abstract-summarizer

Transform lengthy academic papers into concise, structured 250-word abstracts.

Quality

46%

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/Academic Writing/abstract-summarizer/SKILL.md

Quality

Content

38%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 skill provides concrete examples and useful checklists but is padded with generic boilerplate and, critically, its file references and code imports point mostly to scripts/references that are not bundled, undermining both actionability and progressive disclosure. Fixing the bundle/reference alignment and trimming boilerplate would materially raise the score.

Suggestions

Align references with the actual bundle: either ship the listed files (quantitative_checklist.md, disciplinary_guidelines.md, summarizer.py, etc.) or correct the References/Scripts lists to the real files (abstract-templates.md, evaluation-rubric.md, example-abstracts/cs-and-biomed-examples.md, main.py).

Make code examples executable against the shipped code: either include the modules imported (scripts.summarizer, scripts.batch) or rewrite examples to use only scripts/main.py with its real flags.

Remove or compress the generic boilerplate sections (Output Requirements, Response Template, Input Validation, Error Handling, duplicated py_compile blocks) and add an explicit validate-then-retry checkpoint to the batch workflow so it can score above 3.

Dimension	Reasoning	Score
Conciseness	The body is noticeably verbose with several padded/generic boilerplate sections (Output Requirements, Response Template, Input Validation, Error Handling, Implementation Details) plus duplicated py_compile instructions across Quick Check, Audit-Ready Commands, and Example Usage; this fits the 'noticeably verbose; several unnecessary explanations or padded sections' anchor rather than the mostly-efficient 3.	2 / 5
Actionability	Concrete code and CLI commands are present, but the Python examples import 'scripts.summarizer' and 'scripts.batch' modules that do not exist in the bundle and the referenced scripts (summarizer.py, batch_processor.py, etc.) are absent, so the guidance is incomplete and not actually executable against the shipped files, matching the 'incomplete / missing key details' anchor.	3 / 5
Workflow Clarity	A 5-step Workflow and a pre/during/post Quality Checklist provide a sequence, but the batch-processing path (BatchProcessor.summarize_directory) has no validation checkpoints and the referenced validator.py does not exist; per the batch-operations cap, workflow clarity cannot exceed 3, which it sits at exactly.	3 / 5
Progressive Disclosure	The References section lists 5 files and Scripts lists 6, but most do not exist in the bundle; actual files (abstract-templates.md, evaluation-rubric.md, example-abstracts/) are either name-mismatched or unreferenced, and substantial detail (code, field tables) is inlined rather than split out, matching the 'references buried/broken, content that belongs in separate files is inlined' anchor.	2 / 5
	Total	10 / 20 Passed

Description

53%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 is specific and clearly conveys the skill's purpose but omits any 'when to use' trigger guidance, which caps completeness at 3 and limits distinctiveness. Adding an explicit 'Use when...' clause with natural trigger phrases would raise the weakest dimensions.

Suggestions

Append an explicit trigger clause, e.g. 'Use when the user needs to summarize a research paper, write a structured abstract, or condense academic literature into ~250 words.'

Add natural synonyms users say ('research papers', 'literature', 'summarize') alongside 'academic papers' to broaden trigger coverage.

Optionally list 1-2 more concrete actions (e.g. extract quantitative findings, batch-summarize a literature set) to lift specificity toward 4-5.

Dimension	Reasoning	Score
Specificity	The phrase 'Transform lengthy academic papers into concise, structured 250-word abstracts' names a clear domain (academic papers) and one concrete action (producing structured 250-word abstracts), but offers no broader coverage of multiple actions, matching the '1-2 concrete actions' anchor rather than the several-actions anchor at 4.	3 / 5
Completeness	It gives a clear 'what' (transform papers into 250-word abstracts) but no 'when'/'Use when' clause at all, so per the missing-trigger-guidance cap it cannot exceed 3; it lands exactly on the 'clear what, missing when' anchor.	3 / 5
Trigger Term Quality	Natural terms like 'academic papers' and 'abstracts' are present, but common variations users actually say ('summarize this paper', 'research paper', 'literature review', 'write an abstract') are missing, fitting the 'some relevant keywords but missing variations' anchor.	3 / 5
Distinctiveness Conflict Risk	The 'academic papers' + 'structured 250-word abstracts' niche is mostly distinct with only minor overlap risk against general summarization skills; it does not reach 5 because there are no explicit trigger phrases to lock in the niche.	4 / 5
	Total	13 / 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/Academic Writing/abstract-summarizer/SKILL.md
Commit: 63c61d3

Reviewed: 2 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.