talk-groetzinger-skills-everywhere

Explains Kevin Groetzinger's Skills Everywhere talk and helps teams operationalize reusable skills: trigger design, ownership, discoverability, maintenance, quality review, and adoption loops. Use when the user asks about skill design, skill rollout, skill sprawl, shared agent instructions, or making skills reliable across a team.

Quality

82%

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

75%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-organized reference skill body: lean, instruction-dense, with clearly sequenced workflows, concrete output templates, and explicit handling of redacted-content requests. The main weakness is that the core factual workflow leans on bundle files (outline.md, quote.md, transcript.md) that are absent from the provided bundle, weakening both executability and the otherwise well-structured progressive disclosure.

Suggestions

Ship the referenced bundle files (outline.md, quote.md, transcript.md) alongside SKILL.md, or remove the Read Order references if the files are not distributed — the factual-question workflow cannot be executed without outline.md and quote.md.

Add an explicit output-quality checkpoint to the workflows (e.g., after answering a factual question, verify the answer stayed within 2-5 sentences and used the redacted bundle only) to close the workflow_clarity gap.

Trim the Examples section's "Response shape" lines, which restate guidance already covered by the Output Templates and Core Workflow sections.

Dimension	Reasoning	Score
Conciseness	The body is lean with no explanations of concepts Claude already knows — every section (Read Order, Core Workflow, Output Templates, Examples) carries instructions. Minor trim potential remains (the Examples section's "Response shape" lines partially duplicate the Output Templates), so it sits at efficient-with-minor-over rather than the every-token-earns-its-place anchor 5.	4 / 5
Actionability	For an instruction-only skill the guidance is mostly executable: numbered workflow steps, output templates with named fields (Goal, Boundaries, Review points, Evidence, Open questions), and concrete handling of redacted requests. The gap keeping it below 5 is that the factual workflow's first step ("Identify the relevant concept from `outline.md`") depends on bundle files that are not present in the provided bundle.	4 / 5
Workflow Clarity	Two clearly sequenced numbered workflows with a coverage checkpoint ("State when the bundle does not cover a requested detail") and an explicit boundary rule for operational-mechanics requests. No destructive or batch operations, so no validation cap applies; it misses 5 only because the workflows lack an explicit verify-output step beyond that coverage check.	4 / 5
Progressive Disclosure	The Read Order section signals one-level-deep references (`outline.md`, `quote.md`, `transcript.md`) with a clear per-file purpose, which matches good structure. However, scoring against the actual bundle structure as instructed: none of the three referenced files exist in the provided bundle (no references/, scripts/, or assets/ directories), so the navigation cannot be fully verified — keeping it below the anchor 5 easy-navigation bar.	4 / 5
	Total	16 / 20 Passed

Description

83%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 description: third-person voice, explicit what-and-when structure, and natural trigger phrases covering the talk-explanation and skill-operationalization use cases. The only weakness is that capability enumeration reads as topic areas rather than concrete operations, leaving minor specificity and distinctiveness gaps.

Dimension	Reasoning	Score
Specificity	"Explains Kevin Groetzinger's Skills Everywhere talk and helps teams operationalize reusable skills: trigger design, ownership, discoverability, maintenance, quality review, and adoption loops" names the domain plus several specific action areas. It falls short of 5 because the listed items are topic areas rather than fully concrete operations (compare "fill forms, merge documents, convert pages to images").	4 / 5
Completeness	Both what ("Explains ... talk and helps teams operationalize reusable skills: trigger design, ownership, ...") and when ("Use when the user asks about skill design, skill rollout, skill sprawl, shared agent instructions, or making skills reliable") are explicitly and clearly stated with concrete trigger phrases, matching the anchor 5 example structure.	5 / 5
Trigger Term Quality	"Use when the user asks about skill design, skill rollout, skill sprawl, shared agent instructions, or making skills reliable across a team" provides good natural-phrase coverage a user would actually say. A few plausible variants (e.g., "reusable prompts", "skill governance") are missing, keeping it below the comprehensive-synonym anchor 5.	4 / 5
Distinctiveness Conflict Risk	The talk-specific framing ("Kevin Groetzinger's Skills Everywhere talk") gives it a clear niche, but trigger terms like "skill design" and "shared agent instructions" have minor overlap risk with generic skill-authoring skills. Not 5 because of that residual overlap; clearly above the broad-overlap anchors 2-3.	4 / 5
	Total	17 / 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-groetzinger-skills-everywhere/SKILL.md
Commit: 8c173bc

Reviewed: 19 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.