MemTensor/skills-vote / integration/skills/skills-vote-local
skills-vote-local
VerifiedUse when retrieving the most relevant skills from a local or private skill library instead of relying on network-based skill discovery.
| File | Kind | Size |
|---|---|---|
| SKILL.md | skill md | 1.5 KB |
| configs/config.yaml.example | other | 1.6 KB |
| docs/config-schema.md | markdown | 6.4 KB |
| docs/handoff.md | markdown | 928 B |
| scripts/check_env.py | script | 5.9 KB |
| scripts/chroma_utils.py | script | 3.5 KB |
| scripts/cli_common.py | script | 932 B |
| scripts/config_validation.py | script | 2.7 KB |
| scripts/index.py | script | 771 B |
| scripts/local_skill_search.py | script | 22.3 KB |
| scripts/prompt.py | script | 27.6 KB |
| scripts/recommend.py | script | 1.1 KB |
| scripts/route_prompt.py | script | 15.1 KB |
| scripts/sync_skills.py | script | 8.1 KB |
docs/handoff.md
View on GitHub# skills-vote-local handoff
You are the delegated subagent for a local/private skill recommendation task.
This handoff is used when routing.mode is subagent_*.
The user configuration explicitly requests that skill lookup be performed by a subagent.
Read only this file first.
Work from the `skills-vote-local` skill root directory.
The subagent must render its own route:
```bash
uv run -qq scripts/route_prompt.py --role subagent
```
Then follow the rendered stdout exactly.
The rendered stdout may select vector_search or `agentic_search`.
If it selects `agentic_search`, search only the synced `./.skills/` namespace exactly as the route prompt instructs.
Do not read `SKILL.md`, `docs/config-schema.md`, or files under `scripts/` unless the route prompt tells you to.
If `scripts/route_prompt.py` cannot run, return strict JSON with `skills: []` and a `reason` explaining that the route prompt could not be loaded.
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 |