CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

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

75%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide
SecuritybySnyk

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
SKILL.md
Quality
Evals
Security

Quality

Content

45%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 material (CLI examples, sample input/output, quality checklist, batch validation loops) but is undermined by heavy template padding — the description repeated verbatim three times — and by examples that do not match the packaged script's actual API. Referenced bundle files (references/guide.md, references/examples/) do not exist while the real references/guidelines.md is never cited, breaking navigation.

Suggestions

Remove the three verbatim repeats of the frontmatter description from 'When to Use' and 'Key Features', and cut the generic template sections (Output Requirements, Response Template, Input Validation, Implementation Details) that add no skill-specific guidance.

Fix the reference paths: cite the actual references/guidelines.md (not the nonexistent references/guide.md and references/examples/), or add those files to the bundle.

Align code and CLI examples with the real scripts/main.py — either document KeyTakeaways.extract() and the argument-less main(), or extend the script to support the documented --input/--output/--batch flags and process()/export() methods.

DimensionReasoningScore

Conciseness

The 51-word frontmatter description is pasted verbatim three separate times ("Use this skill when the task needs Extracts and summarizes...", "Scope-focused workflow aligned to: Extracts and summarizes...", and again in Key Features), and the body is padded with generic boilerplate: "See `## Workflow` above for related details", "Output Requirements", "Response Template", and an "Input Validation" section that restates scope in abstract terms. This is noticeably verbose with several padded sections (anchor 2), not the occasional tightness issues of anchor 3.

2 / 5

Actionability

There is concrete-looking guidance (CLI commands with --input/--output/--batch flags, Python quick start with tool.process()/tool.export(), JSON validation loops), but the examples do not match the packaged script: scripts/main.py actually defines class KeyTakeaways with an extract() method, no process()/export(), and a main() that accepts no CLI arguments. The examples are effectively non-executable against the real bundle, fitting anchor 3's "missing key details" rather than anchor 4's "minor gaps".

3 / 5

Workflow Clarity

A 5-step Workflow section is present, and validation checkpoints exist for batch operations: a concrete post-batch JSON validation loop, review of output_dir/errors.log after partial failures, py_compile pre-check, and an Error Handling section with an explicit fallback path. This matches anchor 4's "clear sequence with most checkpoints"; it falls short of 5 because the workflow narrative is fragmented across three overlapping sections (Workflow, Example Usage run plan, Implementation Details) and steps like "choose the packaged workflow" stay abstract.

4 / 5

Progressive Disclosure

The References section points to `references/guide.md` - Detailed documentation and `references/examples/`, but neither exists in the bundle; the actual file is references/guidelines.md, which the body never names. Scored against the real bundle structure, the signaled references do not resolve and navigation fails, fitting anchor 2 ("references are buried"/mismatched) rather than anchor 3's merely imperfect organization.

2 / 5

Total

11

/

20

Passed

Description

96%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 description that clearly states what the skill does and when to use it, with natural trigger phrasings (summaries, TL;DR, highlights, main points) and concrete output formats. Its only weakness is that generic document summarization is a broad niche with some overlap risk against other summarization skills.

DimensionReasoningScore

Specificity

The description lists multiple specific concrete actions with comprehensive coverage: "Extracts and summarizes key takeaways from documents, meeting notes, articles", "Produces structured outputs such as numbered lists, executive summaries, and action items", and "Supports configurable output formats including JSON export". It names the domain, input types, output structures, and format options, leaving no meaningful coverage gaps, so it fits the 5 anchor rather than the 4 anchor's "minor gaps".

5 / 5

Completeness

It explicitly answers both questions: what ("Extracts and summarizes key takeaways from documents... Produces structured outputs... Supports configurable output formats") and when ("Use when the user asks for summaries, bullet points, main points, highlights, or a TL;DR"). Both are present with concrete trigger phrases, exactly matching the 5 anchor; the 4 anchor's weaker "when" does not apply.

5 / 5

Trigger Term Quality

Trigger terms are natural user phrasings with synonyms: "summaries, bullet points, main points, highlights, or a TL;DR of any document or body of text", plus "meeting notes, articles". Coverage of how a user would naturally request this is essentially complete (including the colloquial "TL;DR"), matching the 5 anchor rather than 4's "a few natural terms missing".

5 / 5

Distinctiveness Conflict Risk

The takeaway/TL;DR extraction niche is mostly distinct with specific triggers, but summarization of "any document or body of text" is a crowded space where this could overlap with general summarizer or notes-processing skills. Minor overlap risk with closely related skills fits the 4 anchor; it lacks the minimal-conflict sharpness of the 5 anchor.

4 / 5

Total

19

/

20

Passed

Validation

87%

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

CriteriaDescriptionResult

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

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.