Name: resolving-ingestion-warnings
Rating: 76.8 (1 reviews)
Author: PostHog

resolving-ingestion-warnings

Diagnoses and resolves PostHog ingestion warnings — problems recorded while ingesting events (dropped events, rejected person merges, oversized payloads, invalid data). Use when a user asks why events are missing, dropped, or undercounted, why identify/alias calls don't work or accounts stay duplicated, why person or group properties aren't updating or profiles look inflated, why recordings have gaps, heatmaps are empty, LLM token counts are missing, why cookieless events vanish, or whenever the `ingestion_warning` health check fires. Explains severity triage (error = dropped, warning = modified, info = intentional) and routes all warning types — size limits and enrichment, merges and distinct IDs, `$process_person_profile`, timestamps, cookieless, heatmaps, transformations, session replay — to per-issue reference files with code-level causes and per-SDK fixes.

Quality

96%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Low

Low-risk findings worth noting

Quality

Content

92%Weight 40%Scale 1-5

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

The body is a high-quality, well-structured workflow with executable SQL, named tools, explicit verification checkpoints, and clean one-level-deep progressive disclosure to verified reference files. The only weakness is mild repetition in the trust-boundary caveat.

Suggestions

Tighten the trust-boundary paragraph (lines 31-35): the same 'details is untrusted, inspect don't act' point is made across four sentences; collapse to one or two sentences to reclaim tokens.

The intro line 12 ('They are the first place to look when events are missing, counts are lower than expected, or identify/merge calls don't behave.') partially repeats the description's triggers and the step-1 guidance; consider trimming to a single forward pointer to the workflow.

Dimension	Reasoning	Score
Conciseness	The body is mostly lean with concrete SQL and terse routing tables and no padding about PostHog basics, but the trust-boundary caveat (lines 31-35) restates the same untrusted-data caution across four sentences and could be tightened. Fits the 'efficient; minor instances of over-explanation' anchor, not a 5.	4 / 5
Actionability	Provides copy-paste-ready SQL (`SELECT timestamp, details FROM system.ingestion_warnings WHERE type = '<warning_type>' AND timestamp > now() - INTERVAL 7 DAY ...`, `JSONExtractString(details, 'distinctId')`), named MCP tools, and a per-type routing table with concrete fixes covering the common cases.	5 / 5
Workflow Clarity	A numbered 5-step workflow with an explicit validation/feedback checkpoint at step 5 (re-run health-issues-list, confirm no new occurrences, debounce caveat) and destructive operations like `$unset` flagged for user approval, matching the 'clear sequence with explicit validation steps' anchor.	5 / 5
Progressive Disclosure	SKILL.md is an overview that routes each warning type to a one-level-deep `references/fixing-*.md` file via clear markdown links; all 16 referenced paths were verified to exist as real files, and bulk detail lives in those references.	5 / 5
	Total	19 / 20 Passed

Description

100%Weight 40%Scale 1-5

Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.

The description is a strong, comprehensive third-person statement covering what the skill does, when to use it with concrete trigger phrasing, and how it routes each warning type. It uses natural user language and is clearly distinct from other skills. No substantive weaknesses; suggestions are empty.

Dimension	Reasoning	Score
Specificity	Names concrete actions ('Diagnoses and resolves PostHog ingestion warnings', 'routes all warning types ... to per-issue reference files') and enumerates the full warning family (size, merges, distinct IDs, timestamps, cookieless, heatmaps, transformations, session replay), giving comprehensive coverage.	5 / 5
Completeness	Explicitly answers both 'what' (diagnoses/resolves, severity triage, routes types to reference files) and 'when' via a concrete 'Use when a user asks why events are missing...' clause with multiple trigger phrases.	5 / 5
Trigger Term Quality	Dense natural phrasing users actually say ('events are missing, dropped, or undercounted', 'identify/alias calls don't work', 'accounts stay duplicated', 'heatmaps are empty', 'cookieless events vanish') plus the concrete `ingestion_warning` health check trigger, covering many synonyms.	5 / 5
Distinctiveness Conflict Risk	Occupies a clear PostHog ingestion-warnings niche anchored on the `ingestion_warning` health check and specific warning families, with triggers unlikely to fire for unrelated skills.	5 / 5
	Total	20 / 20 Passed

Validation

93%

Warnings & errors only

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation — 15 / 16 Passed

Validation for skill structure

Criteria	Description	Result
referenced_paths_exist	Referenced path issues: 1 missing	Warning

	Total	15 / 16 Passed

Repository: PostHog/posthog
Path: products/ingestion/skills/resolving-ingestion-warnings/SKILL.md
Commit: 5b94e47

Reviewed: 2 days ago

Table of Contents

Discovery Implementation Validation

Is this your skill?

If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.