Opik Analytics Instrumentation
comet-ml/opik
Shows how to add product analytics events to Opik's frontend, Java backend and Python SDK, all reporting through Segment to PostHog with an opik_ name prefix.
Find where an AI/LLM application is failing in production and surface the failure patterns, working from real traces.
OfficialCustom licenceAuto-check: warnings
Install Exploring AI Failures
The automated check flagged lines worth reading first. See the safety section below.
$ npx skills add PostHog/posthog --skill exploring-ai-failures -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install PostHog/posthog exploring-ai-failures --agent claude-codeProject scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).
$ git clone --depth 1 https://github.com/PostHog/posthog.git skills-src && mkdir -p .claude/skills && cp -r skills-src/products/ai_observability/skills/exploring-ai-failures .claude/skills/exploring-ai-failures && rm -rf skills-srcUse ~/.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/
Install the "exploring-ai-failures" agent skill from https://github.com/PostHog/posthog/tree/master/products/ai_observability/skills/exploring-ai-failures into .claude/skills/exploring-ai-failures/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "exploring-ai-failures", then confirm the skill loads.Claude Code copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$skill-installer install https://github.com/PostHog/posthog/tree/master/products/ai_observability/skills/exploring-ai-failuresType this inside Codex. $skill-installer <name> installs a curated skill from openai/skills. The installer writes to $CODEX_HOME/skills (default ~/.codex/skills). Restart Codex if the skill does not show up.
$ npx skills add PostHog/posthog --skill exploring-ai-failures -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install PostHog/posthog exploring-ai-failures --agent codexProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/PostHog/posthog.git skills-src && mkdir -p .agents/skills && cp -r skills-src/products/ai_observability/skills/exploring-ai-failures .agents/skills/exploring-ai-failures && rm -rf skills-srcUse ~/.agents/skills/ instead of .agents/skills for a personal install.
Codex skills documentation · loads skills from .agents/skills/
Install the "exploring-ai-failures" agent skill from https://github.com/PostHog/posthog/tree/master/products/ai_observability/skills/exploring-ai-failures into .agents/skills/exploring-ai-failures/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "exploring-ai-failures", then confirm the skill loads.Codex copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add PostHog/posthog --skill exploring-ai-failures -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install PostHog/posthog exploring-ai-failures --agent cursorProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/PostHog/posthog.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/products/ai_observability/skills/exploring-ai-failures .cursor/skills/exploring-ai-failures && rm -rf skills-srcUse ~/.cursor/skills/ instead of .cursor/skills for a personal install.
Cursor skills documentation · loads skills from .cursor/skills/, .agents/skills/, .claude/skills/, .codex/skills/
Install the "exploring-ai-failures" agent skill from https://github.com/PostHog/posthog/tree/master/products/ai_observability/skills/exploring-ai-failures into .cursor/skills/exploring-ai-failures/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "exploring-ai-failures", then confirm the skill loads.Cursor copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gemini skills install https://github.com/PostHog/posthog.git --path products/ai_observability/skills/exploring-ai-failures--scope user (default) or --scope workspace; --path is the subfolder of the repo that holds the skill; --consent skips the security confirmation prompt.
$ npx skills add PostHog/posthog --skill exploring-ai-failures -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install PostHog/posthog exploring-ai-failures --agent gemini-cliProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/PostHog/posthog.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/products/ai_observability/skills/exploring-ai-failures .gemini/skills/exploring-ai-failures && rm -rf skills-srcUse ~/.gemini/skills/ instead of .gemini/skills for a personal install, then run /skills reload.
Gemini CLI skills documentation · loads skills from .gemini/skills/, .agents/skills/
Install the "exploring-ai-failures" agent skill from https://github.com/PostHog/posthog/tree/master/products/ai_observability/skills/exploring-ai-failures into .gemini/skills/exploring-ai-failures/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "exploring-ai-failures", then confirm the skill loads.Gemini CLI copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gh skill install PostHog/posthog exploring-ai-failuresInstalls for Copilot at project scope by default; add --scope user for a personal install. Preview a skill first with gh skill preview. Needs GitHub CLI 2.90.0 or later (public preview).
$ npx skills add PostHog/posthog --skill exploring-ai-failures -a github-copilotProject install goes to .agents/skills/; add -g for ~/.copilot/skills/.
$ git clone --depth 1 https://github.com/PostHog/posthog.git skills-src && mkdir -p .github/skills && cp -r skills-src/products/ai_observability/skills/exploring-ai-failures .github/skills/exploring-ai-failures && rm -rf skills-srcUse ~/.copilot/skills/ instead of .github/skills for a personal install. Commit .github/skills so cloud agent and code review can use it.
