Name: signals-scout-ingestion-warnings
Rating: 60.8 (1 reviews)
Author: PostHog

signals-scout-ingestion-warnings

Signals scout for ingestion warnings — events and person/group updates that were dropped, mangled, or partially rejected during ingestion. Watches the warnings stream for new warning types, bursts above a type's own baseline, and error-severity clusters with broad reach, and files each actionable root cause as a report with the affected events and the fix.

Quality

72%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

High

Do not use without reviewing

Fix and improve this skill with Tessl

tessl review fix ./products/signals/skills/signals-scout-ingestion-warnings/SKILL.md

Quality

Content

77%Weight 40%Scale 1-3

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

A highly actionable, well-sequenced scouting playbook with executable SQL, concrete tool parameters, and clear validation checkpoints; its main weaknesses are occasional verbosity and a fully monolithic structure with no progressive disclosure to external reference files.

Suggestions

Extract the stable 'MCP tools' reference (and possibly the 'Territory' / 'Disqualifiers' rules) into a bundled reference file linked once from the body, enabling progressive disclosure to score 3.

Tighten the longest compound sentences (e.g. the Decide paragraph's edit/author/priority guidance) into shorter bullet clauses to improve conciseness without losing the concrete detail.

Dimension	Reasoning	Score
Conciseness	Most tokens earn their place as project-specific knowledge (severity enums, debounce behavior, MCP tool semantics) that Claude lacks, but several long compound sentences and repeated framing ('Counts are debounced, not exact ... don't quote them as event counts') could be tightened, matching 'mostly efficient but includes some unnecessary explanation or could be tightened'.	2 / 3
Actionability	Guidance is copy-paste ready: named MCP tools with parameters (`ingestion-warnings-list` with `since=-7d`, `samples` up to 50), an executable SQL query (`SELECT properties.$lib, properties.$lib_version, count() FROM events ... GROUP BY 1, 2 ORDER BY 3 DESC`), and concrete report fields (priority P2/P3, `repository=NO_REPO`), matching the 'fully executable code/commands' anchor.	3 / 3
Workflow Clarity	The run is explicitly sequenced (Get oriented → Profile shape → Explore → Save memory → Decide → Close out) with validation checkpoints: the 'is the stream even loud?' close-out gate, inbox dedupe-before-author, and `execute-sql` corroboration 'before putting numbers in a report', matching the 'clear sequence with explicit validation steps' anchor.	3 / 3
Progressive Disclosure	The body is well-organized with clear headers, a shape table, and bullet lists (not a wall of text), but it is monolithic — no bundle files exist and all content (MCP tool reference, territory rules, disqualifiers) is inline with no one-level-deep references, so it stops short of the 'clear overview with well-signaled references' anchor.	2 / 3
	Total	10 / 12 Passed

Description

67%Weight 40%Scale 1-3

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

A specific, distinctive third-person description that clearly states what the skill does, but it omits an explicit 'Use when...' trigger clause and leans on domain jargon over natural user phrasing, capping completeness and trigger-term quality at 2.

Suggestions

Add an explicit 'Use when ...' trigger clause (e.g. 'Use when investigating PostHog ingestion warnings, dropped events, or rejected person/group updates') to lift completeness to 3.

Broaden trigger-term coverage with plain user phrasings such as 'dropped events', 'ingestion errors', or 'data rejected during ingestion' alongside 'ingestion warnings' to improve trigger-term quality.

Dimension	Reasoning	Score
Specificity	The description names multiple concrete actions — 'Watches the warnings stream for new warning types, bursts above a type's own baseline, and error-severity clusters with broad reach, and files each actionable root cause as a report with the affected events and the fix' — matching the 'lists multiple specific concrete actions' anchor.	3 / 3
Completeness	It clearly answers 'what does this do', but there is no 'Use when...' clause or equivalent explicit trigger guidance for 'when should Claude use it', which per the judging guidelines caps completeness at 2.	2 / 3
Trigger Term Quality	The natural term 'ingestion warnings' is present and central, but coverage is narrow and padded with technical jargon ('error-severity clusters with broad reach', 'bursts above a type's own baseline') rather than a range of plain user variations; it falls short of the 'good coverage of natural terms' anchor.	2 / 3
Distinctiveness Conflict Risk	The niche is sharply defined — a PostHog ingestion-warnings scout that 'files each actionable root cause as a report' — with distinct triggers unlikely to collide with other skills, matching the 'clear niche with distinct triggers' anchor.	3 / 3
	Total	10 / 12 Passed

Validation

87%

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 — 14 / 16 Passed

Validation for skill structure

Criteria	Description	Result
metadata_version	'metadata.version' is missing	Warning
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	14 / 16 Passed

Repository: PostHog/posthog
Path: products/signals/skills/signals-scout-ingestion-warnings/SKILL.md
Commit: 99982fd

Reviewed: 10 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.