abstract-summarizer
Transform lengthy academic papers into concise, structured 250-word abstracts.
36
33%
Does it follow best practices?
Impact
—
No eval scenarios have been run
Advisory
Suggest reviewing before use
Optimize this skill with Tessl
npx tessl skill review --optimize ./scientific-skills/Academic Writing/abstract-summarizer/SKILL.mdQuality
Discovery
32%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 concise and identifies a clear task—transforming academic papers into structured abstracts—but it lacks a 'Use when...' clause, which is critical for Claude to know when to select this skill. It also misses common trigger term variations and could benefit from listing additional specific capabilities beyond just generating abstracts.
Suggestions
Add a 'Use when...' clause with explicit triggers, e.g., 'Use when the user asks to summarize a research paper, generate an abstract, or condense an academic article.'
Include natural keyword variations users might say, such as 'research paper', 'journal article', 'summarize', 'manuscript', 'paper summary', or 'conference abstract'.
List additional specific capabilities beyond abstract generation, such as 'identifies key findings, methods, and conclusions' or 'follows structured abstract formats (background, methods, results, conclusion)'.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Names the domain (academic papers) and a specific action (transform into 250-word abstracts), but only describes a single action rather than listing multiple concrete capabilities like formatting options, citation handling, or section-specific summarization. | 2 / 3 |
Completeness | Describes what the skill does (transform papers into abstracts) but completely lacks a 'Use when...' clause or any explicit trigger guidance for when Claude should select this skill. Per the rubric, a missing 'Use when...' clause caps completeness at 2, and since the 'when' is entirely absent, this scores a 1. | 1 / 3 |
Trigger Term Quality | Includes relevant terms like 'academic papers' and 'abstracts' that users might naturally say, but misses common variations such as 'research paper', 'journal article', 'summary', 'summarize', 'paper abstract', or 'manuscript'. | 2 / 3 |
Distinctiveness Conflict Risk | The focus on academic papers and abstracts provides some specificity, but it could overlap with general summarization skills or other academic writing tools. The 250-word constraint adds some distinctiveness but isn't enough to fully differentiate it. | 2 / 3 |
Total | 7 / 12 Passed |
Implementation
35%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This skill suffers from significant bloat with generic boilerplate sections (Error Handling, Input Validation, Response Template, Output Requirements) that are not specific to abstract summarization and waste context window tokens. The domain-specific content (structured abstract format, quantitative preservation, discipline adaptation, quality checklist, common pitfalls) is genuinely useful but is buried under layers of generic scaffolding. The code examples reference scripts that aren't provided, making actionability questionable.
Suggestions
Remove generic boilerplate sections (Error Handling, Input Validation, Response Template, Output Requirements) that apply to any skill and don't add abstract-summarization-specific value — this alone would cut ~30% of tokens.
Consolidate the scattered workflow content (Example Usage run plan, Workflow section, Quality Checklist) into a single clear numbered workflow with inline validation checkpoints, especially around the critical number-verification step.
Either provide the actual script implementations in the bundle or remove the Python API examples that reference non-existent modules (scripts/summarizer.py, scripts/batch.py) and focus on instructing Claude how to perform summarization directly.
Move the detailed tables (field-specific handling), parameter reference, and common pitfalls into separate reference files to keep SKILL.md as a concise overview with pointers.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The skill is extremely verbose at ~300+ lines, with massive amounts of boilerplate and generic scaffolding (Response Template, Output Requirements, Input Validation, Error Handling sections) that add no domain-specific value. It explains concepts Claude already knows, repeats itself across sections (e.g., 'Workflow' and 'Example Usage' overlap significantly), and includes generic meta-instructions like 'Do not fabricate files, citations, data' that waste tokens. | 1 / 3 |
Actionability | The skill provides Python code examples and CLI commands that appear concrete, but they reference modules (scripts/summarizer.py, scripts/batch.py) whose actual implementations are not provided in any bundle. The code examples look like API documentation for a library that may not exist, making them not truly executable. The CLI examples and structured abstract format are somewhat actionable. | 2 / 3 |
Workflow Clarity | There are multiple workflow-like sections (Example Usage run plan, Workflow section, Quality Checklist) but they are scattered and partially redundant. The Quality Checklist provides good validation checkpoints, but the main Workflow section is generic boilerplate with no domain-specific steps. There's no clear feedback loop for the critical step of verifying numbers match the source document, despite it being marked as CRITICAL. | 2 / 3 |
Progressive Disclosure | The skill references files in references/ and scripts/ directories with clear listings, which is good structure. However, no bundle files are provided to verify these exist, and the main SKILL.md itself is monolithic with too much inline content that could be split out. The 'Implementation Details' section says 'See ## Workflow above' which is a self-referential loop within the same file rather than meaningful progressive disclosure. | 2 / 3 |
Total | 7 / 12 Passed |
Validation
90%Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.
Validation — 10 / 11 Passed
Validation for skill structure
| Criteria | Description | Result |
|---|---|---|
frontmatter_unknown_keys | Unknown frontmatter key(s) found; consider removing or moving to metadata | Warning |
Total | 10 / 11 Passed | |
- Repository
- aipoch/medical-research-skills
- Commit
73f6514
- 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.