conference-tweet-generator

Generates academic conference tweets and summaries by filtering abstracts, translating content, and creating engaging titles. Use when you need to process conference abstracts into social media content.

Quality

60%

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

Fix and improve this skill with Tessl

tessl review fix ./scientific-skills/Other/conference-tweet-generator/SKILL.md

Quality

Content

46%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.

The core workflow is concrete and the bundle references are real and clearly signaled, but the SKILL.md is weighed down by extensive generic boilerplate and lacks inline validation for a batch operation. Tightening the padding and adding a worked output example would materially raise quality.

Suggestions

Strip the generic boilerplate sections ('Implementation Details', 'Deterministic Output Rules', 'Completion Checklist', etc.) that restate obvious process guidance, keeping only the Workflow, Requirements, and Output Contract.

Add one fully worked example: a sample abstract → the generated structured summary and the 3 tweet titles in 'Year Conference | Content' format.

Insert an explicit validation checkpoint inside the workflow (e.g. after filtering, verify each retained abstract has Background/Methods/Results/Conclusion before translating) rather than relegating validation to a separate generic section.

Dimension	Reasoning	Score
Conciseness	The body is padded with generic boilerplate ('Use this skill when the request matches its documented task boundary', 'Execution model: validate the request, choose the packaged workflow, and produce a bounded deliverable') and several redundant sections that add no domain-specific value beyond the concise Workflow block.	2 / 5
Actionability	The workflow gives concrete specifics — use `tavily_search`, extract Background/Methods/Results/Conclusion, titles in 'Year Conference \| Content' format, consult `references/drug_dictionary.md` — but lacks a worked example tweet/summary and leaves the abstract-filtering criterion vague, so guidance is incomplete.	3 / 5
Workflow Clarity	The five steps are clearly sequenced, but this is a batch abstract-processing workflow with no inline validation checkpoints between steps; per the batch-operation rule, the generic 'Validation and Safety Rules' boilerplate does not lift it above 3.	3 / 5
Progressive Disclosure	References are real and well-signaled one level deep (`references/drug_dictionary.md`, `scripts/validate_skill.py` are both invoked in the body), with most content appropriately placed; the main gap is inlined generic boilerplate that bloats rather than earns separation.	4 / 5
	Total	12 / 20 Passed

Description

75%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 solid, third-person description that pairs concrete capabilities with an explicit trigger, sitting comfortably above midpoint but short of the fully comprehensive anchor. The main gap is trigger-phrase breadth rather than structure.

Suggestions

Broaden the trigger clause to enumerate concrete user phrasings, e.g. 'Use when turning conference abstracts into tweets, X/Threads posts, or social media summaries.'

Surface the meeting-search step ('searches for conference background') so the capability list is more comprehensive.

Add file/extension-style signal terms where relevant (e.g. abstract lists, .txt/.csv inputs) to sharpen trigger matching.

Dimension	Reasoning	Score
Specificity	Lists several concrete actions — 'filtering abstracts, translating content, and creating engaging titles' — alongside the headline 'Generates academic conference tweets and summaries', giving good but not fully comprehensive coverage (omits the meeting-search and content-extraction steps).	4 / 5
Completeness	It answers both 'what' (generates tweets/summaries via filtering, translating, titling) and 'when' ('Use when you need to process conference abstracts into social media content'), but the trigger is a single clause rather than multiple concrete trigger phrases, falling just below the 5 anchor.	4 / 5
Trigger Term Quality	Natural terms like 'conference abstracts', 'tweets', 'summaries', and 'social media content' appear, but coverage is not exhaustive — common synonyms such as 'X posts' or 'Twitter threads' are absent.	4 / 5
Distinctiveness Conflict Risk	The academic-conference-to-social-media niche is clear and unlikely to fire for unrelated skills, though the general 'social media content' framing carries minor overlap with broader summarization skills.	4 / 5
	Total	16 / 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
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	15 / 16 Passed

Repository: aipoch/medical-research-skills
Path: scientific-skills/Other/conference-tweet-generator/SKILL.md
Commit: f5ef65b

Reviewed: ~14 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.