skills/ship-faster/skills/_archive/workflow-template-seeder/SKILL.md
Seed a new runnable template under templates/NNN-slug/ from a short spec by chaining existing skills (intake → ship-faster stages) while keeping it clean and shareable (no secrets, minimal scope). Use when creating a new template quickly.
npx skillsauth add enuno/claude-command-and-control workflow-template-seederInstall this skill globally with one command. Works with Claude Code, Cursor, and Windsurf.
3 of 9 scanners reported clean
Some scanners were skipped, did not run, or reported a non-clean status. Review each row below.
Goal: Turn a short template spec into a runnable, documented template under templates/.
This workflow is skills-first:
repo_root: Ship Faster repository root (where templates/ lives)run_dir: runs/template-seeder/active/<run_id>/template_spec.md: One-page spec (what it is, target user, core pages, required integrations)03-plans/template-plan.md05-final/template-summary.mdtemplates/<NNN>-<slug>/ containing:
README.md (5‑minute runnable).env.local.example (keys only)metadata.jsonrun_dir.<slug> from spec (kebab-case)<NNN> as the next available number under templates/ (001, 002, …)01-input/context.json for this workflow:
entry_type: idearepo_root: <path-to-new-template-dir>need_deploy: false (templates should not auto-deploy)Preferred path:
Execution order (recommended):
workflow-project-intake (optional if spec is already complete)workflow-ship-faster with the template directory as repo_root00-index.md / 05-final/template-summary.mdMust do:
.env.local.exampleREADME.md includes:
metadata.json is accurate and generic (no private branding unless intended)At minimum (document results in 05-final/template-summary.md):
dev startsbuild succeeds (if the template requires external credentials, document the minimal required keys)tools
MemPalace local-first AI memory system. Use when setting up persistent memory for Claude Code sessions, mining project files or conversation transcripts, querying past context, configuring MCP tools, managing the knowledge graph, or troubleshooting palace operations.
tools
LangSmith Python SDK — trace, evaluate, and monitor LLM applications. Covers @traceable decorator, trace context manager, Client API, evaluate() / aevaluate(), comparative evaluation, custom evaluators, dataset management, prompt caching, ASGI middleware, and pytest plugin.
development
LangGraph (Python) — build stateful, controllable agent graphs with checkpointing, streaming, persistence, interrupts, fault tolerance, and durable execution. Covers both Graph API (StateGraph) and Functional API (@entrypoint/@task).
development
LangGraph Graph API (Python) — build explicit DAG agent workflows with StateGraph, typed state, nodes, edges, Command routing, Send fan-out, checkpointers, interrupts, and streaming. Use when you need explicit control flow and graph topology.