Relevant jobs
AI / Algorithm Engineer
Backend Engineer
Content Creator / Social Media
Data Analyst / Data Engineer
rag-skillConardLi/rag-skill
Gives AI agents the ability to retrieve and read material from a local knowledge base,…
No ratings yet
Rate this skill
Stars716
Forks205
Watchers716
Open Issues1
InstallOne-line install
UnconfirmedWhether this repository follows the Agent Skills spec (that is, whether it contains a SKILL.md) has not been verified yet. Until that is settled, clone it and use what you need:
git clone https://github.com/ConardLi/rag-skill.git
OverviewOverview
Key Features
Gives AI agents the ability to retrieve and read material from a local knowledge base, so answers are grounded in real documents instead of being generated from nothing. Key capabilities include: 1. Knowledge-base search: uses grep to locate keyword hits in knowledge-base text and returns the file and surrounding context, letting the agent narrow down where the answer lives; 2. On-demand file reading: uses read_file to read only the specified section of a specified file, avoiding dumping whole documents into context, saving tokens and keeping answers traceable; 3. PDF and table parsing: uses pdftotext to convert PDFs into searchable text and pandas to load and filter tabular data, so non-plain-text material can also be retrieved and used; 4. Scale verification: reads the directory and counts files first to confirm knowledge-base coverage before choosing a retrieval strategy, avoiding missed or misjudged results; 5. Conventions and examples: ships a sample knowledge base and best-practice notes showing how to organize directories, name files and write retrieval flows, so the setup can be copied and adapted directly.
Use Cases
Connecting an agent to a company or personal local document library for Q&A, locating specific data inside large collections of PDFs and spreadsheets, retrieval-augmented writing that needs answers traceable to source passages, and auditing the coverage of a new knowledge base.
Target Roles
AI / Algorithm Engineer, Backend Developer, Data Analyst / Data Engineer, Content Creator / Social Media Operator.
RatingUser ratings
Nobody has rated this skill yet. Yours would be the first on the site — your vote becomes the initial average.
RepositoryRepository
| Skill ID | 1217 |
|---|---|
| Data source | GitHub |
| Repository | ConardLi/rag-skill |
| Category | AI & Agent Skills / Knowledge Retrieval & RAG |
| Primary language | Python |
| License | Not specified |
| Default branch | main |
| GitHub repository ID | 1147214344 |
| Node ID | R_kgDORGEaCA |
| Rank | #989 (position within the source ranking) |
| Site-wide popularity rank | #1118 (computed live from Stars, across all 5833 entries) |
GrowthStar / Fork growth
One snapshot per day, tracking how Stars and Forks changed
- Now716
- Previous point · 09-29 714
- vs previous point +2
- 2 data points 12 days
- Now205
- Previous point · 09-29 204
- vs previous point +1
- 2 data points 12 days
TimelineTimeline
Repository created2026-02-01 11:49:369 months ago
Data last updated2026-10-26 12:07:0123 days ago
Last commit2026-04-25 14:59:226 months ago
CommitLatest commit
Version [latest] committed by ConardLi. Update Category: Feature Addition & Enhancement. Commit details: docs: 更新README添加项目归档通知. This update introduces new capabilities and module extensions.