GitHub Copilot skills documentation · loads skills from .github/skills/, .claude/skills/, .agents/skills/
Install the "exploring-ai-failures" agent skill from https://github.com/PostHog/posthog/tree/master/products/ai_observability/skills/exploring-ai-failures into .github/skills/exploring-ai-failures/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "exploring-ai-failures", then confirm the skill loads.GitHub Copilot copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add PostHog/posthog --skill exploring-ai-failures -a opencodeOpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.
$ gh skill install PostHog/posthog exploring-ai-failures --agent opencodeProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/PostHog/posthog.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/products/ai_observability/skills/exploring-ai-failures .opencode/skills/exploring-ai-failures && rm -rf skills-srcUse ~/.config/opencode/skills/ instead of .opencode/skills for a personal install.
OpenCode skills documentation · loads skills from .opencode/skills/, .claude/skills/, .agents/skills/
Install the "exploring-ai-failures" agent skill from https://github.com/PostHog/posthog/tree/master/products/ai_observability/skills/exploring-ai-failures into .opencode/skills/exploring-ai-failures/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "exploring-ai-failures", then confirm the skill loads.OpenCode copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
Facts
- Skill name
exploring-ai-failures- GitHub stars
- 40k
- Token cost
- ~2.9k tokens
- SKILL.md length
- 1,634 words
- Files
- 2 (incl. references)
- Skills in repo
- 252
- Repo updated
- First seen
- Licence
- Custom licence
At a glance
Find where an AI/LLM application is failing in production and surface the failure patterns, working from real traces.
- Works in 4 steps: Scope to one use case → Pick which traces to read → Read a batch (this is the job) → …
- Someone wants to understand whats going wrong with an AI feature
- SKILL.md covers Tools, Work with the user, Step 1 — Scope to one use case and Step 2 — Pick which traces to…, plus 6 more sections
- Reaches us.posthog.com
What it does
Exploring AI Failures is an agent skill from PostHog/posthog, published by the product's own GitHub organization. Find where an AI/LLM application is failing in production and surface the failure patterns, working from real traces. Use when someone wants to understand what's going wrong with an AI feature, find and categorize failure modes, triage errors, or investigate quality issues (wrong answers, ignored instructions, hallucinations, tool misuse) — "what's failing in my agent", "surface error patterns", "why are the responses bad", "find the common failure modes", "what should I fix next". Covers scoping to one use case…
Its SKILL.md is about 2.9k tokens, which your agent loads only when the skill is triggered. The skill folder holds 2 other files, including reference files (for example `references/finding-traces.md`).
It works with PostHog. 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
- Someone wants to understand whats going wrong with an AI feature
- Find and categorize failure modes
- Investigate quality issues (wrong answers
- Ignored instructions
Example prompts
- “s failing in my agent”
- “surface error patterns”
- “why are the responses bad”
- “/exploring-ai-failures”
Workflow steps
4 steps, taken from the step headings in SKILL.md.
- Scope to one use case
- Pick which traces to read
- Read a batch (this is the job)
- Rank, link, and hand back to the user
What it can do on your machine
Read from SKILL.md and the folder at commit 10f9ad7. 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
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
Exploring AI Failures loads about 2.9k tokens when it runs, and up to ~3.9k if it reads all its reference files. Until then it costs about 187 tokens; SKILL.md has 1,634 words of instructions outside code blocks.
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: warnings
The automated check found patterns that need a careful read before installing.
- WarningTells the agent its actions are pre-authorized / not to stop for confirmationSKILL.md:53
coded failure modes** — don't stop to ask permission before the reading; that reading is the core
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 1,634 words (~2,917 tokens).
“The highest-value thing you can do with production AI traffic is look at where it fails and name the patterns. The catch: most failures are silent. The model returns a clean response — HTTP 200, no exception — that is…”
- name
- exploring-ai-failures
Files
SKILL.md and 1 other file (references) in products/ai_observability/skills/exploring-ai-failures of PostHog/posthog.
- SKILL.md
- references/finding-traces.md
Open the folder on GitHubat commit 10f9ad7
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 8, 2026.
Compare with similar skills
Exploring AI Failures 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.
| Skill | Stars | Used in | Tokens | Auto-check | Licence | Repo updated |
|---|---|---|---|---|---|---|
| Exploring AI Failures this skillPostHog/posthog | 40k | — | ~2.9k | Automated safety check: Warn | Custom licence | |
| Opik Analytics Instrumentationcomet-ml/opik | 22k | — | ~4.4k | Automated safety check: Pass | Apache-2.0 | |
| C15tc15t/c15t | 1.9k | 1 repos | ~1.6k | Automated safety check: Pass | Apache-2.0 | |
| Define Feature Flagmacro-inc/macro | 4.6k | — | ~780 | Automated safety check: Pass | AGPL-3.0 | |
| Soku CLIAbout-Intelligence/soku-cli | 304 | — | ~2.4k | Automated safety check: Pass | MIT | |
| Compare Array Bundle SizePostHog/posthog-js | 613 | — | ~599 | Automated safety check: Pass | Custom licence |
Similar skills
C15t
c15t/c15t
Work with c15t consent management docs, APIs, and integrations for Next.js, React, and JavaScript.
