← all tools

cc-skill:claude-code-handoff

Claude Code skill · anthropic · active

0
last 30 days
0 calls
0 of 30 days active
explain like I am new to this
what it does

Converts a spec or plan into a ready-to-copy prompt for Claude Code that stops you from over-building. It breaks the work into 3-5 ordered phases, names exactly what to validate first, and bakes in line-count and complexity limits so Claude Code stays focused and ships something small that works.

who it is for

Anyone handing off a design or spec to Claude Code and wants to avoid bloated, over-engineered first versions.

when it fires

When you say things like 'hand off to Claude Code', 'what do I tell Claude Code to build', 'create build instructions', or when you finish a spec and need to sequence the work.

say something like
  • "Hand off this spec to Claude Code"
  • "What's the Claude Code prompt for this?"
  • "Convert this into build instructions with stop points"
what you might get back
Build LinkedIn Post Scheduler per spec. Sequence: 1. Database schema and user auth. 2. One-page dashboard showing scheduled posts. 3. One API route that posts to LinkedIn deterministically. 4. Optional: LLM agent to suggest captions. Stop after #3. Validate end-to-end with one user, one post before adding more features. Keep v1 under 600 lines. No abstractions yet. Use Supabase and Clerk only.
how to know it worked

You got back a copyable prompt with numbered phases, an explicit STOP point for validation, a defined smallest test scope, and constraints on lines and complexity.

is this skill working for me
never used
cloud runs
0
0 deployments
local fires
0
Claude Code (optional)
posts published
0
from drafts
attributed
$0.00
signups + revenue
Deploy this skill as a cloud automation to put it to work — runs on a schedule, dispatches output to Telegram or email, and logs every result here.

Deploy this skill

no laptop required

Run this skill on a schedule in the cloud. Pipe output to Telegram, email, or any webhook. Every run is logged here with full output, cost, and thumbs feedback.

How this performs

Cloud-automation runs, real outputs, and feedback.

No cloud runs yet for this skill.

Once you deploy it (above), every run will show up here with the actual output, exact cost, and a thumbs button so you can rate quality over time.

what this is

Claude Code skill at /Users/olanrewajukareem/.claude/skills/claude-code-handoff/SKILL.md. Auto-triggered by description matching when you type in Claude Code, OR embedded into agent system prompts (LeadFlow framework skills are wired this way). Auto-synced from disk every 6h via launchd.

Use this skill when Jay needs to convert a spec, plan, or idea into a Claude Code build prompt. Triggers on "hand off to Claude Code", "Claude Code prompt", "build instructions", "what do I tell Claude Code", or when finishing a spec that needs build

Local Claude Code use (optional)

Install the SKILL.md file locally so this skill is available the next time you open Claude Code on your Mac. Most users skip this and just use cloud deployments above.

Install on your machine

Save this skill to ~/.claude/skills/claude-code-handoff/SKILL.md so Claude Code auto-loads it whenever its description matches your prompt.

30-day activity
never used
2026-04-03today
cost model
unitincluded
capabilities
{
  "source": "global",
  "description": "Use this skill when Jay needs to convert a spec, plan, or idea into a Claude Code build prompt. Triggers on \"hand off to Claude Code\", \"Claude Code prompt\", \"build instructions\", \"what do I tell Claude Code\", or when finishing a spec that needs build sequencing. Produces sequenced prompts with stop points and constraints baked in."
}
how it gets called
{
  "method": "embed_in_prompt",
  "skill_path": "/Users/olanrewajukareem/.claude/skills/claude-code-handoff/SKILL.md"
}
This tool has never been called in the last 30 days.

That means either: (a) the system has not had a task that matched its strengths, (b) a more cost-effective alternative was picked by the router, or (c) the related automation is toggled OFF on /automations. The Recommender reviews idle tools weekly and may suggest killing it.