Tessl • The package manager for agent skills

SkillPublic

signals-scout-anomaly-detection

Signals scout that watches the project's most-viewed dashboards and insights for anomalies — bursts, drops, flat-lines, and trend breaks — against each insight's own seasonality-matched baseline.

Quality

70%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

—

The risk profile of this skill

Fix and improve this skill with Tessl

tessl review fix ./products/signals/skills/signals-scout-anomaly-detection/SKILL.md

Quality

Content

68%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 well-structured, actionable scout workflow with clear sequencing and explicit checkpoints. Its critical weakness is progressive disclosure: the skill repeatedly defers its core method, watchlist mechanics, and report contract to referenced files that are absent from the bundle.

Suggestions

Add the missing bundle files (references/anomaly-methods.md, references/watchlist-and-memory.md, references/report-contract.md, scripts/ks2.py) or inline the essential content so the skill is self-contained.

Tighten the longest parenthetical paragraphs (attribution, change-detection lens, decide-author) to improve conciseness.

Consolidate the duplicated tool glossaries — the 'Exploit' and 'MCP tools' sections both enumerate `alert-simulate`, `insight-query`, `execute-sql` — to reduce token cost.

Dimension	Reasoning	Score
Conciseness	Largely efficient and assumes Claude's competence — no padding explaining what a dashboard or z-score is — but a few sentences run long with parenthetical asides (e.g. the attribution and KS-test paragraphs) that could be trimmed.	4 / 5
Actionability	Provides concrete, named tools with specific parameters (`alert-simulate` insight/detector_config, `insight-query` filters_override with JSON examples, `dashboard-insights-run` refresh=blocking) and exact formulas (the MAD z-score), with only minor gaps in copy-paste-ready code blocks.	4 / 5
Workflow Clarity	A clear run sequence (orient → exploit → explore → save memory → decide → close out) with explicit validation checkpoints (search inbox before authoring, only score the latest complete bucket, retire-then-forget), though the destructive/batch report-write path relies on reference docs for its validation feedback loop.	4 / 5
Progressive Disclosure	The body references four bundled files (`references/anomaly-methods.md`, `references/watchlist-and-memory.md`, `references/report-contract.md`, `scripts/ks2.py`) as the spine of the skill, but none of these files exist on disk — the references are broken, leaving the actual detail unreachable.	1 / 5
	Total	13 / 20 Passed

Description

63%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 well-scoped to a distinct anomaly-detection niche, with strong natural trigger terms. Its main weakness is the absence of an explicit 'Use when...' clause, which leaves the invocation trigger only weakly implied.

Suggestions

Add an explicit trigger clause, e.g. 'Use when the signals scout should surface recent dashboard/insight anomalies' so Claude knows precisely when to invoke this skill.

Broaden trigger-term coverage with synonyms users might say ('spikes', 'metric drops', 'unusual changes') to improve natural-term matching.

Dimension	Reasoning	Score
Specificity	Names several concrete anomaly types ('bursts, drops, flat-lines, and trend breaks') and the core mechanism ('seasonality-matched baseline'), but stops short of the comprehensive action list that would earn a 5.	4 / 5
Completeness	The 'what' is clearly stated (watches dashboards/insights and surfaces anomalies against baselines), but there is no explicit 'Use when...' / trigger clause telling Claude when to invoke this scout, which caps completeness at 3.	3 / 5
Trigger Term Quality	Includes natural user-facing terms ('anomalies', 'bursts, drops, flat-lines', 'dashboards', 'insights', 'baseline') with good coverage, though it lacks synonyms/file-extension-style variations that would push it to 5.	4 / 5
Distinctiveness Conflict Risk	Targets a clear niche — PostHog Signals dashboard/insight anomaly detection with seasonality-matched baselines — with distinct triggers and minimal overlap risk against other skills.	5 / 5
	Total	16 / 20 Passed

Validation

75%

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 — 12 / 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
relative_links	Relative link issues: 11 missing	Warning
referenced_paths_exist	Referenced path issues: 24 missing	Warning

	Total	12 / 16 Passed

Repository: PostHog/posthog
Path: products/signals/skills/signals-scout-anomaly-detection/SKILL.md
Revision: 130f3a1

Reviewed: 29 days ago

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.

signals-scout-anomaly-detection

Table of Contents

Is this your skill?