rag-freshness SKILL.md skillA
rag-freshness from amey-thakur/ai-skills is an agent skill: a SKILL.md folder an AI agent loads when a task calls for it.
mdr add amey-thakur/ai-skills/rag-freshness@git:20260728.fe84bd4Pins git:20260728.fe84bd4 in mdr.lock. Pin the fingerprint instead.
- Audit grade
- A, 17 of 17 checks passed
- Kind
- SKILL.md skill
- Repository
- amey-thakur/ai-skills
- Path
skills/ai-memory-rag/rag-freshness/SKILL.md- Versions recorded
- 1
- Latest version
- git:20260728.fe84bd4, committed Jul 28, 2026
- Size
- 1,967 bytes
- Repository stars
- 14
- License
- MIT
Keep a retrieval corpus current as source documents change, with incremental updates, deletion propagation, and a stated staleness budget. Use when retrieved answers cite content that has since changed or been removed.
Collected from public GitHub. Every version is saved exactly as it was and never changes. Install it at an exact version with the mdr tool, and every file is checked before it reaches your agent. The main file is checked against the SHA-256 fingerprint recorded here, and the others against the fingerprints GitHub keeps for its source commit. The automatic checks below grade the latest version, and the same checks always give the same file the same grade.
What the file says
# RAG freshness A retrieval index is a snapshot that starts drifting immediately. The failure is quiet and serious: an answer confidently cites a policy that was superseded last month, with a citation that makes it look verified. ## Method 1. **State the staleness budget per source.** Minutes for operational data, days for documentation. It determines the whole update strategy (see search-indexing-pipeline). 2. **Update incrementally on change events.** Reindexing everything on a schedule is expensive and still leaves a window; capturing changes as they happen is both cheaper and fresher. 3. **Propagate deletions immediately.** A removed document that stays retrievable is worse than a stale one, especially where the removal was for accuracy or permission reasons. 4. **Re-chunk and re-embed on substantive change.** A minor edit may not warrant it; a rewrite does, and treating all edits alike either wastes work or leaves stale vectors (see chunking-strategies). 5. **Carry the source timestamp into the chunk.** The model can then qualify its answer, and users can judge for themselves (see citation-grounding). …
Read the whole file at its exact version.
How to install
mdr add amey-thakur/ai-skills/rag-freshness@sha256:3cb0c0a9d7169228The line at the top of this page pins the label git:20260728.fe84bd4, which is what most people want. This one pins the sha256 fingerprint of the contents instead, so it survives a label being moved. Either way the exact version is written to mdr.lock, and mdr install downloads and checks those contents again, so it installs them exactly or stops with an error.
[](https://markdownregistry.com/a/art_rha3gev4fritkegt)
4 badge image fetches in 30 days. What the badge shows.
Versions
The registry has recorded 1 version of this file, committed on Jul 28, 2026.
Audit of the latest version
- pass: Frontmatter block present
- pass: Frontmatter declares a name
- pass: Frontmatter declares a description
- pass: Size between 200 bytes and 200 KB (1967 bytes)
- pass: No zero-width or bidi control characters
- pass: No instruction hidden inside an HTML comment
- pass: No link to an exfiltration or paste host
- pass: No credential-shaped string
- pass: No instruction to send local credentials anywhere
- pass: No text hidden with inline styles
- pass: No prompt-injection phrasing
- pass: No curl or wget piped into a shell
- pass: No recursive delete of root, home or parent
- pass: No instruction to read or print local credentials
- pass: No base64 blob over 200 characters
- pass: No link to a raw IP address
- pass: No script tag
Source
amey-thakur/ai-skills · 14 stars · license MIT · pushed 2026-09-06 · branch main
API
GET https://markdownregistry.com/api/v1/artifacts/art_rha3gev4fritkegt GET https://markdownregistry.com/api/v1/resolve?ref=amey-thakur/ai-skills/rag-freshness GET https://markdownregistry.com/api/v1/blob/3cb0c0a9d716922887433f6afcefba01049b2723c8e9fc7f214e8bc88e0d55a5
Your AI assistant does the legwork. You hear about the deals worth your word. Hand yours the standing instructions at modelranch.com and it joins the network that reads files like this one.
Guides: the SKILL.md format and its required fields · what to check before you install a skill · how to pin a skill to an exact version · where to find agent skills · keeping a team on the same skills · which agent file does what.