ollama commands

Kochava-Studios/witsy

Command Claude Code

Before considering a task complete, verify ALL items below pass. This is a quality gate - do not skip any step.

Kochava-Studios/witsy

Command Claude Code

Make sure there are no hardcoded strings in the code. Use the i18n system to handle translations.

Kochava-Studios/witsy

Command Claude Code

Make sure you have added or updated tests for any new functionality or bug fixes in the codebase.

nodetool-ai/nodetool

Command Claude Code

Orient yourself in this repo — layout, entry points, and where the thing you are about to change lives.

nodetool-ai/nodetool

Command Claude Code

Start the NodeTool API server on :7777 in the background and verify it is up.

nodetool-ai/nodetool

Command Claude Code

Run the checks that must pass before committing (typecheck, lint, tests).

sprklai/zenii

Command Claude Code

This command runs a dual-agent audit: Codex CLI reviews code with fresh eyes, then Claude independently reads the actual code, judges each finding's validity, designs its own fixes where warranted, and applies only what passes rigorous verification.

sprklai/zenii

Command Claude Code

This command orchestrates the full release workflow: version bump across all files, CHANGELOG update, Cargo.lock generation, secret scan, commit, tag, and push to trigger GitHub Actions release builds.

sprklai/zenii

Command Claude Code

This command formats the code, updates documentation to reflect changes, scans for leaked secrets, commits, and pushes to the remote main branch. It will REFUSE to proceed if any secrets or tokens are detected. It runs fully automatically with NO user prompts unless secrets are found.

omar-A-hassan/medsci-agent

Command

Learn from the latest completed task using ACE post-run feedback (gated; used by auto-hook and manual fallback).

omar-A-hassan/medsci-agent

Command

Run deep literature workflow (discovery, acquisition, then PaperQA synthesis).

omar-A-hassan/medsci-agent

Command

Execute one isolated sandbox job with artifacts and teardown.

mdlmarkham/TailOpsMCP

Command Claude Code

Generate a custom checklist for the current feature based on user requirements.

mdlmarkham/TailOpsMCP

Command Claude Code

Identify underspecified areas in the current feature spec by asking up to 5 highly targeted clarification questions and encoding answers back into the spec.

mdlmarkham/TailOpsMCP

Command Claude Code

Create or update the feature specification from a natural language feature description.

Mirocow/ollama-code-client

Command

This is a sample slash command that demonstrates the command system.

cafitac/hermit-agent

Command Claude Code

Hands the P1–P5 findings from the most recent /code-review to Hermit so Claude doesn't burn tokens re-reading every file and retyping every edit. Claude stays on judgment; Hermit does the mechanical apply.

cafitac/hermit-agent

Command Claude Code

Unlike /code-polish, this variant is a distributed state machine. Hermit runs its own review-and-apply loop until it is self-clean, and Claude provides two independent review passes on top as a quality gate. Claude's token spend is capped at 2 review rounds.

cafitac/hermit-agent

Command Claude Code

Same outline as /feature-develop, but the Phase 3 implementation is delegated to Hermit over MCP so Claude's context never absorbs the grunt-work tool output.

jimmc414/claude-code-plugin-marketplace

Command

Thorough collaborative planning with iterative disambiguation - resolves all ambiguity before planning.

jimmc414/claude-code-plugin-marketplace

Command

Build an aspirational specification for existing code and identify gaps to address.

jimmc414/claude-code-plugin-marketplace

Command

Start a collaborative specification building session with iterative Q&A before implementation.

Medhovarsh/forkmind

Command

Start ForkMind or branch/inspect/regression-test an LLM call.

SkyWalker2506/ccplugin-opencode-bridge

Command

Manage OpenCode/Zen connections, switch models, and configure local Ollama.