CtrlK
BlogDocsLog inGet started
Tessl Logo

signals-scout-logs

Signals scout for PostHog logs. Watches for emerging and rate-shifted message patterns (window-over-window deltas), volume bursts, severity-distribution shifts, service silence, and trace-correlated bursts.

53

Quality

61%

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

Fix and improve this skill with Tessl

tessl review fix ./products/signals/skills/signals-scout-logs/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

77%

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

A dense, highly actionable scouting playbook with clear sequencing and validation checkpoints, built almost entirely from non-obvious tool-specific knowledge. It loses points only on conciseness (some repeated caveats and dated scratchpad examples) and on progressive disclosure (everything is inline with no reference files).

Suggestions

Consolidate the firehose and date-footgun caveats into a single canonical callout and reference it, rather than restating them in the orientation, close-out, and tool sections.

Move the dated scratchpad examples (e.g. '2026-06-30', '2026-04-30') into a clearly labeled 'example baselines' note, since the rubric penalizes time-sensitive specifics that aren't framed as examples.

Extract the per-pattern 'Explore' details and the MCP tools catalog into a reference file, keeping SKILL.md as an overview that signals the reference one level deep.

DimensionReasoningScore

Conciseness

Mostly efficient — every tool caveat (firehose 500s, the m=month footgun, sparkline overflow) is non-obvious domain knowledge Claude lacks — but the body runs ~165 lines with some repetitive restatements of the same firehose/date-footgun warning across sections, which could be tightened.

2 / 3

Actionability

Gives concrete, executable guidance throughout — exact tool names with parameter forms (e.g. 'logs-count severityLevels=["fatal"] over 24h', 'logs-services-create over -24h') and named scratchpad key prefixes — copy-paste ready and specific.

3 / 3

Workflow Clarity

The run is clearly sequenced (orient → explore → save memory → decide → close out) with explicit validation checkpoints: dedupe-before-author via inbox-reports-list, independent corroboration before any write, and a 'When to stop' section with terminal conditions.

3 / 3

Progressive Disclosure

Well-organized with clear section headings, but no bundle files exist and all content is inline in SKILL.md; the reference-heavy MCP-tools section and the per-pattern explore details could be split into reference files for cleaner navigation.

2 / 3

Total

10

/

12

Passed

Description

45%

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 third-person but lacks any explicit 'Use when' trigger guidance and leans on internal jargon rather than natural user keywords. Per the rubric, the missing trigger clause caps completeness at 2.

Suggestions

Add an explicit trigger clause, e.g. 'Use when monitoring PostHog log volume, error-rate spikes, or fresh message patterns in a signals scout run.'

Rewrite jargon terms into plain-language keywords users would say (e.g. 'log bursts', 'error-rate spikes', 'silent services') alongside the technical phrasing.

Add a scope qualifier that distinguishes it from sibling scouts (e.g. 'the logs-scoped variant of the signals scout') to reduce conflict risk.

DimensionReasoningScore

Specificity

Lists multiple concrete actions — 'emerging and rate-shifted message patterns (window-over-window deltas), volume bursts, severity-distribution shifts, service silence, and trace-correlated bursts' — matching the multi-action anchor.

3 / 3

Completeness

Clearly states what the skill does (watches for log patterns), but there is no 'Use when...' clause or equivalent explicit trigger guidance, which the rubric caps at 2.

2 / 3

Trigger Term Quality

Uses internal jargon ('window-over-window deltas', 'trace-correlated bursts', 'rate-shifted') rather than natural keywords a user would say; no plain-language trigger terms like 'logs', 'log volume', 'error spikes'.

1 / 3

Distinctiveness Conflict Risk

The 'PostHog logs' niche is fairly specific, but a sibling 'signals scout' skill for other scopes (events, error tracking) could share near-identical triggers, so it overlaps with similar skills.

2 / 3

Total

8

/

12

Passed

Validation

87%

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

Validation14 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

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
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.