Claude Skills by Dusttoo

Run the independent review gates on an existing PR and merge it only after code-review, required security review, configured verification, and CI are green. Use when the user asks to gate a PR, review and merge a PR through the orchestration pipeline, run merge-on-green, or run the equivalent of the Claude /gate command.

Run every actionable Jira ticket in a configured sprint through the reusable orchestrate-ticket pipeline with bounded concurrency, dependency-aware scheduling, durable checkpoints, restart recovery, and final completed/blocked/user-action summaries. Use when the user asks to orchestrate, run, resume, or finish a sprint or multiple Jira tickets in parallel. Do not use for a single ticket or for trackers other than a repository-configured Jira project.

Drive one ticket or change end-to-end through the full multi-agent orchestration pipeline (isolated implementation, independent code review, security review when warranted, optional verification, and merge on green). Use when the user asks in natural language to "orchestrate" a ticket, "run it through the pipeline", "take it end to end", or otherwise wants the gated implement-review-merge flow rather than a plain one-off edit. This is the natural-language entry to the same flow as the Claude ...

Bootstrap the orchestration harness in a target repo by creating configuration, checking project acceptance criteria, and wiring plugin-owned guardrails. Use when the user asks to initialize, install, bootstrap, or set up orchestration in a repository, including the equivalent of the Claude /orchestration-init command.

Report orchestration cost and performance from the API usage ledger and recommend concrete config changes. Use when the user asks how much orchestration is costing, where tokens or money are going, which role or ticket is expensive, whether prompt caching is working, why runs are slow or rate-limited, or for usage insights over a time window, including the equivalent of the Claude /orchestration-report command.

Recover the uncommitted work of a background or subagent that died, was rate-limited, crashed, timed out, or was interrupted mid-task, instead of re-running it from scratch. Use when an implementer agent stopped without opening its PR, when you see a rate-limit or crash on a spawned agent, or when a worktree has changes but no commit. The work is almost always still on disk in the agent's worktree.

Advance a configured release or candidate workflow through the shared orchestration engine. The skill name is retained for compatibility; release policy comes from repository configuration, not from this skill.

Turn a thin or vague ticket into one you can write a failing test from, before any branch is cut. Use when about to implement a ticket whose description is underspecified, when asked to scope/refine/groom a ticket, or when a task lacks clear acceptance criteria or a defined entry point. The bar is a single question - could you write a red test from this cold? If not, it is not ready to implement.