talk-cormack-tests-lie-observability-ai

Use when the user asks about Justin Cormack's AI Native DevCon talk on tests, observability, AI-generated behavior, evidence, instrumentation, and keeping AI systems honest when test signals are incomplete.

Quality

78%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./Plugins/aidevcon/skills/talk-cormack-tests-lie-observability-ai/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.

A concise, well-structured reference skill with concrete grounding rules and an explicit verification checkpoint. Its main weakness is that the body depends on outline.md, quote.md, and transcript.md, which are not present in the bundle.

Suggestions

Include the referenced bundle files (outline.md, quote.md, transcript.md) under references/ so the grounding workflow is actually executable.

Consider adding a brief fallback note for when a referenced file is unavailable, so the skill degrades gracefully.

Add a short checklist under 'Apply The Talk' to make the concept-match → evidence → adapt sequence and its verification explicit.

Dimension	Reasoning	Score
Conciseness	The body is lean and purposeful: it does not explain what tests or observability are, and every section (grounding rules, safety rules, how-to-help, core concepts) earns its place with no padding.	5 / 5
Actionability	Guidance is concrete for a reference skill ('Read outline.md first', 'verify against transcript.md', 'cite the transcript line IDs', 'Mark anything beyond the talk as your own recommendation'), with specific procedures per help mode, though the referenced source files are not present in the bundle.	4 / 5
Workflow Clarity	Each help mode has a clear sequenced procedure, and there is an explicit verification checkpoint ('If the transcript does not support a claim, say that the talk does not address it'; 'verify against transcript.md when precision matters'), but there is no full error-recovery feedback loop or checklist.	4 / 5
Progressive Disclosure	The body is well-organized into clearly signaled sections and points one level deep to outline.md/quote.md/transcript.md, but those referenced bundle files are not present in references/, so the disclosure structure is partly non-functional.	4 / 5
	Total	17 / 20 Passed

Description

73%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.

A strong, well-targeted description with an explicit trigger clause and a distinct niche. The main gap is that the 'what' action is implied rather than explicitly stated alongside the explicit 'when'.

Suggestions

Add an explicit 'what' clause before the trigger, e.g. 'Answers questions about and applies Justin Cormack's AI Native DevCon talk on tests, observability... Use when the user asks about...'.

Dimension	Reasoning	Score
Specificity	The description names a concrete domain (a specific talk by a named speaker) and several specific topics ('tests, observability, AI-generated behavior, evidence, instrumentation'), but the only action implied is responding to questions about the talk rather than a list of concrete actions.	3 / 5
Completeness	The 'when' is explicit and specific ('Use when the user asks about...'), and the 'what' is implied by 'asks about', but the what-action is not stated as explicitly as anchor 5 requires.	4 / 5
Trigger Term Quality	It includes natural terms a user would say ('Justin Cormack', 'AI Native DevCon talk', 'tests', 'observability', 'evidence', 'instrumentation') with good coverage, though a few natural synonyms (e.g. 'monitoring', 'false confidence') are absent.	4 / 5
Distinctiveness Conflict Risk	It targets a clearly named niche (a specific person's talk at a specific conference) with distinct triggers, making conflict with other skills minimal.	5 / 5
	Total	16 / 20 Passed

Validation

93%

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 — 15 / 16 Passed

Validation for skill structure

Criteria	Description	Result
metadata_version	'metadata.version' is missing	Warning

	Total	15 / 16 Passed

Repository: jscraik/Agent-Skills
Path: Plugins/aidevcon/skills/talk-cormack-tests-lie-observability-ai/SKILL.md
Commit: f1f2f21

Reviewed: 5 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.