Claude MarketplacesSubmit
memtensor avatar

Skills Vote Local

memtensor/skills-vote

If you're running Claude with a private skill library or you've built your own collection locally, this lets you query against that instead of hitting a network service for skill discovery. It uses a routing script that can either handle the lookup directly or delegate to a subagent depending on your setup and what the current runtime allows. The fallback mode is a nice touch for when subagent creation isn't available. Honestly, this is pretty niche unless you're in an airgapped environment or you've invested in curating your own skill set, but if that's your situation, it's exactly what you need. The implementation is straightforward: run the router, follow its output.

GitHub stars
277
last updated
Jun 10, 2026
View on GitHub

Install

$ npx -y skills add memtensor/skills-vote --skill skills-vote-local --agent claude-code

Installs into .claude/skills of the current project.

Files

Skills Vote Local

Read only this file first. Do not read scripts/, docs/, or any other files in this skill unless this file or a script output explicitly tells you to do so.

Use this skill when the current task needs skill discovery from a local or private skill library instead of a network service.

All paths mentioned in this file are relative to this skill root. cd to this root directory before running any command here.

Run:

uv run -qq scripts/route_prompt.py --role main

Then follow the rendered stdout exactly.

If routing.mode selects a subagent route, the user configuration explicitly requests subagent-based skill lookup. The main agent should use subagent delegation when the current host/tooling permits it.

Do not use fallback merely because the current user message did not repeat "use subagent".

If the current host, tool policy, runtime, or authorization model cannot create a subagent in this turn, run:

uv run -qq scripts/route_prompt.py --role main --fallback

Then follow the fallback stdout exactly.

If you are a subagent and you read this file directly, do not run this command with --role main. Run:

SKILL.md on GitHub

Sponsors

Promote your product hereReach 125k+ visitors monthlyPromote your product hereReach 125k+ visitors monthlyAgent CaffeineSponsoredClose your lid, come back to finished workSnugSponsoredThe clipboard manager for the AI eraPromote your product hereReach 125k+ visitors monthlyWaxSponsoredBlock anything with supervision, without erasing your iPhonePromote your product hereReach 125k+ visitors monthlyknobsSponsoredSee your site on any phone, any day, in any language

Details

Repository
github.com/memtensor/skills-vote
License
MIT
First seen
Jun 11, 2026

More from memtensor/skills-vote

All 2

Recommended

1juliusbrussee avatarcavemanjuliusbrussee/cavemanUltra-compressed communication mode. Cuts output tokens 65% (measured) by speaking like caveman while keeping full technical accuracy. Supports intensity levels618.3Kskills.sh installs
2mattpocock avatargrill-memattpocock/skillsA relentless interview to sharpen a plan or design.1.5Mskills.sh installs
3shadcn avatarimproveshadcn/improveSurvey any codebase as a senior advisor and produce prioritized, self-contained implementation plans for OTHER models/agents to execute. Strictly read-only on s40Kskills.sh installs
4obra avatarsystematic-debuggingobra/superpowersUse when encountering any bug, test failure, or unexpected behavior, before proposing fixes326.7Kskills.sh installs
5forrestchang avatarkarpathy-guidelinesforrestchang/andrej-karpathy-skillsBehavioral guidelines to reduce common LLM coding mistakes through explicit assumptions, simplicity, and verifiable success criteria.17.9Kskills.sh installs
6vercel-labs avatarfind-skillsvercel-labs/skillsHelps users discover and install agent skills when they ask questions like "how do I do X", "find a skill for X", "is there a skill that can...", or express int4.3Mskills.sh installs