Name: signals-scout-error-tracking
Rating: 63.2 (1 reviews)
Author: PostHog

signals-scout-error-tracking

Signals scout for PostHog error tracking. Watches `$exception` bursts, stuck loops, multi- fingerprint clusters, and status regressions.

Quality

76%

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

Fix and improve this skill with Tessl

tessl review fix ./products/signals/skills/signals-scout-error-tracking/SKILL.md

Quality

Content

82%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 content is a tightly operational, instruction-only scout playbook with concrete tool calls, key conventions, and a well-sequenced workflow with explicit checkpoints. Its chief weaknesses are minor repetition of the edit-vs-author rule and the external contract reference, and a slightly long body that leans on a sibling-skill reference rather than local bundle files.

Suggestions

Consolidate the edit-vs-author rule and the report-contract reference to a single authoritative statement to reduce repetition across the intro, Explore, and Decide sections.

Consider pulling the recurring report-channel mechanics into a local reference file so the body reads as a leaner overview with clearly signaled one-level-deep navigation.

Add a short explicit decision/checkpoint at the end of each Explore sub-pattern (e.g. 'if shape matches → proceed to Decide; else → Skip with note') to tighten the workflow's feedback structure.

Dimension	Reasoning	Score
Conciseness	The body is dense with domain-specific guidance Claude won't know (harness tools, key prefixes, dedupe rules) with no basic-concept padding; minor repetition ("edit, not a new report" at lines 25/47/104 and the report-contract reference cited ~4×) could be trimmed, fitting anchor 4 over 3.	4 / 5
Actionability	Exact tool calls ("query-error-tracking-issues-list", `execute-sql` with literal SQL predicates), exact scratchpad key prefixes, and quoted example entries make the guidance copy-ready; per the code-vs-instruction note, absence of code is not penalized when guidance is this actionable, matching anchor 5.	5 / 5
Workflow Clarity	A clear sequence (Quick close-out → Get oriented → Profile shape → Explore → Save memory → Decide → Close out) with explicit checkpoints (inbox check before authoring, Disqualifiers, "When to stop") is present, but there is no formal validate→fix→retry error-recovery loop, fitting anchor 4 over 5.	4 / 5
Progressive Disclosure	Report mechanics are deliberately offloaded to a one-level-deep sibling reference ("authoring-scouts → references/report-contract.md") while the body keeps the error-tracking framing, with well-organized sections; the ~130-line body and heavy re-signaling of the external reference keep it at anchor 4 rather than 5.	4 / 5
	Total	17 / 20 Passed

Description

70%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 specific and clearly distinct, naming the PostHog error-tracking domain and four concrete signal types. Its main gap is the absence of an explicit "Use when…" trigger clause, which caps completeness.

Suggestions

Add a 'Use when…' clause naming natural trigger phrases (e.g. 'Use when investigating PostHog `$exception` bursts, error spikes, stuck loops, or resolved-issue regressions').

Include plain-language synonyms like 'errors', 'crashes', and 'exceptions' alongside the technical `$exception` term to broaden trigger-term coverage.

Lead with the action verbs (detect, investigate, report) rather than a single 'watches' to make the capability set read more comprehensively.

Dimension	Reasoning	Score
Specificity	"Watches `$exception` bursts, stuck loops, multi-fingerprint clusters, and status regressions" lists four concrete signal categories, but a single verb ("watches") governs them rather than a broad action set, fitting anchor 4 not 5.	4 / 5
Completeness	The "what" is clear ("Signals scout for PostHog error tracking") but there is no "Use when…" clause or equivalent trigger guidance, which per the rubric caps completeness at 3.	3 / 5
Trigger Term Quality	"PostHog error tracking", "status regressions", and "bursts" are natural user terms, while "$exception" and "multi-fingerprint clusters" are technical; coverage is good but missing plain synonyms like errors/crashes, so anchor 4 over 3.	4 / 5
Distinctiveness Conflict Risk	"Signals scout for PostHog error tracking" with `$exception`-specific triggers carves a clear niche with minimal conflict risk, matching anchor 5.	5 / 5
	Total	16 / 20 Passed

Validation

81%

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 — 13 / 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
referenced_paths_exist	Referenced path issues: 3 missing	Warning

	Total	13 / 16 Passed

Repository: PostHog/posthog
Path: products/signals/skills/signals-scout-error-tracking/SKILL.md
Commit: 57503b8

Reviewed: 4 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.