Vibecosystem harvest-adaptive

Adaptive content summarization - auto-detect content type and produce relevant summary

install
source · Clone the upstream repo
git clone https://github.com/vibeeval/vibecosystem
Claude Code · Install into ~/.claude/skills/
T=$(mktemp -d) && git clone --depth=1 https://github.com/vibeeval/vibecosystem "$T" && mkdir -p ~/.claude/skills && cp -r "$T/skills/harvest-adaptive" ~/.claude/skills/vibeeval-vibecosystem-harvest-adaptive && rm -rf "$T"
manifest: skills/harvest-adaptive/SKILL.md
source content

Harvest Adaptive (Digest)

Automatically detect content type and produce the most useful summary. A blog post gets key takeaways. A library gets feature evaluation. Documentation gets structure overview. API reference gets endpoint catalog.

Usage

/digest <url>

Examples

# Evaluate a library
/digest https://github.com/owner/cool-library

# Summarize an article
/digest https://blog.example.com/microservices-patterns

# Overview documentation
/digest https://docs.example.com

Content Type Detection

TypeSignalsOutput Style
Library/ToolGitHub repo, npm page, PyPIFeature matrix, ecosystem health, recommendation
Blog/ArticleSingle long-form contentKey takeaways, relevance assessment
DocumentationMulti-page, navigation structureStructure map, coverage assessment, quality
API ReferenceEndpoints, methods, paramsEndpoint catalog, auth info, SDK availability
ComparisonTables, vs, alternativesFeature matrix, winner per category
TutorialStep-by-step, code blocksPrerequisites, steps summary, outcome

Output Templates

Library Evaluation

# Library: [name]
> Source: [URL] | Stars: [X] | Last commit: [date]

## What It Does
[1-2 sentence description]

## Key Features
- Feature 1
- Feature 2

## Ecosystem Health
| Metric | Value |
|--------|-------|
| GitHub Stars | X |
| Weekly Downloads | X |
| Last Release | date |
| Open Issues | X |
| Contributors | X |

## API Surface
[Key classes/functions/exports]

## Verdict
[Use when... Don't use when... Alternatives: ...]

Article Summary

# Summary: [title]
> Source: [URL] | Author: [name] | Date: [date]

## Key Takeaways
1. [Point 1]
2. [Point 2]
3. [Point 3]

## Relevance
[How this applies to current project/context]

## Action Items
- [What to do based on this]

Rules

  • Auto-detect, don't ask user for content type
  • Keep summaries under 500 words
  • Always include source URL and date
  • For libraries: check last commit date, flag if > 6 months
  • For articles: check publication date, flag if > 1 year
  • Confidence rating on every assessment