moonlight-lupin/agent-skills / plugins/skill-retrieval
skill-retrieval
VerifiedBM25-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.
tests/conftest.py
View on GitHub"""Make the scripts/ directory importable from tests.
Tests import ``bm25_retriever`` as a top-level module (scripts/ on
sys.path). The plugin package imports the same file as
``scripts.bm25_retriever``. Alias those names onto one module object so
index caches are not split across two identities.
"""
import sys
from pathlib import Path
import pytest
SCRIPTS = Path(__file__).resolve().parent.parent / "scripts"
sys.path.insert(0, str(SCRIPTS))
PLUGIN = Path(__file__).resolve().parent.parent
sys.path.insert(0, str(PLUGIN)) # after the SCRIPTS insert
import scripts.bm25_retriever as _br
sys.modules.setdefault("bm25_retriever", _br) # unify module identity
@pytest.fixture(autouse=True)
def _hermetic_disabled_skills(monkeypatch):
"""Neutralize host config bleed into the runtime cache key.
When the ambient environment can import the real Hermes core (e.g. the
agent kernel's PYTHONPATH), `_session_platform_key_parts` reads the
host's real `skills:` config and folds ~78 real skill names into the
index cache key — the suite's results then depend on where pytest ran.
Tests that care about disabled sets monkeypatch this themselves (their
patches run after this one and win). Host-config behavior is covered by
test_index_cache's self-contained fixture, which stubs the whole agent
module; nothing here exercises the real host config deliberately.
"""
try:
import agent.skill_utils as _su # real core when ambient env exposes it
except Exception:
return # hermetic env: nothing to neutralize
monkeypatch.setattr(_su, "get_disabled_skill_names", lambda platform=None: set(), raising=True)
Related skills
| Skill | Stars | Updated | Works with | Status | Install |
|---|---|---|---|---|---|
| reverse-engineer-anythingmorluto/reaReverse engineer native, managed, Electron/JavaScript, packaged, firmware, and browser targets with REA, and build agent environments (AgentEnv bundles) of web applications from a live instance or a capture, and of Linux desktop apps with a task from a request. Use shipped-artifact or requested runtime evidence to explain features, compare versions, decompile code, or guide a reconstruction. Skip REA for ordinary source-repository architecture analysis. | Stars: 472k | Updated | Claude CodeCodex | Verified | Install |
| diagnosing-superpowersobra/superpowersUse when a superpowers session went wrong and your human partner wants to know why — repeated work, ignored plans, stumbles, poor results, a skill that didn't fire, "it took too long", "why is it so expensive", "what is it doing" — or wants to build a bug report for the superpowers maintainers, for the current session or a past one identified by id or path, on any harness. | Stars: 322k | Updated | Claude CodeCodex | Verified | Install |
| dispatching-parallel-agentsobra/superpowersUse when facing 2+ independent tasks that can be worked on without shared state or sequential dependencies | Stars: 322k | Updated | Claude CodeCodex | Verified | Install |
| executing-plansobra/superpowersUse when executing an implementation plan in the current session as the implementer yourself — your human partner chose inline execution, or no subagent tool is available | Stars: 322k | Updated | Claude CodeCodex | Verified | Install |