exploring-ai-failures
exploring-ai-failures is an agent skill published by posthog, listed under building agents. It lives in the PostHog/skills repository, which has 75 GitHub stars and is licensed under MIT; we last read it on 2026-10-22.
This tool identifies and categorizes failure patterns in AI/LLM applications in production, helping to understand and triage issues such as wrong answers, ignored instructions, and hallucinations. It works by analyzing real traces and can be scoped to specific use cases.
Install
skills is a generic installer for any repository of Claude agent skills -- it reads PostHog/skills’s own structure rather than assuming one, the same way this page reads the skill’s own SKILL.md rather than assuming a format.
npx skills add PostHog/skills
Maintenance
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, finding failing traces by whichever signal fits the context (code errors, metric outliers, trace-type slices, manual review, existing-eval spikes, clustering), and reading them into a ranked failure taxonomy.
exploring-ai-failures compared with similar skills
| Skill | Publisher | What it does | Repo stars | Last update |
|---|---|---|---|---|
| exploring-ai-failures (this page) | posthog | Find where an AI/LLM application is failing in production and surface the failure patterns, working from real… | 75 | 2026-10-25 |
| writing-simplified-technical-english(same repository) | posthog | Write English that a reader cannot misread: one meaning per word, active voice, simple tenses, one idea per s… | 75 | 2026-10-25 |
| claude-handoff | mattpocock | Hand the current conversation off to a fresh background agent that picks up the work immediately. | 303,549 | 2026-10-22 |
| context-engineering | addyosmani | Optimizes agent context setup. Use when starting a new session, when agent output quality degrades, when swit… | 110,611 | 2026-10-13 |
| using-agent-skills | addyosmani | Discovers and invokes agent skills. Use when starting a session, or when you need to decide which skill or wo… | 110,611 | 2026-10-13 |
| agent-platform-inference | Connects to and performs inference with Google Cloud Agent Platform GenAI models, including First-Party Gemin… | 21,580 | 2026-10-25 | |
| agent-platform-skill-registry | Interact with the Gemini Enterprise Agent Platform Skill Registry to create and search for available skills.… | 21,580 | 2026-10-25 |
Skills from the same repository first, then others for this job by repository stars. Figures are from each repository when we last read it.
Common questions about exploring-ai-failures
- What does exploring-ai-failures do?
- This tool identifies and categorizes failure patterns in AI/LLM applications in production, helping to understand and triage issues such as wrong answers, ignored instructions, and hallucinations. It works by analyzing real traces and can be scoped to specific use cases.
- How do I install exploring-ai-failures?
- Run npx skills add PostHog/skills. The skills installer reads the repository’s own structure, so it works for any repository of agent skills.
- Who publishes exploring-ai-failures?
- posthog.
- Is exploring-ai-failures maintained, and what licence does it use?
- Its repository has 75 GitHub stars and its state in our directory is listed. Its last commit we recorded was on 2026-10-25. The repository declares the MIT licence.
More agent skills for building agents
- python-sdkby 101-skills
- widgets-uiby 101-skills
- context-engineeringby addyosmani
- using-agent-skillsby addyosmani
- anti-detect-browserby antibrow
- browser-mcp-agentby antibrow