paper-tweet-generator

Generates a structured reading tweet from an academic paper (PDF, Word, or Text), highlighting specific product advantages. Use when the user wants to turn a document into a social media post or reading summary.

Quality

71%

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 ./scientific-skills/Other/paper-tweet-generator/SKILL.md

Quality

Content

60%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 body delivers a clear, actionable workflow backed by real scripts and a genuine reference file, with decent structure and progressive disclosure. Its main weakness is substantial generic template boilerplate that inflates token usage without adding skill-specific value.

Suggestions

Remove or condense the generic template sections ('When to Use', 'Implementation Details', 'Required Inputs', 'Output Contract', 'Validation and Safety Rules', 'Failure Handling') to skill-specific content, since they currently restate generic guidance Claude already applies.

Delete the 'Key Features' bullet that merely re-quotes the frontmatter description, and the 'See ## Workflow above' placeholder under Implementation Details.

Tighten the Workflow's section-generation step by referencing the specific prompt headings in references/prompt_templates.md (Basic Info, Background, Results, Conclusion) rather than describing them abstractly.

Dimension	Reasoning	Score
Conciseness	Roughly half the body is generic template boilerplate ('When to Use', 'Implementation Details', 'Required Inputs', 'Output Contract', 'Validation and Safety Rules', 'Failure Handling') that restates skill-agnostic guidance and even re-quotes the description in 'Key Features'. This is noticeably padded rather than merely tighten-able, placing it below the 3 anchor.	2 / 5
Actionability	The workflow gives concrete, executable commands (`python scripts/extract_text.py <file_path> extracted_content.txt`, Glob patterns, `Read extracted_content.txt`) and points to real scripts and reference files, with only minor gaps (the LLM section-generation steps remain abstract). It is above the 3 anchor but not fully copy-paste complete like the 5 anchor.	4 / 5
Workflow Clarity	A clear 3-step sequenced workflow with sub-steps and validation/error checkpoints (stderr checks, 'Warning: No text extracted' handling, fallback). This is not a destructive/batch operation so the cap does not apply; it sits above 3 but lacks the tight validate->fix->retry feedback loop of the 5 anchor.	4 / 5
Progressive Disclosure	Detail is appropriately offloaded one level deep to real bundle files (`references/prompt_templates.md`, `scripts/extract_text.py`, `scripts/extract_pdf.py`) which are all present and referenced from the body, with a clear overview. It stays below 5 because of the inline generic boilerplate that adds organizational bulk without navigation value.	4 / 5
	Total	14 / 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.

The description clearly states what the skill does and when to use it, with concrete formats and a specific deliverable. It is well-written in third person with natural trigger terms, suffering only minor gaps in keyword specificity and a slight overlap risk with generic summarization skills.

Dimension	Reasoning	Score
Specificity	Names the domain (academic paper) and several concrete elements ('structured reading tweet', 'PDF, Word, or Text', 'highlighting specific product advantages'), with only minor gaps in coverage. It is above the 3 anchor (which expects just 1-2 actions) but not fully comprehensive like the 5 anchor.	4 / 5
Completeness	Explicitly answers both 'what' ('Generates a structured reading tweet from an academic paper...') and 'when' ('Use when the user wants to turn a document into a social media post or reading summary') with concrete trigger phrases, matching the 5 anchor.	5 / 5
Trigger Term Quality	Includes natural terms users would say ('document', 'social media post', 'reading summary', 'PDF', 'Word') with good coverage, but omits file extensions (.pdf/.docx) and some synonyms, keeping it just below the 5 anchor.	4 / 5
Distinctiveness Conflict Risk	The academic-paper-to-reading-tweet niche is mostly distinct with clear triggers, but the 'turn a document into a social media post or reading summary' phrasing carries minor overlap risk with general summarization skills, so it sits below the 5 anchor.	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
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/paper-tweet-generator/SKILL.md
Commit: 63c61d3

Reviewed: 10 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.