القائمة
Use for local Ollama-first execution with queued multi-agent CLI workflows. Configures auto-tundra for one-human-overseer and many-agent-subscriber code refinery mode.
التثبيت باستخدام Codex أو Claude انسخ هذا Prompt والصقه في Codex أو Claude أو مساعد آخر ليراجع صفحة Skill ويثبّتها لك.
استنادا إلى تصنيف SOC المهني
Use the `at` CLI to create, execute, monitor, and complete tasks on the Auto-Tundra daemon. Covers the full bead lifecycle from sling to done.
Use when troubleshooting build failures, test failures, daemon connectivity issues, or integration errors in Auto-Tundra.
Use the Auto-Tundra HTTP API directly (via curl) for operations not exposed in the CLI, such as task updates, terminal management, GitLab/Linear queries, and Kanban board manipulation.
Use when adding features, fixing bugs, or refactoring code in any Auto-Tundra crate. Covers build, test, lint, and validation workflows.
Use for GitHub/GitLab/Linear wiring in rust-harness to remove stub-token paths, enforce env-driven credential resolution, and add regression tests for real-client behavior with safe fallbacks.
Use when developing or refactoring at-cli. Runs deterministic smoke checks for run/agent/skill/doctor commands, including --dry-run and --out artifact paths.
| name | ollama-refinery-overseer |
| description | Use for local Ollama-first execution with queued multi-agent CLI workflows. Configures auto-tundra for one-human-overseer and many-agent-subscriber code refinery mode. |
| allowed_tools | ["Bash","Read","Edit"] |
| references | ["/Users/studio/rust-harness/scripts/refinery_queue_at.sh","/Users/studio/rust-harness/crates/at-core/src/config.rs","/Users/studio/rust-harness/crates/at-bridge/src/http_api.rs"] |
Use this skill when running local-first workflows with many agent workers and one human overseer.
ollama serve
ollama pull qwen2.5-coder:14b
Edit ~/.auto-tundra/config.toml:
[providers]
local_base_url = "http://127.0.0.1:11434"
local_model = "qwen2.5-coder:14b"
local_api_key_env = "LOCAL_API_KEY"
# Queue local LLM calls (at-intelligence LocalProvider)
export AT_LOCAL_LLM_MAX_CONCURRENT=1
# Queue task pipeline execution in API layer
export AT_PIPELINE_MAX_CONCURRENT=1
Always submit via the wrapper:
/Users/studio/rust-harness/scripts/refinery_queue_at.sh run -t "Refinery task" --dry-run -j
/Users/studio/rust-harness/scripts/refinery_queue_at.sh agent run -r qa-reviewer -t "Refinery review" --dry-run -j
curl -s http://localhost:9090/api/pipeline/queue | jq .
Expected fields:
limitwaitingrunningavailable_permitsrefinery_queue_at.sh.