handoff

Solid

Compact the current conversation into a handoff document for another agent to pick up and continue the work. Suggested skills, task summary, artifacts reference, and redacted sensitive info.

AI & Automation 0 stars 0 forks Updated today MIT

Install

View on GitHub

Quality Score: 78/100

Stars 20%
0
Recency 20%
100
Frontmatter 20%
70
Documentation 15%
100
Issue Health 10%
80
License 10%
100
Description 5%
100

Skill Content

# Handoff (任务交接) Create a handoff document that lets another agent (or a future session of the same agent) pick up the work seamlessly. ## When to Use - "Write a handoff doc for the next session" - "Document what's been done so the team can continue" - End of a session with incomplete work - "Save context so I don't have to repeat myself next time" ## When Not to Use - Simple one-off tasks finished in this session → no handoff needed - Documentation of completed features → use generate-doc instead - Git commit messages → use execute-git ## Procedure 1. **Scan artifacts** — list all files created or modified in this session: specs, plans, ADRs, issues, commits, diffs. Extract their paths and key conclusions. 2. **Summarize context** — concisely state: what was the task, what decisions were made, what is still in progress, what remains to be done. 3. **Identify suggested skills** — based on the remaining work, list 1-3 skills the next agent should invoke (use MY_SKILL skill names from INDEX.yaml). 4. **Redact sensitive info** — scan for API keys, passwords, tokens, PII, internal URLs, and replace with `<REDACTED>` markers. Note what was redacted and where. 5. **Write the document** — save to the OS temp directory (not the workspace). Use a timestamped filename: `handoff-YYYY-MM-DD-HHmm.md`. 6. **Report** — tell the user the file path and a brief summary of what's in the handoff. ## Output Template ```markdown # Handoff: <task-name> - Generated: <timestamp> - Next focus...

Details

Author
AVA-2568
Repository
AVA-2568/MY_SKILL
Created
2 days ago
Last Updated
today
Language
Python
License
MIT

Integrates with

Similar Skills

Semantically similar based on skill content — not just same category