CtrlK
BlogDocsLog inGet started
Tessl Logo

making-academic-presentations

Create academic presentation slide decks and optionally demo videos from research papers. Use when the user asks to "make slides", "create a deck", "make a presentation", "demo video", "paper slides", "conference talk slides", or wants to turn a paper into a visual presentation. Covers slide generation, narration scripts, TTS audio, and video assembly.

70

Quality

85%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

SecuritybySnyk

Low

Low-risk findings worth noting

SKILL.md
Quality
Evals
Security

Quality

Content

80%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, highly actionable skill body with strong progressive disclosure and concrete executable guidance. The main gap is the absence of explicit validation/verification checkpoints for the batch TTS and video-assembly stages, which the rubric caps at workflow_clarity 3 for batch operations.

Suggestions

Add an explicit validation checkpoint after video assembly, e.g. probe the concatenated output with `ffprobe` to confirm sample rate/stereo/AAC match before declaring success.

Insert a verify step into the batch TTS workflow (check every expected MP3 exists and is non-empty) so the batch pipeline has a feedback loop.

Trim the inline edge-tts quick-start snippet since the same code is fully covered in references/tts-engines.md, keeping the body purely as a pointer.

DimensionReasoningScore

Conciseness

Largely lean and assumes competence — pipeline diagram, tables, and code blocks earn their place — with only minor instances of restating reference content inline (e.g., the TTS quick-start snippet duplicates the reference).

4 / 5

Actionability

Copy-paste-ready code and commands throughout: executable ffmpeg invocations, a runnable edge-tts snippet, concrete nanobanana /edit usage, and install commands for every dependency.

5 / 5

Workflow Clarity

The 4-stage pipeline is clearly sequenced, but batch/destructive operations (batch TTS, ffmpeg concat, overwriting outputs with -y) lack explicit validation checkpoints — the "always re-encode" gotcha is stated as a rule but no verify-after step is built into the workflow, capping clarity at 3 per the batch-operation rule.

3 / 5

Progressive Disclosure

Clear overview body with well-signaled, one-level-deep references to real files (slide-generation.md, tts-engines.md, pptx-conversion.md) plus batch scripts in scripts/, all referenced with exact paths and none nested beyond one level.

5 / 5

Total

17

/

20

Passed

Description

91%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 with concrete capabilities, a rich set of natural trigger phrases, and explicit what-and-when guidance in third person. The only mild weakness is that the listed actions are somewhat broad categories and the triggers could marginally overlap a generic presentation tool.

Suggestions

Tighten the capability list from broad categories ("slide generation, narration scripts") to a couple of more concrete verbs to push specificity toward 5.

Add a distinguishing qualifier such as "from research papers / academic sources" earlier in the first sentence to further reduce overlap with generic slide skills.

DimensionReasoningScore

Specificity

Lists several concrete actions — "slide generation, narration scripts, TTS audio, and video assembly" — and names the domain clearly, though the actions are broad categories rather than maximally granular.

4 / 5

Completeness

Explicitly answers both — "what" (create academic slide decks and optionally demo videos from research papers; covers slide generation, narration, TTS, video assembly) and "when" via a concrete "Use when the user asks to..." clause with multiple trigger phrases.

5 / 5

Trigger Term Quality

Comprehensive natural triggers with synonyms and phrasings users actually say: "make slides", "create a deck", "make a presentation", "demo video", "paper slides", "conference talk slides".

5 / 5

Distinctiveness Conflict Risk

The academic-papers-to-decks niche is fairly distinct with specific triggers, but general presentation terms could overlap with a generic slide-editing skill; minimal rather than zero conflict risk.

4 / 5

Total

18

/

20

Passed

Validation

100%

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository
OpenLAIR/dr-claw
Reviewed

Table of Contents

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.