Tessl • The package manager for agent skills

SkillPublic

signals-scout-inbox-validation

Follow-up Signals scout for the inbox itself. Attaches a check to each newly resolved report, spot-checks a couple of settled fixes with fresh probes, answers the checks it is dispatched for, and reports when a fix didn't hold, plus a gated escalation check on dismissed reports.

Quality

76%

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-inbox-validation/SKILL.md

Quality

Content

81%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 high-quality operational runbook: fully actionable with concrete tool calls, SQL, and a verdict table, and a clearly sequenced workflow with validation checkpoints and feedback loops. Its main weakness is conciseness — the dense prose repeats framing and could be trimmed without losing clarity.

Suggestions

Consolidate the repeated close-out and 'when to stop' guidance into a single section; the current treatment restates the same stop conditions in the intro, 'When to stop', and close-out steps.

Move the bulkier SQL query and the MCP tools catalog into a local reference file (e.g. references/probes.md) and summarize inline, improving progressive disclosure and token budget.

Tighten the longest sentences (e.g. step 1 of 'Attach a check', the spot-check intro) by splitting the reasoning from the instruction.

Dimension	Reasoning	Score
Conciseness	The body is dense and operational rather than padded with basics Claude already knows, but at ~200 lines it repeats framing and close-out guidance across sections and several long sentences could be tightened.	3 / 5
Actionability	Fully executable guidance throughout — exact MCP calls with arguments, runnable SQL with real table/column names, concrete memory-key formats, numeric thresholds (24h soak, ≥2×, cap ~5/2) and an observation→verdict→action table.	5 / 5
Workflow Clarity	Clear sequenced workflow (orient → attach checks → spot-check → answer dispatched check → verdict → decide → close out) with explicit validation checkpoints, a Disqualifiers checklist, and feedback loops (errored re-arm, re-validate) appropriate to a batch/report-authoring operation.	5 / 5
Progressive Disclosure	Well-organized sections with a clearly signaled one-level-deep external reference (authoring-scouts → references/report-contract.md) for the report-channel contract; the inlined SQL and MCP-tool catalog is somewhat bulky but there is no local bundle to split into.	4 / 5
	Total	17 / 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 action-rich, naming the skill's concrete behaviors comprehensively, but it omits an explicit 'Use when' trigger clause and leans on internal fleet jargon rather than natural user phrasing. Tightening trigger guidance would raise completeness and trigger-term quality.

Suggestions

Add an explicit 'Use when...' clause naming the situations that should invoke this skill (e.g. 'Use when validating that a merged fix actually stopped the problem, or when a report check needs answering').

Reintroduce user-natural synonyms alongside the internal terms (e.g. 'follow-up', 'verify the fix', 'regression after merge') to improve trigger-term quality.

Lead with the discriminator ('after a fix ships, did the problem actually stop?') before the action list so the niche reads unambiguously to a dispatcher.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions — 'Attaches a check to each newly resolved report', 'spot-checks a couple of settled fixes with fresh probes', 'answers the checks it is dispatched for', 'reports when a fix didn't hold', 'gated escalation check on dismissed reports' — covering the skill's scope comprehensively.	5 / 5
Completeness	The 'what' is clearly and concretely stated, but there is no explicit 'Use when...' or equivalent trigger clause, so per the rubric completeness is capped at 3 with 'when' only weakly implied.	3 / 5
Trigger Term Quality	Relevant domain terms exist ('resolved report', 'fix didn't hold', 'settled fixes', 'dismissed reports') but they skew toward internal jargon ('Signals scout', 'fresh probes') and lack common user-natural synonyms or variations.	3 / 5
Distinctiveness Conflict Risk	It carves a clear niche (follow-up inbox-validation scout) unlikely to trigger sibling skills, but reliance on internal jargon and the missing explicit trigger phrases introduce minor overlap risk with other scouts.	4 / 5
	Total	15 / 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-inbox-validation/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-inbox-validation

Table of Contents

Is this your skill?