talk-groetzinger-skills-everywhere

Skills Everywhere: Pipelining Knowledge Your Engineers Can Read and Your Agents Can Use

Quality

17%

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 ./talk-groetzinger-skills-everywhere/SKILL.md

Quality

Content

35%Scale 1-3

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

This skill is a talk-reference guide that is well-intentioned but significantly over-engineered for its purpose. The six use-case workflows repeat the same core pattern (consult outline.md → read transcript.md → quote verbatim → cite lines) with minor variations, creating substantial redundancy. The grounding rules are valuable but the body content could be reduced by 60-70% without losing any actionable information.

Suggestions

Consolidate the six nearly identical workflow sections into a single 'Core workflow' (outline.md → transcript.md → verbatim quote → cite lines) plus a brief table mapping use-case triggers to any additional steps unique to that case.

Remove instructions that describe capabilities Claude already has (e.g., 'read the file first', 'answer using quotes', 'say so if not found') and focus only on domain-specific constraints like the speaker attribution rules and speech-to-text artifact handling.

Add a concrete example of a well-formed answer (e.g., a sample Q&A exchange showing the expected quote format, line citation style, and attribution phrasing) to make the skill more actionable.

If bundle files (outline.md, transcript.md, quotes.md) exist, include them in the bundle so progressive disclosure can be properly evaluated; if they don't exist, remove references to them.

Dimension	Reasoning	Score
Conciseness	The skill is extremely verbose, with extensive procedural instructions for multiple use-case categories that largely describe how to do things Claude already knows (look up a transcript, quote verbatim, cite line numbers). The repeated 'read outline.md then transcript.md then quote verbatim' pattern across six nearly identical workflow sections is highly redundant. Much of this could be condensed to a short set of grounding rules plus a brief table of use-case triggers.	1 / 3
Actionability	The skill provides concrete procedural steps (read outline.md, find section, quote verbatim, cite line ranges) and specific file references, which is somewhat actionable. However, there are no executable code examples, no concrete output formats, and the guidance is largely process description rather than copy-paste-ready instructions. The audit workflow dimensions are listed but not given as a structured checklist.	2 / 3
Workflow Clarity	Each use-case section has numbered steps with a clear sequence, which is good. However, there are no validation checkpoints or feedback loops — for example, no step to verify that a quote actually appears in the transcript before presenting it, or to confirm the outline.md lookup succeeded. The workflows are sequential but lack error-recovery guidance.	2 / 3
Progressive Disclosure	The skill references supporting files (outline.md, transcript.md, quotes.md) which suggests a bundle structure, but no bundle files were provided, making it impossible to verify the references work. The SKILL.md itself is monolithic — six detailed workflow sections are inlined rather than being split into separate reference files. The quotes.md reference for pre-extracted highlights is a good progressive disclosure pattern, but the overall body is too long for what could be a concise overview with pointers.	2 / 3
	Total	7 / 12 Passed

Description

0%Scale 1-3

Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.

This description reads like a conference talk title or marketing slogan rather than a functional skill description. It contains no concrete actions, no trigger terms, no 'Use when...' guidance, and no specificity about what the skill actually does. It would be essentially unusable for skill selection among even a small set of skills.

Suggestions

Replace the tagline with concrete actions describing what this skill does (e.g., 'Creates reusable skill files from engineering documentation and pipeline configurations').

Add an explicit 'Use when...' clause with natural trigger terms that describe when Claude should select this skill (e.g., 'Use when the user asks to create skill files, convert documentation to agent-readable formats, or set up knowledge pipelines').

Remove marketing language like 'Skills Everywhere' and 'Pipelining Knowledge' and replace with specific, actionable descriptions that distinguish this skill from others.

Dimension	Reasoning	Score
Specificity	The description contains no concrete actions whatsoever. It reads like a marketing tagline or blog post title rather than a functional skill description. There are no verbs describing what the skill actually does.	1 / 3
Completeness	Neither 'what does this do' nor 'when should Claude use it' is answered. There is no 'Use when...' clause and no description of capabilities. Both dimensions are entirely missing.	1 / 3
Trigger Term Quality	The terms 'pipelining', 'knowledge', 'engineers', and 'agents' are abstract buzzwords that users would not naturally use when requesting a specific task. No natural trigger keywords are present.	1 / 3
Distinctiveness Conflict Risk	The description is so vague and generic that it could apply to virtually anything involving knowledge management, documentation, or agent workflows. It provides no clear niche or distinct triggers.	1 / 3
	Total	4 / 12 Passed

Validation

100%

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 — 11 / 11 Passed

Validation for skill structure

No warnings or errors.

Repository: AINativeDev/aidevcon-2026-ldn
Path: talk-groetzinger-skills-everywhere/SKILL.md
Commit: 1887349

Reviewed: ~2 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.