key-takeaways

Extracts and summarizes key takeaways from documents, meeting notes, articles, and other text content. Use when the user asks for summaries, bullet points, main points, highlights, or a TL;DR of any document or body of text. Produces structured outputs such as numbered lists, executive summaries, and action items. Supports configurable output formats including JSON export for downstream use.

Quality

68%

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/Evidence Insight/key-takeaways/SKILL.md

Quality

Content

48%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 contains genuinely useful concrete examples but is undermined by verbatim description repetition, generic boilerplate, code examples that don't match the actual bundled script, and broken reference paths. Tightening padding and aligning examples with main.py would substantially raise quality.

Suggestions

Remove the verbatim description pasted into the 'When to Use' and 'Key Features' sections and replace with concise, skill-specific guidance to cut padding.

Align code and CLI examples with the actual scripts/main.py API (KeyTakeaways.extract, no --input/--batch flags), or update main.py to support the documented interface so examples are executable.

Fix the References section to point to the real references/guidelines.md and remove the non-existent references/examples/ path, or add the missing files.

Dimension	Reasoning	Score
Conciseness	Noticeably verbose: the full frontmatter description is pasted verbatim into both the 'When to Use' and 'Key Features' sections, and several generic boilerplate sections ('Output Requirements', 'Response Template', 'Error Handling', 'Input Validation') plus a circular 'See ## Workflow above' reference add padding without skill-specific value.	2 / 5
Actionability	Concrete-looking code and CLI examples cover common cases (process, export, config, batch), but they do not match the bundled script — main.py defines KeyTakeaways.extract() with no CLI args, while the body documents Key_Takeaways.process()/export() and --input/--batch/--config flags that do not exist, so the examples are not actually executable against the bundle.	3 / 5
Workflow Clarity	A clear 5-step Workflow with an explicit fallback path (step 5) plus validation checkpoints (py_compile Quick Check, batch JSON validation), though the main workflow steps are somewhat abstract and the validation commands live in separate sections rather than inline.	4 / 5
Progressive Disclosure	The body has section structure but is a ~235-line monolith with content that could be split out, and the References section points to references/guide.md and references/examples/ which do not exist (the actual file is references/guidelines.md), so navigation is present but inaccurate.	3 / 5
	Total	12 / 20 Passed

Description

88%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 strong, third-person description that explicitly covers both capabilities and trigger conditions with concrete, natural language. Minor improvements possible by adding a few more trigger synonyms and sharpening distinction from generic summarization skills.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions — 'Extracts and summarizes key takeaways', 'Produces structured outputs such as numbered lists, executive summaries, and action items', and 'Supports configurable output formats including JSON export' — giving comprehensive coverage of capabilities.	5 / 5
Completeness	Clearly answers both 'what' (extracts/summarizes takeaways into structured outputs) and 'when' ('Use when the user asks for summaries, bullet points, main points, highlights, or a TL;DR') with concrete trigger phrases.	5 / 5
Trigger Term Quality	Strong natural trigger terms ('summaries, bullet points, main points, highlights, or a TL;DR') that users would actually say, but missing a few common variants (e.g. 'recap', 'summarize', 'key points') and no file extensions, so not fully comprehensive.	4 / 5
Distinctiveness Conflict Risk	The TL;DR / key-takeaways framing is a fairly distinct niche, but the generic 'summaries' trigger could overlap with other general summarization skills, leaving minor overlap risk with closely related skills.	4 / 5
	Total	18 / 20 Passed

Validation

87%

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 — 14 / 16 Passed

Validation for skill structure

Criteria	Description	Result
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning
referenced_paths_exist	Referenced path issues: 2 missing	Warning

	Total	14 / 16 Passed

Repository: aipoch/medical-research-skills
Path: scientific-skills/Evidence Insight/key-takeaways/SKILL.md
Commit: 63c61d3

Reviewed: 11 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.