presenting-conference-talks

Generates conference presentation slides (Beamer LaTeX PDF and editable PPTX) from a compiled paper with speaker notes and talk script. Use when preparing oral talks, spotlight presentations, or invited talks for ML and systems conferences.

Quality

92%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Low

Low-risk findings worth noting

Quality

Content

85%

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

The body is highly actionable with a clear sequenced workflow and well-structured progressive disclosure pointing to a real reference file. Its main weakness is conciseness — the inline slide-structure listings and code snippets could be trimmed since full templates already live in the reference.

Suggestions

Move the full per-talk-type slide-by-slide structure listings (poster/spotlight/oral/invited) into references/slide-templates.md and keep only a compact summary table in SKILL.md to reduce inline verbosity.

Replace the inline abbreviated Beamer and python-pptx code blocks with a one-line pointer to the reference templates, since the complete versions already live there.

Trim explanatory prose such as the 'Advantages:' lines under each output format, which state properties Claude can reasonably infer.

Dimension	Reasoning	Score
Conciseness	Content is mostly efficient and domain-specific, but the full per-talk-type slide-by-slide structure listings and inline Beamer/PPTX snippets add length that could be tightened or offloaded to the reference file.	2 / 3
Actionability	Provides copy-paste-ready Beamer and python-pptx code, concrete commands (latexmk -pdf slides.tex, python3 generate_slides.py), and explicit per-slide structure templates — fully executable guidance.	3 / 3
Workflow Clarity	A clear four-step workflow (Content Extraction → Outline → Slide-by-Slide → Review and Polish) is paired with a verification Quick Checklist and a Common Issues and Solutions table giving error-recovery feedback loops.	3 / 3
Progressive Disclosure	SKILL.md is an overview with a single clearly-signaled one-level-deep reference (references/slide-templates.md, confirmed to exist with the full templates) and no nested indirection.	3 / 3
	Total	11 / 12 Passed

Description

100%

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, complete, and uses natural trigger terms with an explicit 'Use when' clause, hitting all four anchors at the top level. No vague fluff or over-claims are present.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions — 'Generates conference presentation slides (Beamer LaTeX PDF and editable PPTX) ... with speaker notes and talk script' — naming distinct deliverables rather than vague verbs.	3 / 3
Completeness	Explicitly answers both what ('Generates ... slides ... with speaker notes and talk script') and when ('Use when preparing oral talks, spotlight presentations, or invited talks'), with an explicit trigger clause.	3 / 3
Trigger Term Quality	Covers natural user phrasing — 'oral talks, spotlight presentations, or invited talks for ML and systems conferences' — the vocabulary a presenter would actually use when requesting this skill.	3 / 3
Distinctiveness Conflict Risk	Niche is narrow (conference talks from a compiled paper) with venue- and talk-type-specific triggers, clearly separable from adjacent skills like paper writing or plotting.	3 / 3
	Total	12 / 12 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
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	15 / 16 Passed

Repository: Orchestra-Research/AI-Research-SKILLs
Path: 20-ml-paper-writing/presenting-conference-talks/SKILL.md
Commit: 773a529

Reviewed: about 12 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.