Skill
architect
Use for design-level judgement: requirements, quality attributes, trade-offs, ADR, contracts, resilience, security,…
@shafthqInstall SkillTesting
Skill
/local-runtimes
Use when choosing an optional local inference runtime for a narrow mechanical or offline job.
Install
$ npx -y skills add ShaftHQ/SHAFT_ENGINE --skill local-runtimes --agent claude-codeHow it fires
How this skill gets triggered: by you, by Claude, or both.
- Fires itselfAuto-invocation. Claude auto-loads it when your prompt matches the work.Auto-invocation is when the right skill fires by itself at the right moment, driven by a FLOW.md router and a hook, instead of you invoking it by name. It is the difference between a skill being installed and a skill actually getting used.Read the full definition →
- You can call itInvoke it directly when you want it.
- Slash command
/local-runtimes
Context preview
The summary Claude sees to decide when to auto-load this skill.
Use when choosing an optional local inference runtime for a narrow mechanical or offline job.
SKILL.md
local-runtimes.SKILL.mdname: local-runtimes
description: >-
Use when choosing an optional local inference runtime for a narrow mechanical
or offline job.
license: MIT
Local runtimes
Cloud implementers write code directly. A local runtime is optional and only pays for narrow mechanical or offline jobs; never let it review its own diff. Pick one row, then open only that route.
| Need | Route | Open | | --- | --- | --- | | Which model size fits this machine | hardware probe | [local-coding-delegate](references/local-coding-delegate.md) | | Already READY loopback server (Ollama, LM Studio, llamacpp) | loopback | [local-openai-compat](references/local-openai-compat.md) | | Standalone FreeToken process | FreeToken | [freetoken](references/freetoken.md) | | Frontier MoE through disk/RAM/VRAM tiers | Colibri | [colibri](references/colibri.md) | | OmniRoute runner with delegate continuity | OmniRoute | [omniroute](references/omniroute.md) | | Local agents (OpenCode / OSS agency) | agency | [local-agency](../local-agency/SKILL.md) |
FreeToken and Colibri share the [loopback runtime contract](references/loopback-runtime-contract.md).
Rules:
- A runtime is used only when its READY probe passes; otherwise stay on the
cloud implementer and record `local: skipped(<reason>)` once.
- One-shot jobs only: one short spec in, one digest out. No parent relay.
- Avoided-spend metering and USD/EGP lines are required only when a local
inference channel was actually used ([process owner](../../references/process-owner-scrum-master.md)).
- Descriptions, paths and host exposure live in the
[catalog](../../references/catalog.md).
Read more
name: local-runtimes description: >- Use when choosing an optional local inference runtime for a narrow mechanical or offline job. license: MIT
Local runtimes
Cloud implementers write code directly. A local runtime is optional and only pays for narrow mechanical or offline jobs; never let it review its own diff. Pick one row, then open only that route.
| Need | Route | Open | | --- | --- | --- | | Which model size fits this machine | hardware probe | [local-coding-delegate](references/local-coding-delegate.md) | | Already READY loopback server (Ollama, LM Studio, llamacpp) | loopback | [local-openai-compat](references/local-openai-compat.md) | | Standalone FreeToken process | FreeToken | [freetoken](references/freetoken.md) | | Frontier MoE through disk/RAM/VRAM tiers | Colibri | [colibri](references/colibri.md) | | OmniRoute runner with delegate continuity | OmniRoute | [omniroute](references/omniroute.md) | | Local agents (OpenCode / OSS agency) | agency | [local-agency](../local-agency/SKILL.md) |
FreeToken and Colibri share the [loopback runtime contract](references/loopback-runtime-contract.md).
Rules:
- A runtime is used only when its READY probe passes; otherwise stay on the
cloud implementer and record `local: skipped(<reason>)` once.
- One-shot jobs only: one short spec in, one digest out. No parent relay.
- Avoided-spend metering and USD/EGP lines are required only when a local
inference channel was actually used ([process owner](../../references/process-owner-scrum-master.md)).
- Descriptions, paths and host exposure live in the
[catalog](../../references/catalog.md).
Ships withshaft-engine
One Java engine for web, mobile, API, CLI, database, and desktop. Drivers, waits, and evidence are handled. Every run ends in an Allure report. Upgrade to SHAFT_ENGINE · ▶ Watch the 26-second clip with sound and captions · 100-second overview
Get the whole plugin
Other skills on shaft-engine.
@shafthqInstall SkillSkill
chaos-engine
Canonical provider-neutral skill router and working contract. Use at the start of every task, on every host, in every main thread…
@shafthqInstall SkillSkill
ci-cd
Use when PR merge waits are long or CI/CD is being designed, audited, or sped up: targets, PR/main/nightly tiers, opt-in labels,…
@shafthqInstall SkillSkill
colibri
Frontier MoE through a disk/RAM/VRAM hierarchy via the optional Colibri process. Use when a large-model offline job needs…
@shafthqInstall SkillSkill
freetoken
Standalone FreeToken process: install, READY probe and bounded dispatch. Use when the local-runtimes table points a job at…
@shafthqInstall SkillSkill
git-cleanup
Use when a git worktree is dirty or another local branch or worktree exists. Ask before cleanup unless the session is unattended.
@shafthqInstall Skill