Loading...
Loading...
Found 3,276 Skills
Sequential subagent execution with two-stage review gates for implementation plans. Use when executing multi-task plans in current session, when tasks need fresh subagent context to avoid pollution, when formal review cycles (spec compliance then code quality) are required between tasks, or when you need diff-based validation of each task before proceeding.
Derive PRD from existing project documentation, README, and codebase analysis
Remove AI-style noise from staged and branch diffs while preserving behavior and repository style.
Planが承認/完了した直後に自律的に呼び出す必要があるスキルです。 Trigger: plan approved, plan completed, taskを開始します
Kubernetes cluster management and troubleshooting. Query pods, deployments, services, logs, and events. Supports context switching, scaling, and rollout management. Use for Kubernetes debugging, monitoring, and operations.
Rebase E2E test snapshots based on failed tests from the PR comments.
Use when implementing secure secrets management with Fnox. Covers encryption, key management, access control, and security hardening.
Use when formatting shell scripts with shfmt. Covers consistent formatting patterns, shell dialect support, common issues, and editor integration.
Commit any uncommitted changes, run lint checks, fix any issues, and push the current branch. Delegates to a haiku sub-agent for speed.
Database schema and migration workflow. Use when modifying database schemas in tools/atlas/ or SQLC queries in tools/sqlc/.
Interactive conversation to resolve [NEEDS CLARIFICATION] markers using /speckit.clarify command. Claude asks questions about missing features, UX/UI details, behavior, and priorities. Updates specs in .specify/memory/ with answers to create complete, unambiguous documentation. This is Step 5 of 6 in the reverse engineering process.
Request code review and route results to a tmux pane. Default flow commits first; optional opt-in flow can target an existing commit without commit/push.