Build a repository's existing Antora documentation site, setting it up first (via `iru-setup-antora`) if it doesn't exist yet. Invoke as `/iru-build-docs`. Does no code exploration and makes no content edits to any existing page — it only ensures the…
Check for a license file (LICENSE, LICENSE.txt, LICENSE.md, COPYING, etc.) in the repository root, and if one exists, verify every source and test file carries a header consistent with it. Learns the header format from files that already have one; if none…
Scan the repository for accidentally committed secrets (API keys, passwords, tokens, private keys, etc.) using the `detect-secrets` CLI (https://github.com/Yelp/detect-secrets). Checks whether `detect-secrets` is installed and, if it isn't, first checks for…
Execute the tasks in implementation_plan.md at the repository root, one task group at a time — implement every task in a group (in parallel where the plan marks the group parallelizable), validate the whole group once (tests, coverage, code quality), and…
Draft and file a new GitHub issue that is ready to be picked up by the `/iru-issue`, `/iru-plan`, `/iru-code` flow. Runs the `iru-explore` skill first to ground the issue in the actual codebase, then asks the user for the purpose of the task to be…
Implement every task in one database-tagged plan-group bucket by calling `iru-database-code-one-task` once per task, one at a time, in the plan's order — always sequential, regardless of the group's `Parallelizable` verdict, since database changes (schema…
Generate (and, when a connected database MCP allows it, execute) the queries a single database-tagged plan task calls for — grounded in the actual schema/models discovered via the `iru-explore` skill's findings (reused from earlier in the conversation if…
Implement a single task from a .NET `implementation_plan.md`-style task list — just the implementation and its tests. Re-checks the current code state, implements exactly what the task specifies, writes/updates test-framework tests (xUnit/NUnit/MSTest,…