academic-abstract-refiner
Refines long medical academic texts into SCI-style unstructured Chinese and English abstracts; use when you need to condense drafts/reports/summaries into bilingual abstracts and generate Summary_Report.md.
57
48%
Does it follow best practices?
Impact
Pending
No eval scenarios have been run
Passed
No known issues
Optimize this skill with Tessl
npx tessl skill review --optimize ./scientific-skills/Academic Writing/academic-abstract-refiner/SKILL.mdQuality
Discovery
75%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 reasonably well-constructed with a clear 'use when' clause and a distinctive niche combining medical academic writing, SCI-style abstracts, and bilingual output. Its main weaknesses are moderate specificity in listing concrete actions and limited coverage of natural trigger terms users might employ when seeking this skill.
Suggestions
Add more specific concrete actions such as 'structures Background, Methods, Results, and Conclusions sections' or 'formats per target journal guidelines' to improve specificity.
Expand trigger terms to include common user phrases like 'paper abstract', 'journal abstract', 'manuscript summary', 'research paper summary', or 'scientific writing' to improve discoverability.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | The description names the domain (medical academic texts, SCI-style abstracts) and mentions some actions (refines, condense, generate Summary_Report.md), but doesn't list multiple concrete actions in detail—e.g., it doesn't specify structuring sections like Background/Methods/Results/Conclusions or formatting conventions. | 2 / 3 |
Completeness | The description clearly answers both 'what' (refines long medical academic texts into SCI-style unstructured Chinese and English abstracts) and 'when' (use when you need to condense drafts/reports/summaries into bilingual abstracts and generate Summary_Report.md), with an explicit 'use when' clause. | 3 / 3 |
Trigger Term Quality | Includes some relevant keywords like 'SCI-style', 'abstracts', 'bilingual', 'medical academic texts', 'Summary_Report.md', but misses common user variations such as 'paper abstract', 'manuscript summary', 'journal abstract', 'research paper', or 'scientific writing'. | 2 / 3 |
Distinctiveness Conflict Risk | The combination of medical academic texts, SCI-style formatting, bilingual Chinese/English abstracts, and the specific output file Summary_Report.md creates a very distinct niche that is unlikely to conflict with other skills. | 3 / 3 |
Total | 10 / 12 Passed |
Implementation
22%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This skill is heavily padded with generic, reusable boilerplate sections (failure handling, safety rules, completion checklists, deterministic output rules) that add no skill-specific value and waste token budget. The actual unique content—a simple script that writes two strings into a markdown file—is buried under verbose scaffolding. The core intellectual task of refining medical text into SCI-style abstracts lacks any concrete guidance, examples, or workflow steps.
Suggestions
Remove all generic boilerplate sections (Failure Handling, Validation and Safety Rules, Deterministic Output Rules, Completion Checklist, Output Contract) that describe behaviors Claude already knows—this could cut the file by 60%+.
Add a concrete, worked example showing how to take a sample medical text passage and produce both Chinese and English unstructured abstracts, with specific guidance on what to include/exclude.
Replace the generic 'Recommended Workflow' with a specific multi-step process: e.g., 1) Read source text, 2) Identify key findings/methods/conclusions, 3) Draft Chinese abstract (single paragraph, ~250 words), 4) Draft English abstract, 5) Verify no fabricated data, 6) Run the formatting script.
Add a concrete example of a well-formed Summary_Report.md output showing the expected markdown structure with realistic medical abstract content.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The skill is extremely verbose and padded with generic boilerplate sections (Failure Handling, Validation and Safety Rules, Deterministic Output Rules, Completion Checklist) that are not specific to this skill and describe things Claude already knows how to do. The actual unique content (run a script with two string args) could be conveyed in ~20 lines. | 1 / 3 |
Actionability | There is one concrete executable command example with clear flags, but the core task—actually refining a long medical text into abstracts—has no concrete guidance. The script merely formats pre-written abstracts into markdown; the actual intellectual work (condensing text) is hand-waved as 'assumed to be completed by the agent' with no examples, prompts, or strategies provided. | 2 / 3 |
Workflow Clarity | The 'Recommended Workflow' section is entirely generic (validate inputs, select execution path, produce output, validate) with no steps specific to medical abstract refinement. There is no clear sequence for how to go from a long source text to final abstracts, no validation of abstract quality, and no feedback loop for iterating on the refinement. | 1 / 3 |
Progressive Disclosure | The content is organized with clear section headers, which aids navigation. However, it's a monolithic file with excessive inline boilerplate that should either be removed or split out, and there are no references to supplementary files for advanced usage or examples. | 2 / 3 |
Total | 6 / 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
8277276
- 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.