add-component
Checklists for adding a new MCP tool, a new Flyway database migration, or a new Gradle dependency to the Task Orchestrator…
Compatibility assessment for items with the needs-api-compat-review trait. Evaluates the MCP tool surface and the REST surface separately, since their compatibility models differ. Invoked via skillPointer when filling api-compatibility notes.
$ npx -y skills add jpicklyk/task-orchestrator --skill api-compat-review --agent claude-codeHow it fires
How this skill gets triggered: by you, by Claude, or both.
/api-compat-reviewContext preview
The summary Claude sees to decide when to auto-load this skill.
Compatibility assessment for items with the needs-api-compat-review trait. Evaluates the MCP tool surface and the REST surface separately, since their compatibility models differ. Invoked via skillPointer when filling api-compatibility notes.
name: api-compat-review description: Compatibility assessment for items with the needs-api-compat-review trait. Evaluates the MCP tool surface and the REST surface separately, since their compatibility models differ. Invoked via skillPointer when filling api-compatibility notes. user-invocable: false
Assess API changes by surface — the MCP tool surface (dynamically re-discovered by clients) and the REST surface (hardcoded clients) have different compatibility models. Do not apply REST-style breaking-change caution to MCP tools, and do not apply MCP's rename-friendliness to REST.
Determine which surface(s) the change touches:
A single change (e.g., a domain model field rename) can touch both surfaces independently — assess each.
LLM clients re-read the `tools/list` schema every session — there is no persistent client binding to break. A pure parameter rename does NOT require keeping the old name working. Verify instead:
HTTP clients hardcode field and param names, so compatibility DOES matter here:
Compose the `api-compatibility` note with findings from Step 2 and/or Step 3, scoped to whichever surface(s) the change actually touches. If a surface wasn't touched, say so explicitly rather than omitting it silently.
Server-enforced workflow discipline for AI agents. Prompt-based frameworks hope the LLM follows instructions. This one blocks the call if it doesn't.
Checklists for adding a new MCP tool, a new Flyway database migration, or a new Gradle dependency to the Task Orchestrator…
Guides the full lifecycle of a feature-implementation tagged MCP item (the feature container) — from queue through review.…
End-to-end workflow for taking MCP work items from backlog to merged PR. Handles git branching, schema-driven planning,…
SQLite migration assessment for items with the needs-migration-review trait. Evaluates schema changes, table recreation patterns,…
Performance impact assessment for items with the needs-perf-review trait. Evaluates hot paths, query patterns, and measurement…
Assessment of plugin skill and hook changes needed after MCP or config changes. Evaluates skill references, hook context,…