code-handoff
Skill1 starsChanged 49 days agoMITView on GitHub
Package a design/ideation conversation into a self-contained handoff brief for a coding agent (Claude Code or a fresh coding session) so implementation starts from locked decisions instead of re-deriving context or re-exploring already-rejected approaches. Use whenever the user says they're moving from planning/chat into building, asks to "hand this off to Claude Code," or wants a task prompt/context file to paste into a coding session. Do not use this to write the actual implementation — only to produce the handoff artifact.
1 other project uses a version of this.
Adopted by
Most recently taken up by
- martinffx/ateliertheir own version, first seen Oct 9, 2026
Other versions1 project uses a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 1
- martinffx/atelier★ 51same name
How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.
In this repository32 other files it gives its agents.
- agent-system-designSkill
- api-contract-designSkill
- architecture-designSkill
- architecture-optimizationSkill
- ci-speedupSkill
- cross-ai-handoffSkill
- crypto-storage-auditSkill
- database-designSkill
- dataset-sourcingSkill
- distributed-debuggerSkill
- embedded-constrained-codingSkill
- freedom-to-operate-analysisSkill
- frontend-architectureSkill
- github-masterSkill
- idea-finderSkill
- ieee-paper-drafterSkill
- memory-leak-hunterSkill
- ml-model-selectionSkill
- ml-security-auditSkill
- mobile-platform-architectureSkill
- observability-designSkill
- patent-drafterSkill
- patent-novelty-evaluatorSkill
- performance-optimizationSkill
- project-scaffoldingSkill
- researcher-evaluatorSkill
- researcherSkill
- safety-compliance-scopingSkill
- scale-refactorSkill
- secure-code-reviewSkill
- slow-query-optimizerSkill
- test-architectSkill
The file
Files
Code Handoff (Chat → Coding Agent)
The failure mode this skill prevents: Claude Code starts a fresh session with no memory of the design conversation, re-derives requirements from scratch, re-explores an approach that was already ruled out, and quietly makes a decision the user thought was already settled. The fix is a handoff document that contains decisions, not vibes.
What to extract from the conversation
Pull these out explicitly — don't paraphrase into vaguer language, keep the actual constraints as stated:
- Goal — one line, the actual deliverable.
- Decisions already locked — bullet list of choices already made in this conversation (stack, approach, architecture, format). These are not up for re-litigation by Claude Code.
- Explicitly open items — anything still undecided. Mark these clearly as "needs input" so Claude Code doesn't silently pick an answer and present it as settled.
- Dead ends already ruled out, and why — this is the highest-value section and the one most often skipped. If an approach was considered and rejected, say so and say why, or Claude Code will burn time re-discovering the same dead end.
- Environment / stack constraints — language, framework, existing repo conventions, dependencies that are fixed vs. flexible.
- File/repo layout — if one exists or is expected, state it; if none exists yet, say so explicitly rather than leaving it ambiguous.
- Acceptance criteria / definition of done — testable, not aspirational. "Works well" is not acceptance criteria; "handles input X without exceeding Y ms" is.
- Relevant project context — if this connects to an existing project file/patent/architecture doc the user maintains, name it and summarize only what's load-bearing for this task, not the whole history.
Output format
A single markdown block, ready to paste as the first message of a Claude Code session (or saved as a context file, e.g. TASK.md):
# Task: [one-line goal]
## Locked decisions
- ...
## Open — needs input before/while building
- ...
## Ruled out (do not re-explore)
- [approach] — rejected because [reason]
## Environment
- ...
## Definition of done
- ...Anti-pattern
Don't hand off a vision statement ("build something that detects hazards using multiple cameras"). Hand off the decisions that were actually made in the conversation, the constraints that are actually fixed, and a definition of done that can be checked mechanically. If the conversation didn't actually settle something, mark it "needs input" instead of inventing a plausible-sounding decision to fill the gap — that's exactly the failure mode this skill exists to prevent.
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

