CtrlK
BlogDocsLog inGet started
Tessl Logo

triaging-error-issues

Triage PostHog error tracking issues during a daily or on-call review. Use when the user asks "what's broken?", "what new errors do we have?", "show me top errors today", "what should I look at this morning", or wants a prioritized list of active issues to work on. Surfaces new and high-impact issues, ranks by users affected and recency, points at linked replays, and proposes next actions (investigate, assign, suppress, merge).

75

Quality

93%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

SecuritybySnyk

Low

Low-risk findings worth noting

SKILL.md
Quality
Evals
Security

Quality

Content

86%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.

A high-quality, actionable triage skill body: executable query examples, a clear multi-step workflow, and clean self-contained structure. The only room for improvement is minor tightening of a few explanatory passages.

Suggestions

Tighten the library/SDK filter bullet list (posthog-node, posthog-python, ...) into a compact reference or move to a single inline example plus a pointer, to reduce token cost for rarely-needed detail.

Trim explanatory asides like "A single bucket only gives a total, not a shape" — the volumeResolution rule alone is actionable enough.

If you want workflow_clarity at the top anchor, add one explicit verification checkpoint (e.g. "confirm candidate count is small enough to present; widen window if under ~5") so the narrow/widen decision is a named step rather than implied.

DimensionReasoningScore

Conciseness

Mostly lean with concrete JSON snippets and tight prose that assumes Claude's competence; minor over-explanation in the long library/SDK filter list and a few explanatory asides ("A single bucket only gives a total, not a shape") that could be trimmed.

4 / 5

Actionability

Provides copy-paste-ready, executable JSON query blocks for the actual MCP tools with specific parameter values, plus concrete filter guidance and a presentation template covering the common triage cases.

5 / 5

Workflow Clarity

A clearly sequenced 5-step workflow with decision guidance (new/high-impact/trending, first_seen comparison rules), but as a read-only triage/presentation skill it lacks explicit validate-fix-retry checkpoints, keeping it just below the top anchor.

4 / 5

Progressive Disclosure

Self-contained overview with well-organized sections and no bundle files; cross-links to peer skills in a Related skills section rather than nesting references, which is appropriate for a skill of this size.

5 / 5

Total

18

/

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.

A strong, well-constructed description: concrete capabilities, natural trigger phrases, explicit what-and-when guidance, and a clearly scoped niche. It hits the anchors for the top score across all four dimensions.

DimensionReasoningScore

Specificity

Lists multiple concrete actions — "Surfaces new and high-impact issues, ranks by users affected and recency, points at linked replays, and proposes next actions (investigate, assign, suppress, merge)" — giving comprehensive, specific coverage rather than vague domain naming.

5 / 5

Completeness

Explicitly answers both what (triage, surface, rank, recommend actions) and when via a concrete "Use when the user asks..." clause with specific trigger phrases.

5 / 5

Trigger Term Quality

Includes several natural phrases a user would actually say ("what's broken?", "what new errors do we have?", "show me top errors today", "what should I look at this morning"), covering synonyms and variations comprehensively.

5 / 5

Distinctiveness Conflict Risk

Occupies a clear niche (PostHog error tracking triage) with distinctive triggers unlikely to fire for unrelated skills.

5 / 5

Total

20

/

20

Passed

Validation

100%

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

Validation16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository
PostHog/posthog
Reviewed

Table of Contents

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.