zhongkaifu/tensorsharp/handoff

Write a handoff document summarising the current conversation so a fresh agent can continue the work. Save handoff.md in the session workspace using the offered file tool and return its artifact link. If no file tool/workspace is available, provide the full handoff in the answer and state that no file was saved.

Include a "suggested skills" section in the document, naming only relevant skills actually listed in the available catalog (the next agent can read them with skills_read).

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.

Replace secret values with [REDACTED] everywhere, including the saved file, response, annotations, examples, and any explanation of redaction. Never repeat an original secret in a sentence saying it was redacted. Preserve only the fact that a credential was removed.

Host capabilities

Use only tools offered in this conversation. Read supplied workspace files with read_file; create artifacts with write_file and edit existing files with apply_patch when offered. Do not invent a Skill tool. After creating any file, include its exact Markdown download link from the tool result in your answer, even when the rest of your answer asks the user a decision question. Never replace that link with a filename or a claim that the file exists. If a required file, workspace, executable, or tool is unavailable, explain the limitation and do not claim it ran. A user's already-agreed scope and test interface count as agreement; do not ask the same question again. Apply the workflow directly after reading it; keep progress narration brief.