Skip to content

MemTensor/skills-vote / integration/skills/skills-vote-local

skills-vote-local

Verified

Use when retrieving the most relevant skills from a local or private skill library instead of relying on network-based skill discovery.

configs/config.yaml.example

View on GitHub
# Production starter config for skills-vote-local.
# Copy this file to configs/config.yaml, then replace skill_library.include.

routing:
  # main_single_pass | main_multi_pass | subagent_single_pass | subagent_multi_pass
  mode: subagent_multi_pass
  # Used only by multi-pass routes. Single-pass routes always use one pass.
  max_passes: 3

retrieval:
  # agentic_search is the production default: no embedding service or vector_search index is required.
  # Use vector_search only when you intentionally want recommend.py + Chroma retrieval.
  method: agentic_search

retrieval_context:
  # In agentic_search mode this is informational; search scope is always ./.skills/.
  # In vector_search mode it controls recommendation-time candidate inspection.
  mode: recommend_plus_skill_md

skill_library:
  # Replace with one or more real skill-library globs.
  include:
    - /path/to/your-skill-library/**/SKILL.md
  exclude:
    - "**/.git/**"
    - "**/.hg/**"
    - "**/.svn/**"
    - "**/.skills/**"
    - "**/.venv/**"
    - "**/venv/**"
    - "**/node_modules/**"
    - "**/__pycache__/**"
    - "**/.pytest_cache/**"
    - "**/.mypy_cache/**"
    - "**/.ruff_cache/**"
    - "**/dist/**"
    - "**/build/**"

# Optional vector_search settings.
# These are used only when retrieval.method is vector_search.
#
# chroma:
#  path: ../output/chroma/skills_vote_local
#  collection: skills_vote_local
#
# embedding:
#  provider: openai-compatible
#  model: bge-m3
#  dimensions: 1024
#  api_key_env: OPENAI_API_KEY
#  api_key: ""
#  base_url: https://api.openai.com/v1
#  extra_headers: {}
#
# retrieval:
#  method: vector_search
#  top_k: 5
#
# indexing:
#  update_on_start: true
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: 472kUpdated Claude CodeCodexVerifiedInstall
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: 322kUpdated Claude CodeCodexVerifiedInstall
dispatching-parallel-agentsobra/superpowersUse when facing 2+ independent tasks that can be worked on without shared state or sequential dependenciesStars: 322kUpdated Claude CodeCodexVerifiedInstall
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 availableStars: 322kUpdated Claude CodeCodexVerifiedInstall