page covers the copy in PostHog/posthog, which our catalogue first saw on October 7, 2026.

Compare with similar skills

Diagnosing Experiment Health 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.

Diagnosing Experiment Health compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Diagnosing Experiment Health this skillPostHog/posthog40k—~5.9kAutomated safety check: PassCustom licence
Evolving The Data ModelTriliumNext/Trilium38k—~2.1kAutomated safety check: PassAGPL-3.0
Orchardcore Data MigrationOrchardCMS/OrchardCore8.2k—~1.7kAutomated safety check: PassBSD-3-Clause
SQL Optimization Patternsynulihao/AgentSkillOS61811 repos~3.3kAutomated safety check: PassNone
SQL PortabilityHL7/sql-on-fhir151—~512Automated safety check: PassCustom licence
ChronicleailyProject/aily-blockly3.8k—~1.6kAutomated safety check: PassGPL-3.0

Similar skills

  • Evolving The Data Model

    TriliumNext/Trilium

    A skill your agent uses when adding a DB migration or a new column/field to a Becca entity in Trilium ("add a migration", "new column on notes/attributes", "ALTER TABLE", "add a field to…

    38k GitHub stars~2.1k tokensUpdated today
    DatabasesAuto-check passed

  • Orchardcore Data Migration

    OrchardCMS/OrchardCore

    Creates and updates OrchardCore data migrations (DataMigration classes with CreateAsync/UpdateFromX).

    8.2k GitHub stars~1.7k tokensUpdated yesterday
    DatabasesAuto-check passed

  • SQL Optimization Patterns

    ynulihao/AgentSkillOS

    Master SQL query optimization, indexing strategies, and EXPLAIN analysis to dramatically improve database performance and eliminate slow queries.

    618 GitHub starsUsed in 11 repos~3.3k tokens
    DatabasesAuto-check passed

  • SQL Portability

    HL7/sql-on-fhir

    Analyse whether a SQL query is portable across database implementations using sqlglot transpilation.

    151 GitHub stars~512 tokensUpdated 5 days ago
    DatabasesAuto-check passed

  • Chronicle

    ailyProject/aily-blockly

    Analyze indexed Aily chat session history for prior decisions, tool executions, project summaries, usage tips, and session-store reindexing.

    3.8k GitHub stars~1.6k tokensUpdated today
    DatabasesAuto-check passed

  • Stmo

    SAP/project-foxhound

    Official

    Manage Redash queries and dashboards on Mozilla's STMO (sql.telemetry.mozilla.org) using stmo-cli.

    180 GitHub starsUsed in 2 repos~1.8k tokens
    DatabasesAuto-check passed

More from PostHog/posthog

All 254 skills in this repo

  • Authoring Log Alerts

    PostHog/posthog

    Official

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

    40k GitHub stars~3k tokensUpdated today
    Auto-check passed

  • Autoresolving PR Conflicts

    PostHog/posthog

    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…

    40k GitHub stars~4.2k tokensUpdated today
    Auto-check passed

  • Diagnosing Stacktrace Symbolication

    PostHog/posthog

    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).

    40k GitHub stars~2.2k tokensUpdated today
    Auto-check passed

  • Exploring Apm Traces

    PostHog/posthog

    Official

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

    40k GitHub stars~3.5k tokensUpdated today
    Auto-check passed

  • Exploring LLM Traces

    PostHog/posthog

    Official

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

    40k GitHub stars~4.4k tokensUpdated today
    Auto-check passed

  • Investigate Metric

    PostHog/posthog

    Official

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

    40k GitHub stars~1.9k tokensUpdated today
    Auto-check passed

Works with

Categories

Questions about Diagnosing Experiment Health

What does Diagnosing Experiment Health do?

Runs diagnostics and a health check on one PostHog experiment: its setup, exposures, results and changes during the run. Diagnosing Experiment Health is an agent skill from PostHog/posthog, published by the product's own GitHub organization. Runs diagnostics and a health check on one PostHog experiment: its setup, exposures, results and changes during the run.

When should I use Diagnosing Experiment Health?

Diagnosing Experiment Health fits situations like: : user asks is my experiment healthy / set up right / biased?; why 0 exposures?; asks why it counts different people than their insight; mentions the bias.

How do I install Diagnosing Experiment Health in Claude Code?

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

How do I install Diagnosing Experiment Health in Codex?

Run `npx skills add PostHog/posthog --skill diagnosing-experiment-health -a codex`. Or copy the skill folder (products/experiments/skills/diagnosing-experiment-health in PostHog/posthog) into .agents/skills/diagnosing-experiment-health in your project. Codex loads it when a task matches its description.

Can I use Diagnosing Experiment Health 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 --skill diagnosing-experiment-health -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/diagnosing-experiment-health, .gemini/skills/diagnosing-experiment-health, .github/skills/diagnosing-experiment-health and .opencode/skills/diagnosing-experiment-health in your project.

What does Diagnosing Experiment Health need to run?

SKILL.md names no scripts, command-line tools or credentials: Diagnosing Experiment Health is instructions for the agent only.

Does Diagnosing Experiment Health 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 Diagnosing Experiment Health 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 Diagnosing Experiment Health use?

Diagnosing Experiment Health has a licence file (the repository's licence) that doesn't match a standard licence. Read it on GitHub before reusing the skill.

How many tokens does Diagnosing Experiment Health use?

About 5.9k tokens (SKILL.md is roughly 24k 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 56k tokens, read only when the agent opens those files.

What are the alternatives to Diagnosing Experiment Health?

Skills that share tags, products or a category with Diagnosing Experiment Health: Evolving The Data Model (TriliumNext/Trilium, 38k stars), Orchardcore Data Migration (OrchardCMS/OrchardCore, 8.2k stars), SQL Optimization Patterns (ynulihao/AgentSkillOS, 618 stars) and SQL Portability (HL7/sql-on-fhir, 151 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Diagnosing Experiment Health?

PostHog (a GitHub organization, an official publisher) maintains it in PostHog/posthog, which has 40,209 GitHub stars. The repository holds 254 skills in this directory. The repository was last updated on October 10, 2026.

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