talk-dubnov-merge-rate-ai-adoption

Answers questions about, applies frameworks from, and generates artifacts based on Tammuz Dubnov's talk "When Our PM Started Writing Code: What Merge Rate Taught Us About AI Adoption." Grounds every response in the bundled transcript and outline files. Use when a user asks about AI-native org design, merge rate measurement, non-technical contributors shipping PRs, harness engineering, zero-dev-touch rate, AI adoption ROI, or wants to audit their team against Tammuz's framework, apply his concepts to their situation, draft a measurement dashboard or checklist, or understand terms like Calamarous Coding and the PM-to-engineer authority collapse.

Quality

83%

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

Quality

Content

71%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 well-structured reference skill body with actionable templates and a clear grounding workflow. Its main weakness is that the referenced bundle files (outline.md, transcript.md, quote.md) are absent, undermining progressive disclosure, and a few sections slightly overlap the description.

Suggestions

Include the referenced bundle files (outline.md, transcript.md, quote.md) in the skill bundle so the grounding workflow's file lookups actually resolve.

Tighten the 'Key Concepts from the Talk' list to avoid re-listing trigger terms already present in the description, or move fuller definitions into outline.md.

Add an explicit fix-and-retry branch to the Grounding Workflow for when a candidate quote fails the verbatim-verification step (e.g., re-scan transcript.md for the exact wording before quoting).

Dimension	Reasoning	Score
Conciseness	Mostly lean and assumes Claude's competence, but the 'Key Concepts from the Talk' bullet list partially duplicates trigger terms already in the description and could be trimmed without losing routing value.	4 / 5
Actionability	Provides concrete, specific guidance — a numbered grounding workflow, named dashboard fields ('non-technical PR count', 'merge rate', 'zero-dev-touch rate', 'review latency'), and a checklist row template — though it is instruction-only with no executable code, which is appropriate for a reference skill.	4 / 5
Workflow Clarity	The Grounding Workflow is a clear five-step sequence with an explicit validation checkpoint (step 4: verify quoted phrases appear verbatim) and a partial-answer handling step (step 5), but lacks a defined fix-and-retry loop if verification fails.	4 / 5
Progressive Disclosure	Structure is well-organized with clearly signaled one-level-deep references to outline.md, transcript.md, and quote.md, but those referenced bundle files are not present in the review directory, so the disclosed navigation is effectively broken.	3 / 5
	Total	15 / 20 Passed

Description

95%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-constructed description that clearly states capability, grounds usage in bundled sources, and provides rich, distinctive trigger phrases. The only minor gap is that the action verbs are slightly generic rather than maximally concrete.

Dimension	Reasoning	Score
Specificity	Names the domain (Tammuz Dubnov's talk) and three concrete actions — 'Answers questions about, applies frameworks from, and generates artifacts based on' — plus 'Grounds every response in the bundled transcript and outline files', but the verbs are somewhat generic rather than exhaustively enumerated.	4 / 5
Completeness	Explicitly answers both 'what' (answers/applies/generates/grounds) and 'when' via a concrete 'Use when a user asks about...' clause listing multiple trigger scenarios.	5 / 5
Trigger Term Quality	Comprehensive natural trigger coverage including synonyms and talk-specific terms a user would actually say: 'AI-native org design, merge rate measurement, non-technical contributors shipping PRs, harness engineering, zero-dev-touch rate, AI adoption ROI', 'Calamarous Coding', and 'PM-to-engineer authority collapse'.	5 / 5
Distinctiveness Conflict Risk	Occupies a clear niche tied to one specific talk with highly distinctive triggers (Calamarous Coding, PM-to-engineer authority collapse), making conflict with other skills minimal.	5 / 5
	Total	19 / 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-dubnov-merge-rate-ai-adoption/SKILL.md
Commit: a3808a9

Reviewed: ~4 hours 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.