Tessl • The package manager for agent skills

SkillPublic

signals-scout-conversations

Signals scout for PostHog Conversations (support inbox). Watches `$conversation_*` ticket- lifecycle events for SLA breach steps, first-response latency blowouts, backlog imbalance, and channel or assignment concentration.

Quality

80%

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-conversations/SKILL.md

Quality

Content

85%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 highly actionable and well-sequenced with strong validation checkpoints, and it respects Claude's competence without padding basics. Its main weakness is progressive disclosure: everything is inlined into a single long file with no reference files to offload detail.

Suggestions

Split the reusable SQL query library and the events/properties table into a references/ file (e.g., references/queries.md), keeping SKILL.md as an overview that links one level deep.

Move the disqualifiers list and the events schema into separate reference files and signal them clearly from the body.

Trim the repeated "empty run is a real outcome" phrasing and the emission-pipeline distinction to a single stated instance each to tighten conciseness.

Dimension	Reasoning	Score
Conciseness	The body is dense and assumes Claude's competence (no explaining of what SLA/PostHog/events are), but repeats a few themes — the "empty/nothing-meaningful run is a real outcome" line and the emission-pipeline distinction each appear multiple times — that could be trimmed without loss.	4 / 5
Actionability	Provides multiple copy-paste-ready SQL queries with concrete property names and explicit volume-guard thresholds (~15), plus specific tool calls and minimum-volume rules that cover the common operational cases.	5 / 5
Workflow Clarity	A clear sequenced run (Get oriented → Profile shape → Explore → Save memory → Decide → Close out) with explicit validation checkpoints (minimum-volume guard, same-weekday baseline, corroborate-backlog-against-ticket-state) and feedback loops (edit-on-persisting-regression, idempotent re-checks).	5 / 5
Progressive Disclosure	No bundle/reference files exist and the entire skill lives in one ~200-line SKILL.md; content that could be split out (the SQL query library, the events table, the disqualifier list) is inlined with no one-level-deep references, despite good internal section structure.	3 / 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 clearly conveys a specific, well-scoped operational niche and names concrete signals, but it omits any explicit "when to use" trigger guidance, which caps completeness. Trigger terms are domain-appropriate but somewhat jargon-heavy.

Suggestions

Add an explicit 'Use when...' clause stating when Claude should invoke this scout (e.g., 'Use when triaging PostHog Conversations support-inbox health — SLA, first-response, backlog, or routing regressions').

Soften the technical phrasing of the trigger (the `$conversation_*` token) with a user-natural synonym so it reads as something a user would actually say.

Consider adding a second action verb beyond 'Watches' (e.g., 'detects', 'reports') to better reflect the scout's report-filing behavior.

Dimension	Reasoning	Score
Specificity	Names four concrete phenomena the scout watches for ("SLA breach steps, first-response latency blowouts, backlog imbalance, and channel or assignment concentration"), but relies on a single verb ("Watches") rather than listing several distinct action verbs, keeping it just below a 5.	4 / 5
Completeness	Provides a clear "what" (watches ticket-lifecycle events for the four named signals) but has no "Use when..." or equivalent explicit trigger clause, so per the guideline completeness is capped at 3.	3 / 5
Trigger Term Quality	Includes natural domain terms like "support inbox", "SLA", "first-response", and "backlog", but leans on technical/jargon phrasing ("PostHog Conversations", "$conversation_* ticket-lifecycle events") rather than comprehensive user-natural synonyms, so it stops short of a 5.	4 / 5
Distinctiveness Conflict Risk	The niche is highly specific — a signals scout for a named product's support inbox keyed on a specific event family and four signal types — making it clearly distinct with minimal risk of triggering for the wrong skill.	5 / 5
	Total	16 / 20 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-conversations/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-conversations

Table of Contents

Is this your skill?