add agent memory skill for persistent context and recency decay

[Goodnight77]

What this PR does

Adds a new qdrant-agent-memory skill as a single leaf skill for agent memory architecture in Qdrant. It focuses on operational judgment for storage selection, admission control, composite retrieval scoring, isolation guardrails, provenance, and memory-bloat mitigation, based on issue research and maintainer feedback around score boosting and decay-based recency ranking

references used

• https://qdrant.tech/blog/qdrant-1.14.x/#idea-2-reranking-most-recent-results
• https://qdrant.tech/documentation/search/search-relevance/#score-boosting
• https://qdrant.tech/blog/decay-functions/

Type

• new skill
• skill improvement
• bug fix
• repo hygiene

Checklist

• python3 scripts/validate_skills.py passes
• skill answers "when?" or "why?", not "how?"
• skill navigates to docs, does not duplicate or replace them
• description has Use when with 5+ trigger phrases
• leaf skills omit allowed-tools, hub skills declare them
• ends with ## What NOT to Do section
• no code blocks except minimal snippets when absolutely required (reference the docs instead)
• all doc links go to search.qdrant.tech/md/documentation/
• tested with a realistic prompt (paste below or link to eval)

Test prompt

 I’m building an AI agent with long-term memory and I’m not sure what should go into Qdrant versus Redis or
  Postgres. I also need to avoid duplicate memories, keep recent memories ranked higher, and make sure one agent
  never retrieves another agent’s memory.

screenshots

tested with claude code

---

related issues #39

@thierrypdamiba looking forward to your feedback and happy to refine this further

[Copilot]

Pull request overview

Adds a new leaf skill, qdrant-agent-memory, to guide operational “when/why” decisions for implementing persistent agent memory with Qdrant (storage selection, admission control, retrieval scoring, isolation, provenance, and memory-bloat mitigation).

Changes:

• Introduces skills/qdrant-agent-memory/SKILL.md with guidance for storage separation, deduplication/admission, composite reranking, isolation filters, and provenance.
• Adds qdrant-agent-memory to the top-level skills list in README.md.

Reviewed changes

Copilot reviewed 2 out of 2 changed files in this pull request and generated 2 comments.

File	Description
skills/qdrant-agent-memory/SKILL.md	New leaf skill describing operational patterns for agent memory architecture using Qdrant + complementary stores.
README.md	Registers the new skill in the repository’s skills table for discoverability.

---

💡 Add Copilot custom instructions for smarter, more guided reviews. Learn how to get started.