skill-retrieval SKILL.md skillA
skill-retrieval from moonlight-lupin/agent-skills is an agent skill: a SKILL.md folder an AI agent loads when a task calls for it.
mdr add moonlight-lupin/agent-skills/skill-retrieval@v0.7.0Pins v0.7.0 in mdr.lock. Pin the fingerprint instead.
- Audit grade
- A, 17 of 17 checks passed
- Kind
- SKILL.md skill
- Repository
- moonlight-lupin/agent-skills
- Path
plugins/skill-retrieval/SKILL.md- Versions recorded
- 14
- Latest version
- v0.7.0, committed Oct 26, 2026
- First version recorded
- Aug 19, 2026
- Size
- 11,544 bytes
- Repository stars
- 119
- License
- MIT
BM25-based skill retrieval plugin for Hermes Agent. Replaces the full skill list in the system prompt with a names-only compact view (~2K tokens) and injects top-K relevant skill descriptions per turn via BM25 retrieval (~300 tokens). Saves ~9K tokens/turn. Use when system prompt token overhead from skills is a concern, or when skill discovery quality matters.
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
# Skill Retrieval This is a **Hermes Agent** plugin. It is not a Claude Code plugin and will not load in Claude Code — that runtime has no `pre_llm_call` event, no Python `register()` entry point, and reads `.claude-plugin/plugin.json` rather than `plugin.yaml`. Requires Hermes Agent >=0.21.1 (`requires_hermes` in `plugin.yaml`). BM25-based progressive disclosure for Hermes Agent skills. Instead of dumping every skill description into the system prompt (~11.5K tokens), this plugin keeps a compact names-only index and injects only the top-K relevant descriptions per turn. ## What it does Two-phase progressive disclosure: 1. **Phase 1 — System prompt compaction** (an `llm_request` middleware): Rewrites the outgoing request's `<available_skills>` block so it lists skill names only (descriptions stripped). All skills remain discoverable by name (~2K tokens instead of ~11.5K). The system prompt Hermes builds is never modified — prompt caching is unaffected. 2. **Phase 2 — Per-turn BM25 retrieval** (`pre_llm_call` hook): Tokenizes the user message, ranks active skill descriptions with BM25 Okapi, and injects …
Read the whole file at its exact version.
How to install
mdr add moonlight-lupin/agent-skills/skill-retrieval@sha256:64d2e2c33d2a509bThe line at the top of this page pins the label v0.7.0, 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_nvgmgiv7wy6ung62)
4 badge image fetches in 30 days. What the badge shows.
Versions
The registry has recorded 14 versions of this file, between Aug 19, 2026 and Oct 26, 2026, about one every 5 days.
| version | committed | commit | size | audit | |
|---|---|---|---|---|---|
| v0.7.0 latest | 2026-10-26 | 8a7d424 | 11,544 B | A | view · diff |
| v0.7.0 | 2026-10-17 | d89e1a3 | 11,249 B | A | view · diff |
| v0.6.1 | 2026-10-17 | 5eeb4e5 | 11,249 B | A | view · diff |
| v0.6.1 | 2026-10-17 | 8048734 | 10,583 B | A | view · diff |
| v0.6.1 | 2026-10-13 | 8bbbdba | 10,309 B | A | view · diff |
| v0.6.0 | 2026-10-03 | 79801c6 | 10,309 B | A | view · diff |
| v0.5.0 | 2026-10-02 | 46f9818 | 9,423 B | B | view · diff |
| v0.3.1 | 2026-09-26 | 9d5a255 | 8,252 B | A | view · diff |
| v0.3.0 | 2026-09-26 | 6fb4770 | 7,407 B | A | view · diff |
| v0.1.0 | 2026-09-09 | 6a8f18f | 7,103 B | A | view · diff |
| v0.1.0 | 2026-09-06 | 953188a | 6,936 B | A | view · diff |
| v0.1.0 | 2026-08-19 | 67a82c6 | 6,923 B | A | view · diff |
| v0.1.0 | 2026-08-19 | ce43583 | 5,809 B | A | view · diff |
| v0.1.0 | 2026-08-19 | cb94991 | 5,785 B | A | view |
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 (11544 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
moonlight-lupin/agent-skills · 119 stars · license MIT · pushed 2026-10-30 · branch main
API
GET https://markdownregistry.com/api/v1/artifacts/art_nvgmgiv7wy6ung62 GET https://markdownregistry.com/api/v1/resolve?ref=moonlight-lupin/agent-skills/skill-retrieval GET https://markdownregistry.com/api/v1/blob/64d2e2c33d2a509bae76079633c63e096442b84b63bf7538a971dbff5e5320bc
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.