doc-serve

1 forks
88
B

Advanced document search with BM25 keyword matching, semantic vector search, and hybrid retrieval.Enables precise technical queries, conceptual understanding, and intelligent result fusion.Supports local document indexing and provides comprehensive search capabilities for knowledge bases.

Commands
#search#hybrid#vector#API#hybrid search#vector search#technical#Search Guide

Third-Party Agent Skill: Review the code before installing. Agent skills execute in your AI assistant's environment and can access your files. Learn more about security

Installation for Agentic Skill

View all platforms →
skilz install SpillwaveSolutions/doc-serve-skill/doc-serve
skilz install SpillwaveSolutions/doc-serve-skill/doc-serve --agent opencode
skilz install SpillwaveSolutions/doc-serve-skill/doc-serve --agent codex
skilz install SpillwaveSolutions/doc-serve-skill/doc-serve --agent gemini

First time? Install Skilz: pip install skilz

Works with 22+ AI coding assistants

Cursor, Aider, Copilot, Windsurf, Qwen, Kimi, and more...

View All Agents
Download Agent Skill ZIP

Extract and copy to ~/.claude/skills/ then restart Claude Desktop

1. Clone the repository:
git clone https://github.com/SpillwaveSolutions/doc-serve-skill
2. Copy the agent skill directory:
cp -r doc-serve-skill/doc-serve-skill/doc-serve ~/.claude/skills/

Need detailed installation help? Check our platform-specific guides:

Related Agentic Skills

Agentic Skill Details

Forks
1
Type
Non-Technical
Meta-Domain
general
Primary Domain
general
Sub-Domain
api search data
Market Score
88

Agent Skill Grade

B
Score: 88/100 Click to see breakdown

Score Breakdown

Spec Compliance
12/15
PDA Architecture
26/30
Ease of Use
22/25
Writing Style
8/10
Utility
17/20
Modifiers: +3

Areas to Improve

  • Description needs trigger phrases
  • Missing TOC in main SKILL.md
  • Redundant search mode table

Recommendations

  • Add trigger phrases to description for discoverability
  • Add table of contents for files over 100 lines

Graded: 2026-01-19

Developer Feedback

I took a look at your doc-serve skill and wanted to share some thoughts.

Links:

The TL;DR

You're at 88/100, solidly in B territory. This is based on Anthropic's skill best practices rubric. Your strongest area is Ease of Use (22/25) — the trigger list and metadata are really well done. The weakest is Spec Compliance (12/15), which is dragging you down a few points. Overall, it's a functional, practical skill that just needs some structural polish.

What's Working Well

  • Excellent trigger variety — "doc serve", "search domain", "hybrid search", etc. give natural activation paths. Users will find this easily.
  • Rich reference architecture — Five focused reference documents (BM25, vector, hybrid, troubleshooting, API) with clear one-level separation. That's solid Progressive Disclosure.
  • Comprehensive troubleshooting coverage — The troubleshooting guide validates setup and gives debugging output patterns. Real practical value here.
  • Good CLI/API examples — Input/output pairs and integration scripts show how to actually use this, not just theory.

The Big One: Missing Trigger Phrases in Description

Your frontmatter description says "Advanced document search with BM25 keyword matching, semantic vector search, and hybrid retrieval" — but it's missing trigger phrases. The spec requires phrases like "Use when asked to..." that help Claude understand how to activate the skill naturally.

Fix: Rewrite the description to something like:

Performs doc serve operations. Use when asked to "doc serve", "run doc serve", "semantic search", or "hybrid document search".

This is worth +2 points alone and moves you closer to A territory.

Other Things Worth Fixing

  1. **Add a t...

AI-Detected Topics

Extracted using NLP analysis

search hybrid vector API hybrid search vector search technical Search Guide Mode Mode User

Report Security Issue

Found a security vulnerability in this agent skill?