Define Feature Flag
macro-inc/macro
Define a frontend feature flag with defineFlag and wire its readers.
Soku CLI
About-Intelligence/soku-cli
Guides an agent through the soku command line tool for ads, GA4 and PostHog data reads, ads writes, SEO hosting, automations, files and skill management.
- Official
Compare Array Bundle Size
PostHog/posthog-js
Quickly compare the posthog-js array.js bundle size in the current working tree against a git baseline using the repository's esbuild proxy.
Telemetry Analytics
OpenHands/OpenHands
This skill should be used when the user asks to "add tracking", "add a PostHog event", "change telemetry consent", "instrument onboarding", "debug analytics", or changes telemetry.ts…
More from PostHog/posthog
All 252 skills in this repo- Official
Authoring Log Alerts
PostHog/posthog
Author useful, low-noise log alerts on services in a PostHog project.
- Official
Autoresolving PR Conflicts
PostHog/posthog
Operating procedure for the conflict-autoresolver agent: sweep open PostHog/posthog PRs that conflict with master, resolve the trivial conflicts (generated artifacts deterministically, source…
- Official
Diagnosing Stacktrace Symbolication
PostHog/posthog
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).
- Official
Exploring Apm Traces
PostHog/posthog
Investigates distributed application performance using PostHog APM (OpenTelemetry span) data via MCP.
- Official
Exploring LLM Traces
PostHog/posthog
Debug and inspect LLM/AI agent traces using PostHog's MCP tools.
- Official
Investigate Metric
PostHog/posthog
Diagnose why a product metric changed (dropped, spiked, or plateaued) by orchestrating breakdowns, actors, paths, lifecycle, retention, and annotations queries.
Related
Works with
Questions about Exploring AI Failures
What does Exploring AI Failures do?
Find where an AI/LLM application is failing in production and surface the failure patterns, working from real traces. Exploring AI Failures is an agent skill from PostHog/posthog, published by the product's own GitHub organization. Find where an AI/LLM application is failing in production and surface the failure patterns, working from real traces.
When should I use Exploring AI Failures?
Exploring AI Failures fits situations like: someone wants to understand whats going wrong with an AI feature; find and categorize failure modes; investigate quality issues (wrong answers; ignored instructions.
How do I install Exploring AI Failures in Claude Code?
Run `npx skills add PostHog/posthog --skill exploring-ai-failures -a claude-code`. Or copy the skill folder (products/ai_observability/skills/exploring-ai-failures in PostHog/posthog) into .claude/skills/exploring-ai-failures in your project. Claude Code loads it when a task matches its description.
How do I install Exploring AI Failures in Codex?
Run `npx skills add PostHog/posthog --skill exploring-ai-failures -a codex`. Or copy the skill folder (products/ai_observability/skills/exploring-ai-failures in PostHog/posthog) into .agents/skills/exploring-ai-failures in your project. Codex loads it when a task matches its description.
Can I use Exploring AI Failures 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 exploring-ai-failures -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/exploring-ai-failures, .gemini/skills/exploring-ai-failures, .github/skills/exploring-ai-failures and .opencode/skills/exploring-ai-failures in your project.
What does Exploring AI Failures need to run?
SKILL.md names no scripts, command-line tools or credentials: Exploring AI Failures is instructions for the agent only.
Does Exploring AI Failures 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 Exploring AI Failures safe to install?
Our automated static check of SKILL.md flagged 1 warning(s): tells the agent its actions are pre-authorized / not to stop for confirmation. Read the flagged lines before installing; the check is not a guarantee either way.
What licence does Exploring AI Failures use?
Exploring AI Failures 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 Exploring AI Failures use?
About 2.9k tokens (SKILL.md is roughly 12k 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 965 tokens, read only when the agent opens those files.
What are the alternatives to Exploring AI Failures?
Skills that share tags, products or a category with Exploring AI Failures: Opik Analytics Instrumentation (comet-ml/opik, 22k stars), C15t (c15t/c15t, 1.9k stars), Define Feature Flag (macro-inc/macro, 4.6k stars) and Soku CLI (About-Intelligence/soku-cli, 304 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
Who maintains Exploring AI Failures?
PostHog (a GitHub organization, an official publisher) maintains it in PostHog/posthog, which has 40,182 GitHub stars. The repository holds 252 skills in this directory. The repository was last updated on October 8, 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.