fresh-start
Skill0 starsChanged 26 days agoMITView on GitHub
Write a handoff document for the current conversation and offer a fresh session that starts from it.
2 other projects use a version of this.
Adopted by
Most recently taken up by
- egorfedorov/claude-context-optimizertheir own version, first seen Nov 1, 2026
- AbdouMoumen/claude-skills-plugintheir own version, first seen Nov 1, 2026
Other versions2 projects use a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 2
- egorfedorov/claude-context-optimizer★ 127same name
- AbdouMoumen/claude-skills-plugin★ 1same 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.
The file
We split this skill into the rules it gives an agent
2 rules. About 0 are common, 2 are distinctive, and 0 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈2
Distinctive · estimate
This author's own choices. Worth a look.
0
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Distinctive: line 12
Do not duplicate content already captured in other artifacts (specs, plans, ADRs, issues, commits, diffs).
- Distinctive: line 16
If the user passed arguments, treat them as a description of what the next session will focus on and tailor the doc accordingly.
≈ “Common” is an estimate: at least 1 in 5 of the 350,495 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
Write a handoff document summarising the current conversation so a fresh agent can continue the work. Save it where it will still be there in a week and cannot be committed by accident: ~/.claude/handoffs/<project-folder-name>/YYYY-MM-DD-<short-slug>.md (create the folders if needed; use %USERPROFILE%\.claude\handoffs\... on Windows). Do not save it inside the project or a worktree.
Include a "suggested skills" section in the document, naming which skills the next agent should call the Skill tool for.
Do not duplicate content already captured in other artifacts (specs, plans, ADRs, issues, commits, diffs). Reference them by path or URL instead.
Redact any sensitive information, such as API keys, passwords, or personally identifiable information.
If the user passed arguments, treat them as a description of what the next session will focus on and tailor the doc accordingly.
After the file is written, offer the fresh session as a card the user starts with one click. The prompt for it gives the handoff file's absolute path and says to read it in full and continue from it (starting with what the user's arguments named, else the first open item). Use the first of these tools the session has; a tool listed only as deferred is loaded first with ToolSearch (select:<name>), alone in its message:
mcp__ccd_session__start_session(the current desktop app): call it once withinitiation: "own_initiative",context: "fresh",titlesuch as "Continue:<topic>",promptas above, andbackground(at least 80 characters): a one-line summary of what the new session will pick up and that the handoff file holds the rest.mcp__ccd_session__spawn_task(older app versions): call it once with the same prompt, a title such as "Continue:<topic>", and a one-line summary of what the new session will pick up.
Then tell the user in one or two lines where the file is, that one click on the card starts a new session with it, and that this conversation stays in the sidebar. If neither tool is available, give the path and the one line to paste into a new session instead. Do not clear or compact the current conversation.
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.