AI Agent Skills

Use for dependency upgrades, vulnerability fixes, version conflicts, lockfiles, package managers, and migration risk.

Use to implement/review frontend UI, routing, state, API integration, responsive layout, accessibility, and browser behavior.

Use when the requested feature genuinely spans at least two delivery layers such as frontend, backend, API, data, scripts, or tests. Do not expand a single-layer change…

Use for non-trivial Git state such as branch strategy, worktrees, merge/rebase decisions, conflicts, reviewer-facing PR preparation, tags, and release notes. Do not trig…

Use to plan modernization, framework upgrades, service extraction, schema migrations, rewrites, and rollback paths.

为 cfKanban 源码仓库准备和发布 RC 或正式版，校验 GitHub 工件与 stable 入口，并按授权升级默认的 cfkanban.dev 长期测试实例。用于维护者发版，不用于普通用户安装、自部署或日常看板操作。

Summarize a software release for engineers who skipped the release meeting. Use when turning a list of merged changes into a short release note that separates behavior c…

Use this skill to author and validate DMN (Decision Model and Notation) decisions for Camunda 8 — decision tables and literal expressions inside a Decision Requirements…

Use this skill to write, debug, evaluate, and validate FEEL (Friendly Enough Expression Language) expressions for Camunda 8 — the expression language Zeebe uses in BPMN,…

Use this skill to create and edit Camunda Form JSON schemas for user tasks and start events in Camunda 8. Use for: field layouts (textfield, textarea, number, checkbox,…

Use this skill to deploy BPMN, DMN, and form resources to a Camunda 8 cluster and operate live processes via c8ctl. Use for: deploying resources, starting process instan…

Check an installed AutoBot workspace with its read-only doctor and focused runtime diagnostics. Use for installation health, capability readiness or a requested health r…

Coordinate authorized parallel workers on bounded AutoBot subtasks and verify their outputs. Use when the user requests delegation or the current environment explicitly…

Keep a substantial AutoBot assignment recoverable with one durable objective, exact checkpoints, supported continuation and verified deliverables. Use when the user asks…

Retrieve and update scoped AutoBot memory and apply user corrections with provenance. Use when the user asks to remember a durable fact, correct a saved preference or ca…

Stagnation detector + persona switcher. Triggers when the same file is edited 3+ times for the same issue, the same hypothesis fails 3+ times in mcp_think, the auditor r…